{"items":[{"id":"chatgpt","name":"ChatGPT","vendor":"OpenAI","category":"chat-assistant","tags":["assistant"],"tagline":"The most widely used AI assistant.","description":"General-purpose assistant with search, deep research, agent mode, image generation, voice and apps.","pricingModel":"freemium","openSource":false,"website":"https://chatgpt.com","launchedYear":2022,"platforms":["Web","iOS","Android","macOS","Windows"],"features":["Agent mode","Deep research","Voice","Apps"],"useCases":["chat","writing","research"],"technologies":["reasoning","computer-use","rag"],"relatedModelIds":["gpt-6-astra","gpt-6.1-sol"],"popularity":99},{"id":"claude-code","name":"Claude Code","vendor":"Anthropic","category":"coding-assistant","tags":["cli","agent","terminal"],"tagline":"Agentic coding in your terminal, IDE and browser.","description":"Anthropic’s agentic coding tool that reads your codebase, edits files, runs commands and opens PRs. Available as a CLI, IDE extensions, desktop and web.","pricingModel":"paid","openSource":false,"website":"https://www.anthropic.com/claude-code","docs":"https://docs.anthropic.com/en/docs/claude-code","launchedYear":2025,"platforms":["CLI","VS Code","JetBrains","Web","Desktop"],"features":["Autonomous multi-file edits","Runs tests & commands","Hooks, skills and MCP","Subagents"],"useCases":["coding","agents"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":["claude-opus-5.5","claude-sonnet-5.5","claude-haiku-5.5"],"usage":{"appRank":2,"asOf":"2026-10-31"},"popularity":95},{"id":"github-copilot","name":"GitHub Copilot","vendor":"GitHub (Microsoft)","category":"coding-assistant","tags":["ide","autocomplete"],"tagline":"The most widely deployed AI pair programmer.","description":"Inline completions, chat and a cloud coding agent that works on GitHub issues, with a choice of models from several labs.","pricingModel":"freemium","openSource":false,"website":"https://github.com/features/copilot","launchedYear":2021,"platforms":["VS Code","JetBrains","Visual Studio","GitHub.com","CLI"],"features":["Inline completions","Copilot coding agent","Code review","Multi-model choice"],"useCases":["coding","enterprise"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":["claude-sonnet-5.5","gpt-6.1-sol","gemini-3.8-flash"],"popularity":94},{"id":"cursor","name":"Cursor","vendor":"Anysphere","category":"coding-assistant","tags":["ide","editor"],"tagline":"The AI-native code editor.","description":"A VS Code–based editor built around AI: tab completion, agent mode, background agents and codebase-aware chat.","pricingModel":"freemium","openSource":false,"website":"https://cursor.com","launchedYear":2023,"platforms":["macOS","Windows","Linux","Web"],"features":["Agent mode","Background agents","Codebase indexing","Bugbot code review"],"useCases":["coding","agents"],"technologies":["agent-orchestration","mcp","rag"],"relatedModelIds":["claude-sonnet-5.5","claude-opus-5.5","gpt-6.1-sol"],"usage":{"appRank":25,"asOf":"2026-10-31"},"popularity":93},{"id":"mcp","name":"Model Context Protocol","vendor":"Anthropic (open standard)","category":"agent-framework","tags":["protocol","standard","integrations"],"tagline":"The open standard for connecting AI to tools and data.","description":"An open protocol that lets any AI client connect to tool and data servers; supported across the major model providers and IDEs.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://modelcontextprotocol.io","github":"https://github.com/modelcontextprotocol","launchedYear":2024,"platforms":["TypeScript","Python","Java","C#","Go"],"features":["Tools, resources & prompts","Remote servers with OAuth","Thousands of community servers"],"useCases":["agents","enterprise"],"technologies":["mcp"],"relatedModelIds":[],"popularity":92},{"id":"gemini-app","name":"Gemini","vendor":"Google","category":"chat-assistant","tags":["assistant"],"tagline":"Google’s AI assistant across Search, Android and Workspace.","description":"Assistant integrated with Google apps, featuring Deep Research, Canvas, Gems and image/video generation.","pricingModel":"freemium","openSource":false,"website":"https://gemini.google.com","launchedYear":2023,"platforms":["Web","Android","iOS"],"features":["Deep Research","Workspace integration","Gems"],"useCases":["chat","research","multimodal"],"technologies":["reasoning","native-multimodal"],"relatedModelIds":["gemini-3.8-flash"],"popularity":92},{"id":"hugging-face","name":"Hugging Face","vendor":"Hugging Face","category":"data-ml","tags":["hub","open source"],"tagline":"The home of open models and datasets.","description":"Hub for 2M+ models and datasets, Spaces demos, Transformers library and inference endpoints.","pricingModel":"freemium","openSource":false,"website":"https://huggingface.co","github":"https://github.com/huggingface/transformers","launchedYear":2016,"platforms":["Web","Python","API"],"features":["Model hub","Datasets","Transformers","Inference providers"],"useCases":["on-device","research"],"technologies":["fine-tuning"],"relatedModelIds":[],"popularity":92},{"id":"claude-app","name":"Claude","vendor":"Anthropic","category":"chat-assistant","tags":["assistant"],"tagline":"Anthropic’s AI assistant for thinking and making.","description":"Assistant for writing, analysis and coding with artifacts, projects, research, connectors and Claude Code built in.","pricingModel":"freemium","openSource":false,"website":"https://claude.ai","launchedYear":2023,"platforms":["Web","iOS","Android","macOS","Windows"],"features":["Artifacts","Projects","Research","Connectors"],"useCases":["chat","writing","coding","research"],"technologies":["reasoning","mcp","computer-use"],"relatedModelIds":["claude-opus-5.5","claude-sonnet-5.5"],"popularity":90},{"id":"langchain","name":"LangChain","vendor":"LangChain","category":"llm-framework","tags":["rag","framework"],"tagline":"The most widely used LLM application framework.","description":"Composable building blocks — models, retrievers, tools and agents — with hundreds of integrations.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://www.langchain.com","github":"https://github.com/langchain-ai/langchain","launchedYear":2022,"platforms":["Python","TypeScript"],"features":["700+ integrations","Agents","Retrievers"],"useCases":["agents","long-context"],"technologies":["rag","agent-orchestration"],"relatedModelIds":[],"usage":{"appRank":23,"asOf":"2026-10-31"},"popularity":88},{"id":"ollama","name":"Ollama","vendor":"Ollama","category":"inference-platform","tags":["local","self-host"],"tagline":"Run open models locally with one command.","description":"The simplest way to download and run open-weight models on macOS, Windows and Linux, with an OpenAI-compatible API.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://ollama.com","github":"https://github.com/ollama/ollama","launchedYear":2023,"platforms":["macOS","Windows","Linux"],"features":["One-line model pulls","Local API","GPU acceleration"],"useCases":["on-device"],"technologies":["quantization"],"relatedModelIds":["gpt-oss-20b","qwen3.6-35b-a3b","gemma-4-31b"],"popularity":88},{"id":"openrouter","name":"OpenRouter","vendor":"OpenRouter","category":"ai-gateway","tags":["router","gateway","api"],"tagline":"One API for hundreds of models.","description":"Unified, OpenAI-compatible API routing to hundreds of models across providers with automatic fallbacks and price/latency routing.","pricingModel":"paid","openSource":false,"website":"https://openrouter.ai","launchedYear":2023,"platforms":["API"],"features":["400+ models","Provider fallbacks","Usage rankings"],"useCases":["high-volume"],"technologies":[],"relatedModelIds":[],"popularity":86},{"id":"microsoft-copilot","name":"Microsoft Copilot","vendor":"Microsoft","category":"chat-assistant","tags":["assistant","office"],"tagline":"AI across Windows and Microsoft 365.","description":"Assistant built into Windows, Edge and Microsoft 365 apps, grounded in your work data for business users.","pricingModel":"freemium","openSource":false,"website":"https://copilot.microsoft.com","launchedYear":2023,"platforms":["Windows","Web","Microsoft 365"],"features":["M365 grounding","Agents","Copilot Studio"],"useCases":["chat","enterprise","writing"],"technologies":["rag"],"relatedModelIds":[],"popularity":86},{"id":"midjourney","name":"Midjourney","vendor":"Midjourney","category":"image-video","tags":["image","art"],"tagline":"Distinctive, high-aesthetic image generation.","description":"Image and video generation known for its aesthetic quality, with a web editor and style references.","pricingModel":"paid","openSource":false,"website":"https://www.midjourney.com","launchedYear":2022,"platforms":["Web","Discord"],"features":["Style references","Editor","Video"],"useCases":["image-generation"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":86},{"id":"langgraph","name":"LangGraph","vendor":"LangChain","category":"agent-framework","tags":["orchestration","graph"],"tagline":"Stateful, controllable agent orchestration.","description":"Low-level framework for building long-running, stateful agents as graphs with persistence, streaming and human-in-the-loop.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://www.langchain.com/langgraph","github":"https://github.com/langchain-ai/langgraph","launchedYear":2024,"platforms":["Python","TypeScript"],"features":["Durable execution","Human-in-the-loop","Checkpointing","Managed platform"],"useCases":["agents","enterprise"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":85},{"id":"openai-codex","name":"Codex","vendor":"OpenAI","category":"coding-assistant","tags":["cli","agent"],"tagline":"OpenAI’s cloud and CLI coding agent.","description":"Delegates software tasks to agents that run in sandboxes, with a local CLI and IDE integration.","pricingModel":"paid","openSource":false,"website":"https://openai.com/codex","launchedYear":2025,"platforms":["CLI","Web","IDE"],"features":["Parallel cloud tasks","Open-source CLI","PR generation"],"useCases":["coding","agents"],"technologies":["agent-orchestration"],"relatedModelIds":["gpt-6.1-sol","gpt-6-astra"],"usage":{"appRank":5,"asOf":"2026-10-31"},"popularity":84},{"id":"pgvector","name":"pgvector","vendor":"Open source","category":"vector-database","tags":["postgres","rag"],"tagline":"Vector similarity search inside Postgres.","description":"Postgres extension adding vector types and HNSW/IVFFlat indexes — keep embeddings next to your relational data.","pricingModel":"open-source","openSource":true,"license":"PostgreSQL","website":"https://github.com/pgvector/pgvector","github":"https://github.com/pgvector/pgvector","launchedYear":2021,"platforms":["PostgreSQL"],"features":["HNSW indexes","SQL joins with vectors","Available on every major cloud"],"useCases":["long-context","enterprise"],"technologies":["vector-search"],"relatedModelIds":[],"popularity":84},{"id":"n8n","name":"n8n","vendor":"n8n","category":"automation","tags":["workflow","self-host","low code"],"tagline":"Fair-code workflow automation with AI agents.","description":"Visual workflow automation with 400+ integrations and native AI agent nodes; self-hostable.","pricingModel":"freemium","openSource":true,"license":"Sustainable Use License","website":"https://n8n.io","github":"https://github.com/n8n-io/n8n","launchedYear":2019,"platforms":["Cloud","Self-hosted"],"features":["AI agent nodes","400+ integrations","Code when needed"],"useCases":["agents","enterprise"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":[],"popularity":84},{"id":"perplexity","name":"Perplexity","vendor":"Perplexity","category":"chat-assistant","tags":["search","assistant"],"tagline":"Answer engine with citations.","description":"Conversational search that answers with sources, plus the Comet browser and deep research.","pricingModel":"freemium","openSource":false,"website":"https://www.perplexity.ai","launchedYear":2022,"platforms":["Web","iOS","Android","Comet browser"],"features":["Cited answers","Deep research","Spaces"],"useCases":["research","chat"],"technologies":["rag"],"relatedModelIds":[],"popularity":84},{"id":"elevenlabs","name":"ElevenLabs","vendor":"ElevenLabs","category":"voice-audio","tags":["tts","voice"],"tagline":"Lifelike AI voice, dubbing and voice agents.","description":"Text-to-speech, voice cloning, dubbing, music and a conversational voice-agent platform.","pricingModel":"freemium","openSource":false,"website":"https://elevenlabs.io","launchedYear":2022,"platforms":["Web","API","iOS"],"features":["TTS & cloning","Agents platform","Dubbing","Music"],"useCases":["multimodal","realtime"],"technologies":["realtime-voice"],"relatedModelIds":[],"popularity":84},{"id":"vercel-ai-sdk","name":"AI SDK","vendor":"Vercel","category":"llm-framework","tags":["typescript","react"],"tagline":"The TypeScript toolkit for AI apps.","description":"Unified TypeScript API for every major model provider with streaming UI hooks for React, Svelte and Vue.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://ai-sdk.dev","github":"https://github.com/vercel/ai","launchedYear":2023,"platforms":["TypeScript"],"features":["Provider-agnostic","Streaming UI","Tool calling","Structured outputs"],"useCases":["chat","agents"],"technologies":["constrained-decoding","mcp"],"relatedModelIds":[],"popularity":82},{"id":"vllm","name":"vLLM","vendor":"vLLM project","category":"inference-platform","tags":["serving","self-host"],"tagline":"High-throughput LLM serving engine.","description":"Open-source inference engine with PagedAttention and continuous batching; the de-facto standard for self-hosted serving.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://vllm.ai","github":"https://github.com/vllm-project/vllm","launchedYear":2023,"platforms":["Linux","GPU","TPU"],"features":["PagedAttention","Continuous batching","OpenAI-compatible server"],"useCases":["on-device","high-volume"],"technologies":["speculative-decoding","quantization"],"relatedModelIds":[],"popularity":82},{"id":"zapier","name":"Zapier","vendor":"Zapier","category":"automation","tags":["no code","integrations"],"tagline":"Automate across 8,000+ apps with AI.","description":"The largest no-code automation platform, with AI agents, chatbots, tables and an MCP server.","pricingModel":"freemium","openSource":false,"website":"https://zapier.com","launchedYear":2011,"platforms":["Cloud"],"features":["8,000+ app integrations","Zapier Agents","MCP server"],"useCases":["agents"],"technologies":["mcp"],"relatedModelIds":[],"popularity":82},{"id":"llamaindex","name":"LlamaIndex","vendor":"LlamaIndex","category":"llm-framework","tags":["rag","documents"],"tagline":"Data framework for RAG and document agents.","description":"Framework and cloud platform (LlamaParse, LlamaCloud) for ingesting, indexing and querying documents with LLMs.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://www.llamaindex.ai","github":"https://github.com/run-llama/llama_index","launchedYear":2022,"platforms":["Python","TypeScript"],"features":["Document parsing","Indexing","Agentic workflows"],"useCases":["research","extraction","long-context"],"technologies":["rag","agent-orchestration"],"relatedModelIds":[],"popularity":80},{"id":"pinecone","name":"Pinecone","vendor":"Pinecone","category":"vector-database","tags":["managed","rag"],"tagline":"Fully managed serverless vector database.","description":"Serverless vector database with integrated embedding, reranking and hybrid search.","pricingModel":"freemium","openSource":false,"website":"https://www.pinecone.io","launchedYear":2019,"platforms":["Cloud"],"features":["Serverless","Hybrid search","Integrated inference"],"useCases":["long-context","enterprise"],"technologies":["vector-search","rag"],"relatedModelIds":[],"popularity":80},{"id":"llama-cpp","name":"llama.cpp","vendor":"ggml","category":"inference-platform","tags":["local","quantization"],"tagline":"LLM inference in C/C++ on any hardware.","description":"Portable inference engine and GGUF format powering most local-LLM apps, from laptops to phones.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://github.com/ggml-org/llama.cpp","github":"https://github.com/ggml-org/llama.cpp","launchedYear":2023,"platforms":["CPU","Apple Silicon","CUDA","Vulkan"],"features":["GGUF quantization","Runs on CPU","Server mode"],"useCases":["on-device"],"technologies":["quantization","speculative-decoding"],"relatedModelIds":[],"popularity":80},{"id":"notebooklm","name":"NotebookLM","vendor":"Google","category":"productivity","tags":["notes","study"],"tagline":"AI research notebook grounded in your sources.","description":"Upload documents and get grounded answers, study guides, mind maps and audio/video overviews.","pricingModel":"freemium","openSource":false,"website":"https://notebooklm.google.com","launchedYear":2023,"platforms":["Web","iOS","Android"],"features":["Audio overviews","Source-grounded chat","Mind maps"],"useCases":["research","long-context"],"technologies":["rag"],"relatedModelIds":[],"popularity":80},{"id":"claude-agent-sdk","name":"Claude Agent SDK","vendor":"Anthropic","category":"agent-framework","tags":["sdk"],"tagline":"The agent harness behind Claude Code, as a library.","description":"Build production agents with the same loop, tools, context management and permissions that power Claude Code.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://docs.anthropic.com/en/docs/agent-sdk/overview","github":"https://github.com/anthropics/claude-agent-sdk-python","launchedYear":2025,"platforms":["Python","TypeScript"],"features":["Built-in file & shell tools","Subagents","MCP","Context compaction"],"useCases":["agents","coding"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":["claude-opus-5.5","claude-sonnet-5.5"],"popularity":78},{"id":"amazon-bedrock","name":"Amazon Bedrock","vendor":"AWS","category":"inference-platform","tags":["cloud","aws"],"tagline":"Foundation models on AWS.","description":"Managed access to models from Anthropic, Amazon, Meta, Mistral and others with AWS security, guardrails and agents.","pricingModel":"paid","openSource":false,"website":"https://aws.amazon.com/bedrock/","launchedYear":2023,"platforms":["AWS"],"features":["Many providers","Guardrails","AgentCore","VPC & compliance"],"useCases":["enterprise"],"technologies":["guardrails","rag"],"relatedModelIds":["claude-sonnet-5.5","nova-2-lite","llama-4-maverick"],"popularity":78},{"id":"whisper","name":"Whisper","vendor":"OpenAI","category":"voice-audio","tags":["stt","open weights"],"tagline":"Open-source multilingual speech recognition.","description":"Open-weight speech recognition model family supporting ~100 languages; widely embedded in local apps.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://github.com/openai/whisper","github":"https://github.com/openai/whisper","launchedYear":2022,"platforms":["Python","Local"],"features":["Multilingual STT","Translation","Runs locally"],"useCases":["on-device","multimodal"],"technologies":[],"relatedModelIds":[],"popularity":78},{"id":"sora","name":"Sora","vendor":"OpenAI","category":"image-video","tags":["video"],"tagline":"OpenAI’s video generation app.","description":"Generates video with synchronized audio from text and images, with a social creation app.","pricingModel":"freemium","openSource":false,"website":"https://openai.com/sora","launchedYear":2024,"platforms":["Web","iOS","Android"],"features":["Video with audio","Cameos","Remix"],"useCases":["image-generation","multimodal"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":76},{"id":"microsoft-365-copilot","name":"Microsoft 365 Copilot","vendor":"Microsoft","category":"productivity","tags":["office","enterprise"],"tagline":"Copilot inside Word, Excel, PowerPoint, Outlook and Teams.","description":"Microsoft’s work assistant grounded in your organisation’s Microsoft 365 data via Microsoft Graph, with agents for research and analysis and a builder for custom agents.","pricingModel":"paid","openSource":false,"website":"https://www.microsoft.com/microsoft-365/copilot","launchedYear":2023,"platforms":["Web","Desktop","iOS","Android"],"features":["Office app integration","Graph-grounded answers","Custom agents"],"useCases":["enterprise","writing","research"],"technologies":["rag","agent-orchestration"],"relatedModelIds":[],"popularity":75},{"id":"cline","name":"Cline","vendor":"Cline","category":"coding-assistant","tags":["byok","vscode"],"tagline":"Open-source autonomous coding agent for VS Code.","description":"Bring-your-own-model coding agent that plans, edits files and runs commands with human approval at each step.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://cline.bot","github":"https://github.com/cline/cline","launchedYear":2024,"platforms":["VS Code","JetBrains","CLI"],"features":["Plan/Act modes","Any model via API","MCP support"],"useCases":["coding","agents"],"technologies":["agent-orchestration","mcp","computer-use"],"relatedModelIds":[],"usage":{"appRank":6,"asOf":"2026-10-31"},"popularity":74},{"id":"openai-agents-sdk","name":"OpenAI Agents SDK","vendor":"OpenAI","category":"agent-framework","tags":["sdk"],"tagline":"Lightweight multi-agent workflows with handoffs.","description":"A minimal SDK for agents, handoffs, guardrails and tracing; provider-agnostic.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://openai.github.io/openai-agents-python/","github":"https://github.com/openai/openai-agents-python","launchedYear":2025,"platforms":["Python","TypeScript"],"features":["Handoffs","Guardrails","Built-in tracing"],"useCases":["agents"],"technologies":["agent-orchestration","guardrails"],"relatedModelIds":["gpt-6.1-sol","gpt-6-luna"],"popularity":74},{"id":"vertex-ai","name":"Vertex AI","vendor":"Google Cloud","category":"inference-platform","tags":["cloud","gcp"],"tagline":"Google Cloud’s AI platform.","description":"Gemini plus partner and open models with tuning, evaluation, grounding and agent tooling on Google Cloud.","pricingModel":"paid","openSource":false,"website":"https://cloud.google.com/vertex-ai","launchedYear":2021,"platforms":["Google Cloud"],"features":["Model Garden","Grounding with Search","Agent Engine"],"useCases":["enterprise"],"technologies":["rag","fine-tuning"],"relatedModelIds":["gemini-3.8-flash","claude-opus-5.5"],"popularity":74},{"id":"langsmith","name":"LangSmith","vendor":"LangChain","category":"observability","tags":["tracing","evals"],"tagline":"Tracing, evals and monitoring for LLM apps.","description":"Observability and evaluation platform for LLM applications and agents, framework-agnostic.","pricingModel":"freemium","openSource":false,"website":"https://www.langchain.com/langsmith","launchedYear":2023,"platforms":["Cloud","Self-hosted"],"features":["Tracing","Datasets & evals","Prompt hub"],"useCases":["enterprise","agents"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":74},{"id":"runway","name":"Runway","vendor":"Runway","category":"image-video","tags":["video"],"tagline":"AI video generation and editing for creators.","description":"Generative video models and an editing suite used by filmmakers and studios.","pricingModel":"freemium","openSource":false,"website":"https://runwayml.com","launchedYear":2018,"platforms":["Web","iOS"],"features":["Text & image to video","Video editing","Act-Two performance"],"useCases":["image-generation","multimodal"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":74},{"id":"notion-ai","name":"Notion AI","vendor":"Notion","category":"productivity","tags":["docs","notes"],"tagline":"AI agents inside your workspace.","description":"Writing, search across connected apps, meeting notes and agents that work across your Notion workspace.","pricingModel":"paid","openSource":false,"website":"https://www.notion.com/product/ai","launchedYear":2023,"platforms":["Web","macOS","Windows","iOS","Android"],"features":["Notion Agent","Enterprise search","Meeting notes"],"useCases":["writing","enterprise"],"technologies":["rag"],"relatedModelIds":[],"popularity":74},{"id":"windsurf","name":"Windsurf","vendor":"Cognition","category":"coding-assistant","tags":["ide"],"tagline":"Agentic IDE with the Cascade agent.","description":"An AI-native IDE whose Cascade agent tracks your actions to keep context across multi-step edits.","pricingModel":"freemium","openSource":false,"website":"https://windsurf.com","launchedYear":2024,"platforms":["macOS","Windows","Linux"],"features":["Cascade agent","Previews & deploys","Memories"],"useCases":["coding"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":[],"popularity":72},{"id":"google-antigravity","name":"Google Antigravity","vendor":"Google","category":"coding-assistant","tags":["ide","agent","multi-agent"],"tagline":"Agent-first IDE with a manager view for orchestrating many agents.","description":"Google’s agent-first development environment, built on a fork of VS Code and launched alongside Gemini 3 in November 2025. Antigravity 2.0 (I/O 2026) added a Manager surface to spawn, orchestrate and observe multiple agents working asynchronously across workspaces, next to a classic Editor view. Runs Gemini models with optional third-party models; still in public preview.","pricingModel":"freemium","openSource":false,"website":"https://antigravity.google","launchedYear":2025,"platforms":["macOS","Windows","Linux"],"features":["Multi-agent manager","Editor + agent views","Browser and terminal control","Command allow/deny lists"],"useCases":["coding","agents"],"technologies":["agent-orchestration","computer-use"],"relatedModelIds":["gemini-4-argon","gemini-3.8-flash"],"popularity":72},{"id":"crewai","name":"CrewAI","vendor":"CrewAI","category":"agent-framework","tags":["multi-agent"],"tagline":"Role-based multi-agent crews.","description":"Framework for orchestrating role-playing agents that collaborate on tasks, plus an enterprise platform.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://www.crewai.com","github":"https://github.com/crewAIInc/crewAI","launchedYear":2023,"platforms":["Python"],"features":["Crews & flows","Role-based agents","Enterprise control plane"],"useCases":["agents","enterprise"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":72},{"id":"lm-studio","name":"LM Studio","vendor":"Element Labs","category":"inference-platform","tags":["local","desktop"],"tagline":"Desktop app to discover and run local LLMs.","description":"Polished desktop app for downloading, chatting with and serving local models, with MLX support on Mac.","pricingModel":"free","openSource":false,"website":"https://lmstudio.ai","launchedYear":2023,"platforms":["macOS","Windows","Linux"],"features":["Model discovery","MLX & GGUF","Local server"],"useCases":["on-device"],"technologies":["quantization"],"relatedModelIds":[],"popularity":72},{"id":"azure-ai-foundry","name":"Azure AI Foundry","vendor":"Microsoft","category":"inference-platform","tags":["cloud","azure"],"tagline":"Build and run AI apps on Azure.","description":"Azure’s platform for OpenAI and partner models, agents, evaluation and responsible-AI tooling.","pricingModel":"paid","openSource":false,"website":"https://azure.microsoft.com/products/ai-foundry","launchedYear":2023,"platforms":["Azure"],"features":["Azure OpenAI","Agent service","Content safety"],"useCases":["enterprise"],"technologies":["guardrails","agent-orchestration"],"relatedModelIds":["gpt-6.1-sol","gpt-6-astra"],"popularity":72},{"id":"langfuse","name":"Langfuse","vendor":"Langfuse","category":"observability","tags":["tracing","self-host"],"tagline":"Open-source LLM engineering platform.","description":"Open-source tracing, prompt management, evals and metrics, self-hostable or cloud.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://langfuse.com","github":"https://github.com/langfuse/langfuse","launchedYear":2023,"platforms":["Self-hosted","Cloud"],"features":["OpenTelemetry tracing","Prompt management","LLM-as-judge evals"],"useCases":["enterprise"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":72},{"id":"deepseek-app","name":"DeepSeek","vendor":"DeepSeek","category":"chat-assistant","tags":["assistant","chatbot"],"tagline":"Free chat assistant for DeepSeek’s open-weight models.","description":"DeepSeek’s web and mobile assistant with a thinking mode for harder problems, web search and file reading, free to use.","pricingModel":"free","openSource":false,"website":"https://chat.deepseek.com","launchedYear":2023,"platforms":["Web","iOS","Android"],"features":["Thinking mode","Web search","File reading"],"useCases":["chat","reasoning","coding"],"technologies":[],"relatedModelIds":["deepseek-v4-pro","deepseek-v4.1-flash"],"popularity":72},{"id":"comfyui","name":"ComfyUI","vendor":"Comfy Org","category":"image-video","tags":["image","local"],"tagline":"Node-based open-source diffusion workflows.","description":"Powerful node-graph interface for building image, video and 3D generation pipelines with open models.","pricingModel":"open-source","openSource":true,"license":"GPL-3.0","website":"https://www.comfy.org","github":"https://github.com/Comfy-Org/ComfyUI","launchedYear":2023,"platforms":["Windows","macOS","Linux","Cloud"],"features":["Node graphs","Custom nodes","Runs locally"],"useCases":["image-generation","on-device"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":72},{"id":"suno","name":"Suno","vendor":"Suno","category":"voice-audio","tags":["music"],"tagline":"Make any song you can imagine.","description":"Generates full songs with vocals and instrumentation from text prompts, with a studio editor.","pricingModel":"freemium","openSource":false,"website":"https://suno.com","launchedYear":2023,"platforms":["Web","iOS","Android"],"features":["Full songs with vocals","Studio editor","Stems"],"useCases":["multimodal","writing"],"technologies":[],"relatedModelIds":[],"popularity":72},{"id":"lovable","name":"Lovable","vendor":"Lovable","category":"coding-assistant","tags":["app builder","no code"],"tagline":"Build apps by chatting with AI.","description":"Prompt-driven app builder aimed at non-engineers, with built-in backend, auth and hosting.","pricingModel":"freemium","openSource":false,"website":"https://lovable.dev","launchedYear":2024,"platforms":["Web"],"features":["Chat to app","Supabase integration","Hosting"],"useCases":["coding"],"technologies":[],"relatedModelIds":[],"popularity":71},{"id":"v0","name":"v0","vendor":"Vercel","category":"coding-assistant","tags":["app builder","frontend"],"tagline":"Generate full-stack web apps from prompts.","description":"Prompt-to-app builder producing React/Next.js code with one-click deploys to Vercel.","pricingModel":"freemium","openSource":false,"website":"https://v0.app","launchedYear":2023,"platforms":["Web"],"features":["UI generation","Full-stack apps","Deploy to Vercel"],"useCases":["coding"],"technologies":[],"relatedModelIds":[],"popularity":70},{"id":"gemini-cli","name":"Gemini CLI","vendor":"Google","category":"coding-assistant","tags":["cli","agent","terminal"],"tagline":"Open-source terminal coding agent powered by Gemini.","description":"An open-source AI agent for the terminal that reads and edits code, runs commands and uses MCP servers, with a generous free tier on a personal Google account.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://github.com/google-gemini/gemini-cli","github":"https://github.com/google-gemini/gemini-cli","launchedYear":2025,"platforms":["CLI"],"features":["Terminal agent","MCP support","Free tier"],"useCases":["coding","agents"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":["gemini-3.8-flash"],"popularity":70},{"id":"a2a-protocol","name":"Agent2Agent (A2A) Protocol","vendor":"Linux Foundation (Google-originated)","category":"agent-framework","tags":["protocol","standard","multi-agent"],"tagline":"An open protocol for agents to discover and talk to each other.","description":"A2A lets agents built on different frameworks and vendors find each other through Agent Cards and hand off work as tasks with a defined lifecycle. Google introduced it in 2025 and it is now governed under the Linux Foundation; it complements MCP, which connects agents to tools.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://a2a-protocol.org","github":"https://github.com/a2aproject/A2A","launchedYear":2025,"platforms":["Python","TypeScript","Java","Go","C#"],"features":["Agent Cards discovery","Task lifecycle","Streaming updates"],"useCases":["agents","enterprise"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":70},{"id":"qdrant","name":"Qdrant","vendor":"Qdrant","category":"vector-database","tags":["rust","rag"],"tagline":"High-performance vector search engine in Rust.","description":"Open-source vector database with rich payload filtering, quantization and a managed cloud.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://qdrant.tech","github":"https://github.com/qdrant/qdrant","launchedYear":2021,"platforms":["Self-hosted","Cloud"],"features":["Payload filtering","Quantization","Hybrid search"],"useCases":["long-context"],"technologies":["vector-search","quantization"],"relatedModelIds":[],"popularity":70},{"id":"groq","name":"Groq","vendor":"Groq","category":"inference-platform","tags":["fast","hardware"],"tagline":"Ultra-fast inference on custom LPUs.","description":"Inference cloud built on Language Processing Units delivering very high tokens/second for open models.","pricingModel":"freemium","openSource":false,"website":"https://groq.com","launchedYear":2024,"platforms":["API"],"features":["LPU hardware","Very high throughput","OpenAI-compatible"],"useCases":["realtime","high-volume"],"technologies":["custom-silicon"],"relatedModelIds":[],"popularity":70},{"id":"litellm","name":"LiteLLM","vendor":"BerriAI","category":"ai-gateway","tags":["gateway","router","self-hosted"],"tagline":"Open-source, self-hosted gateway to 100+ LLM APIs in the OpenAI format.","description":"A Python SDK and proxy server that calls 100+ model providers through one OpenAI-compatible API, with load balancing, fallbacks, spend tracking, budgets and virtual keys. The most common self-hosted choice for running a gateway inside your own infrastructure.","pricingModel":"open-source","openSource":true,"website":"https://www.litellm.ai","github":"https://github.com/BerriAI/litellm","docs":"https://docs.litellm.ai","launchedYear":2023,"platforms":["Python","Docker","Self-hosted"],"features":["OpenAI-compatible proxy","Fallbacks & load balancing","Budgets & virtual keys"],"useCases":["enterprise","high-volume"],"technologies":[],"relatedModelIds":[],"popularity":70},{"id":"openclaw","name":"OpenClaw","vendor":"OpenClaw Foundation","category":"chat-assistant","tags":["self-hosted","byok"],"tagline":"Self-hosted open-source assistant you message from your chat apps.","description":"Runs a personal or team AI assistant on your own machine and connects it to the chat apps you already use — Telegram, WhatsApp, Slack, Discord, iMessage, Teams and more — plus native desktop and mobile apps. Memory, state and credentials stay on your hardware; models and agent harnesses are swappable plugins. Stewarded by a non-profit foundation, with no paid tier.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://openclaw.ai","github":"https://github.com/openclaw/openclaw","docs":"https://docs.openclaw.ai","launchedYear":2025,"platforms":["macOS","Windows","Linux","iOS","Android"],"features":["Works in 20+ chat apps","Local memory and credentials","Any model"],"useCases":["chat","agents"],"technologies":["agent-memory","computer-use"],"relatedModelIds":[],"usage":{"appRank":9,"asOf":"2026-10-31"},"popularity":70},{"id":"google-flow","name":"Flow (Veo)","vendor":"Google","category":"image-video","tags":["video"],"tagline":"AI filmmaking with Veo.","description":"Google’s filmmaking tool built on the Veo video models with native audio and scene building.","pricingModel":"paid","openSource":false,"website":"https://labs.google/flow","launchedYear":2025,"platforms":["Web"],"features":["Veo video with audio","Scene builder","Camera controls"],"useCases":["image-generation","multimodal"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":70},{"id":"flux","name":"FLUX","vendor":"Black Forest Labs","category":"image-video","tags":["image","open weights"],"tagline":"State-of-the-art image models, open and pro.","description":"Family of image generation and editing models with open-weight dev variants and a commercial API.","pricingModel":"freemium","openSource":true,"website":"https://bfl.ai","launchedYear":2024,"platforms":["API","Open weights"],"features":["Text to image","In-context editing","Open dev weights"],"useCases":["image-generation"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":70},{"id":"wandb","name":"Weights & Biases","vendor":"Weights & Biases","category":"data-ml","tags":["mlops"],"tagline":"The AI developer platform.","description":"Experiment tracking, model registry and artifact management for training and fine-tuning.","pricingModel":"freemium","openSource":false,"website":"https://wandb.ai","launchedYear":2017,"platforms":["Cloud","Self-hosted"],"features":["Experiment tracking","Model registry","Sweeps"],"useCases":["enterprise"],"technologies":["fine-tuning","llm-evals"],"relatedModelIds":[],"popularity":70},{"id":"grammarly","name":"Grammarly","vendor":"Superhuman (Grammarly)","category":"productivity","tags":["writing assistant"],"tagline":"AI writing assistance everywhere you type.","description":"Grammar, clarity and tone suggestions plus generative rewriting and specialised writing agents across browsers, desktop apps and documents, for individuals and teams.","pricingModel":"freemium","openSource":false,"website":"https://www.grammarly.com","launchedYear":2009,"platforms":["Web","Chrome","macOS","Windows","iOS","Android"],"features":["Grammar & tone","Generative rewriting","Writing agents"],"useCases":["writing"],"technologies":[],"relatedModelIds":[],"popularity":70},{"id":"chroma","name":"Chroma","vendor":"Chroma","category":"vector-database","tags":["rag","prototyping"],"tagline":"The open-source embedding database.","description":"Developer-friendly embedding store that runs in-process for prototyping and scales via Chroma Cloud.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://www.trychroma.com","github":"https://github.com/chroma-core/chroma","launchedYear":2022,"platforms":["Python","TypeScript","Cloud"],"features":["In-process mode","Full-text + vector","Serverless cloud"],"useCases":["long-context","on-device"],"technologies":["vector-search","rag"],"relatedModelIds":[],"popularity":68},{"id":"together-ai","name":"Together AI","vendor":"Together AI","category":"inference-platform","tags":["api","open models"],"tagline":"Fast inference and fine-tuning for open models.","description":"Serverless and dedicated inference for open models plus fine-tuning and GPU clusters.","pricingModel":"paid","openSource":false,"website":"https://www.together.ai","launchedYear":2022,"platforms":["API","Cloud"],"features":["Serverless endpoints","Fine-tuning","GPU clusters"],"useCases":["high-volume"],"technologies":["fine-tuning","speculative-decoding"],"relatedModelIds":[],"popularity":68},{"id":"firecrawl","name":"Firecrawl","vendor":"Firecrawl","category":"search-api","tags":["scraping","crawler"],"tagline":"Turn websites into LLM-ready data.","description":"Crawl, scrape and extract structured data from any website as clean markdown or JSON.","pricingModel":"open-source","openSource":true,"license":"AGPL-3.0","website":"https://www.firecrawl.dev","github":"https://github.com/firecrawl/firecrawl","launchedYear":2024,"platforms":["API","Self-hosted"],"features":["Crawl & scrape","Structured extract","Browser actions"],"useCases":["extraction","research"],"technologies":["rag"],"relatedModelIds":[],"popularity":68},{"id":"replit-agent","name":"Replit Agent","vendor":"Replit","category":"coding-assistant","tags":["app builder"],"tagline":"Build and deploy apps from natural language.","description":"Cloud IDE agent that scaffolds, builds, tests and deploys applications inside Replit.","pricingModel":"freemium","openSource":false,"website":"https://replit.com","launchedYear":2024,"platforms":["Web","Mobile"],"features":["Instant deploys","Built-in database","Self-testing"],"useCases":["coding","agents"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":66},{"id":"weaviate","name":"Weaviate","vendor":"Weaviate","category":"vector-database","tags":["rag"],"tagline":"AI-native open-source vector database.","description":"Vector database with built-in vectorizer modules, hybrid search and multi-tenancy.","pricingModel":"open-source","openSource":true,"license":"BSD-3-Clause","website":"https://weaviate.io","github":"https://github.com/weaviate/weaviate","launchedYear":2019,"platforms":["Self-hosted","Cloud"],"features":["Hybrid search","Multi-tenancy","Vectorizer modules"],"useCases":["long-context","enterprise"],"technologies":["vector-search","rag"],"relatedModelIds":[],"popularity":66},{"id":"mlflow","name":"MLflow","vendor":"Databricks (Linux Foundation project)","category":"observability","tags":["tracing","evals","mlops"],"tagline":"Open-source tracing, evaluation and prompt management for GenAI and ML.","description":"The long-standing ML lifecycle platform now covers GenAI: OpenTelemetry-compatible tracing for agents, LLM-judge evaluations, prompt versioning and a model registry, self-hosted or managed on Databricks.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://mlflow.org","github":"https://github.com/mlflow/mlflow","launchedYear":2018,"platforms":["Python","TypeScript","Self-host","Cloud"],"features":["Agent tracing","LLM evaluation","Prompt registry","Model registry"],"useCases":["enterprise"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":66},{"id":"make","name":"Make","vendor":"Make (Celonis)","category":"automation","tags":["no code"],"tagline":"Visual automation platform.","description":"Visual scenario builder for complex automations with AI modules and agents.","pricingModel":"freemium","openSource":false,"website":"https://www.make.com","launchedYear":2012,"platforms":["Cloud"],"features":["Visual builder","AI agents","Routers & iterators"],"useCases":["agents"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":66},{"id":"meta-ai","name":"Meta AI","vendor":"Meta","category":"chat-assistant","tags":["assistant","consumer"],"tagline":"Meta’s assistant across WhatsApp, Instagram, Facebook and glasses.","description":"Assistant built into Meta’s apps and Ray-Ban Meta glasses, plus a standalone app, for chat, image generation and voice.","pricingModel":"free","openSource":false,"website":"https://www.meta.ai","launchedYear":2023,"platforms":["Web","iOS","Android","WhatsApp","Smart glasses"],"features":["In-app everywhere","Image generation","Voice"],"useCases":["chat","multimodal"],"technologies":[],"relatedModelIds":["muse-spark-1.3"],"popularity":66},{"id":"unsloth","name":"Unsloth","vendor":"Unsloth AI","category":"data-ml","tags":["fine tuning"],"tagline":"Fine-tune LLMs faster with less memory.","description":"Open-source library for fast, memory-efficient fine-tuning and RL of open models on a single GPU.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://unsloth.ai","github":"https://github.com/unslothai/unsloth","launchedYear":2023,"platforms":["Python","Colab"],"features":["2x faster training","Low VRAM","GRPO / RL"],"useCases":["on-device"],"technologies":["fine-tuning","quantization"],"relatedModelIds":[],"popularity":66},{"id":"google-adk","name":"Agent Development Kit","vendor":"Google","category":"agent-framework","tags":["sdk"],"tagline":"Google’s open-source framework for multi-agent systems.","description":"Code-first toolkit for building, evaluating and deploying agents, optimized for Gemini and Vertex AI but model-agnostic.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://google.github.io/adk-docs/","github":"https://github.com/google/adk-python","launchedYear":2025,"platforms":["Python","Java","TypeScript"],"features":["Multi-agent hierarchies","Built-in evaluation","A2A protocol"],"useCases":["agents"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":["gemini-3.8-flash"],"popularity":64},{"id":"agno","name":"Agno","vendor":"Agno","category":"agent-framework","tags":["python","multi-agent"],"tagline":"Python framework and runtime for multi-agent systems.","description":"Formerly Phidata. Builds agents, teams and step-based workflows in Python with memory, knowledge and human-in-the-loop built in, and serves them through its AgentOS runtime.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://www.agno.com","github":"https://github.com/agno-agi/agno","docs":"https://docs.agno.com","launchedYear":2022,"platforms":["Python"],"features":["Agent teams","Workflows","Memory & knowledge","AgentOS runtime"],"useCases":["agents"],"technologies":["agent-orchestration","agent-memory","rag"],"relatedModelIds":[],"popularity":64},{"id":"replicate","name":"Replicate","vendor":"Replicate","category":"inference-platform","tags":["api"],"tagline":"Run open-source models with an API.","description":"Run and fine-tune thousands of community models — especially image, video and audio — via a simple API.","pricingModel":"paid","openSource":false,"website":"https://replicate.com","launchedYear":2020,"platforms":["API"],"features":["Thousands of models","Cog packaging","Pay per second"],"useCases":["image-generation","multimodal"],"technologies":[],"relatedModelIds":[],"popularity":64},{"id":"tavily","name":"Tavily","vendor":"Tavily","category":"search-api","tags":["search","grounding"],"tagline":"Real-time search API for agents.","description":"Search, extract and crawl APIs optimized for RAG and agent tool calls.","pricingModel":"freemium","openSource":false,"website":"https://www.tavily.com","launchedYear":2023,"platforms":["API"],"features":["Search","Extract","Crawl"],"useCases":["research","agents"],"technologies":["rag"],"relatedModelIds":[],"popularity":64},{"id":"grok-app","name":"Grok","vendor":"SpaceXAI","category":"chat-assistant","tags":["assistant","x"],"tagline":"SpaceXAI’s assistant with real-time X data.","description":"Chat assistant in X and standalone apps with web and X search, image and video generation (Grok Imagine) and voice mode.","pricingModel":"freemium","openSource":false,"website":"https://grok.com","launchedYear":2023,"platforms":["Web","iOS","Android","X"],"features":["Real-time X search","Grok Imagine","Voice mode"],"useCases":["chat","research"],"technologies":["reasoning","rag"],"relatedModelIds":["grok-4.7","grok-imagine-image-2"],"popularity":64},{"id":"deepgram","name":"Deepgram","vendor":"Deepgram","category":"voice-audio","tags":["stt","voice"],"tagline":"Speech-to-text and voice AI APIs.","description":"Fast, accurate speech recognition, TTS and a voice-agent API for real-time applications.","pricingModel":"freemium","openSource":false,"website":"https://deepgram.com","launchedYear":2015,"platforms":["API","Self-hosted"],"features":["Streaming STT","TTS","Voice agent API"],"useCases":["realtime","multimodal"],"technologies":["realtime-voice"],"relatedModelIds":[],"popularity":64},{"id":"pydantic-ai","name":"Pydantic AI","vendor":"Pydantic","category":"agent-framework","tags":["python","typed"],"tagline":"Type-safe agent framework for Python.","description":"Agent framework from the Pydantic team bringing type safety, structured outputs and dependency injection to LLM apps.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://ai.pydantic.dev","github":"https://github.com/pydantic/pydantic-ai","launchedYear":2024,"platforms":["Python"],"features":["Typed outputs","Dependency injection","Logfire integration"],"useCases":["agents","extraction"],"technologies":["agent-orchestration","constrained-decoding"],"relatedModelIds":[],"popularity":63},{"id":"aider","name":"Aider","vendor":"Aider","category":"coding-assistant","tags":["cli","git"],"tagline":"AI pair programming in your terminal.","description":"Git-native terminal coding assistant that edits files and commits with sensible messages; works with almost any LLM.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://aider.chat","github":"https://github.com/Aider-AI/aider","launchedYear":2023,"platforms":["CLI"],"features":["Repo map","Auto commits","Works with local models"],"useCases":["coding","on-device"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":62},{"id":"temporal","name":"Temporal","vendor":"Temporal Technologies","category":"agent-infra","tags":["durable execution","workflows"],"tagline":"Durable execution for long-running workflows and agents.","description":"Persists every step of a workflow so code survives crashes, retries automatically and can wait for hours or days, which suits long-running agent loops and human approvals. Self-host the MIT-licensed server or use Temporal Cloud.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://temporal.io","github":"https://github.com/temporalio/temporal","docs":"https://docs.temporal.io","launchedYear":2019,"platforms":["Go","Java","TypeScript","Python",".NET","Cloud","Self-host"],"features":["Durable execution","Automatic retries","Long-running timers","Temporal Cloud"],"useCases":["agents","enterprise"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":62},{"id":"milvus","name":"Milvus","vendor":"Zilliz","category":"vector-database","tags":["scale"],"tagline":"Vector database for billion-scale workloads.","description":"Cloud-native, distributed vector database (managed as Zilliz Cloud) designed for massive scale.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://milvus.io","github":"https://github.com/milvus-io/milvus","launchedYear":2019,"platforms":["Self-hosted","Cloud"],"features":["Billion-scale","GPU indexing","Distributed"],"useCases":["enterprise","long-context"],"technologies":["vector-search"],"relatedModelIds":[],"popularity":62},{"id":"fireworks-ai","name":"Fireworks AI","vendor":"Fireworks AI","category":"inference-platform","tags":["api"],"tagline":"Production inference for open models.","description":"Low-latency inference platform for open models with fine-tuning and compound AI tooling.","pricingModel":"paid","openSource":false,"website":"https://fireworks.ai","launchedYear":2022,"platforms":["API"],"features":["Low latency","Fine-tuning","Structured outputs"],"useCases":["high-volume","realtime"],"technologies":["fine-tuning","speculative-decoding"],"relatedModelIds":[],"popularity":62},{"id":"braintrust","name":"Braintrust","vendor":"Braintrust","category":"observability","tags":["evals"],"tagline":"The evals platform for AI products.","description":"End-to-end platform for evaluating, logging and iterating on AI products with a fast playground.","pricingModel":"freemium","openSource":false,"website":"https://www.braintrust.dev","launchedYear":2023,"platforms":["Cloud"],"features":["Experiments","Online scoring","Playground"],"useCases":["enterprise"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":62},{"id":"exa","name":"Exa","vendor":"Exa","category":"search-api","tags":["search","grounding"],"tagline":"Web search API built for AI.","description":"Neural search engine and API returning clean page content for LLM grounding, research agents and dataset building.","pricingModel":"freemium","openSource":false,"website":"https://exa.ai","launchedYear":2023,"platforms":["API"],"features":["Neural search","Contents API","Websets"],"useCases":["research","agents"],"technologies":["rag","vector-search"],"relatedModelIds":[],"popularity":62},{"id":"hermes-agent","name":"Hermes Agent","vendor":"Nous Research","category":"chat-assistant","tags":["self-hosted","byok"],"tagline":"Open-source agent that learns reusable skills as you use it.","description":"A long-running personal agent from Nous Research that turns finished tasks into reusable skills, searches its own past sessions and keeps a model of the user. Reach it from a terminal UI or from Telegram, Discord, Slack, WhatsApp and Signal through one gateway; it can schedule jobs, spawn subagents and run in local, Docker, SSH or serverless sandboxes. Works with any model provider.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://hermes-agent.nousresearch.com","github":"https://github.com/NousResearch/hermes-agent","launchedYear":2025,"platforms":["CLI","Linux","macOS","Windows","Android"],"features":["Self-improving skills","Scheduled automations","Subagents","Any model"],"useCases":["agents","chat"],"technologies":["agent-memory","agent-orchestration"],"relatedModelIds":[],"usage":{"appRank":1,"asOf":"2026-10-31"},"popularity":62},{"id":"adobe-firefly","name":"Adobe Firefly","vendor":"Adobe","category":"image-video","tags":["image","video","design"],"tagline":"Commercially safe image, video and audio generation inside Adobe’s apps.","description":"Adobe’s generative AI app and model family, trained for commercial safety and built into Photoshop, Premiere and Express. The Firefly app also offers selected partner models alongside Adobe’s own.","pricingModel":"freemium","openSource":false,"website":"https://www.adobe.com/products/firefly.html","launchedYear":2023,"platforms":["Web","Desktop","iOS","Android"],"features":["Commercially safe training","Photoshop/Premiere integration","Partner models"],"useCases":["image-generation","enterprise"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":62},{"id":"devin","name":"Devin","vendor":"Cognition","category":"coding-assistant","tags":["autonomous"],"tagline":"Autonomous AI software engineer.","description":"An autonomous agent that takes tickets end to end in its own cloud workspace, integrating with Slack, Linear and GitHub.","pricingModel":"paid","openSource":false,"website":"https://devin.ai","launchedYear":2024,"platforms":["Web","Slack"],"features":["Ticket-to-PR","Own shell, browser & editor","DeepWiki"],"useCases":["coding","agents","enterprise"],"technologies":["agent-orchestration","computer-use"],"relatedModelIds":[],"popularity":60},{"id":"bolt-new","name":"Bolt.new","vendor":"StackBlitz","category":"coding-assistant","tags":["app-builder","no-code"],"tagline":"Prompt, run, edit and deploy full-stack apps in the browser.","description":"An in-browser app builder from StackBlitz: describe an app and an agent scaffolds, runs and edits a full-stack project inside WebContainers, then deploys it — no local setup required.","pricingModel":"freemium","openSource":false,"website":"https://bolt.new","launchedYear":2024,"platforms":["Web"],"features":["Prompt-to-app","In-browser runtime","One-click deploy"],"useCases":["coding"],"technologies":["agent-orchestration"],"relatedModelIds":["claude-sonnet-5.5"],"popularity":60},{"id":"microsoft-agent-framework","name":"Microsoft Agent Framework","vendor":"Microsoft","category":"agent-framework","tags":["autogen","semantic kernel"],"tagline":"Successor to AutoGen and Semantic Kernel.","description":"Open-source SDK unifying AutoGen’s multi-agent patterns with Semantic Kernel’s enterprise features, for .NET and Python.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://learn.microsoft.com/agent-framework/","github":"https://github.com/microsoft/agent-framework","launchedYear":2025,"platforms":[".NET","Python"],"features":["Multi-agent orchestration","Azure AI Foundry integration","Workflows"],"useCases":["agents","enterprise"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":[],"popularity":60},{"id":"dspy","name":"DSPy","vendor":"Stanford NLP","category":"llm-framework","tags":["optimization","research"],"tagline":"Program — don’t prompt — language models.","description":"Declarative framework that compiles LM programs and optimizes prompts and weights automatically.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://dspy.ai","github":"https://github.com/stanfordnlp/dspy","launchedYear":2023,"platforms":["Python"],"features":["Prompt optimizers","Signatures","Modules"],"useCases":["reasoning","extraction"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":60},{"id":"elasticsearch","name":"Elasticsearch","vendor":"Elastic","category":"vector-database","tags":["search engine","hybrid search"],"tagline":"Search engine with dense, sparse and hybrid vector retrieval.","description":"The widely deployed search engine now supports dense kNN, learned sparse retrieval (ELSER), hybrid ranking and semantic reranking for RAG.","pricingModel":"freemium","openSource":true,"website":"https://www.elastic.co/elasticsearch","github":"https://github.com/elastic/elasticsearch","launchedYear":2010,"platforms":["Cloud","Self-host"],"features":["Hybrid BM25 + vector","Sparse retrieval (ELSER)","Reranking"],"useCases":["enterprise","research"],"technologies":["vector-search","rag"],"relatedModelIds":[],"popularity":60},{"id":"modal","name":"Modal","vendor":"Modal Labs","category":"inference-platform","tags":["gpu","serverless"],"tagline":"Serverless GPUs for AI workloads.","description":"Python-native serverless compute for inference, fine-tuning and batch jobs with sub-second cold starts.","pricingModel":"paid","openSource":false,"website":"https://modal.com","launchedYear":2022,"platforms":["Python","Cloud"],"features":["Serverless GPUs","Fast cold starts","Sandboxes"],"useCases":["high-volume"],"technologies":["fine-tuning"],"relatedModelIds":[],"popularity":60},{"id":"microsoft-copilot-studio","name":"Microsoft Copilot Studio","vendor":"Microsoft","category":"automation","tags":["low code","microsoft"],"tagline":"Low-code agent builder for Microsoft 365 and Power Platform.","description":"Build, test and publish agents that use company knowledge, connectors and Power Automate flows, and deploy them to Teams, Microsoft 365 Copilot or websites. Includes computer-use agents and enterprise governance; licensed through Microsoft.","pricingModel":"paid","openSource":false,"website":"https://www.microsoft.com/en-us/microsoft-copilot/microsoft-copilot-studio","launchedYear":2023,"platforms":["Web","Microsoft 365"],"features":["Low-code agent builder","Power Platform connectors","Computer-use agents"],"useCases":["agents","enterprise"],"technologies":["agent-orchestration","computer-use"],"relatedModelIds":[],"popularity":60},{"id":"openai-dots","name":"OpenAI dots","vendor":"OpenAI","category":"chat-assistant","tags":["agent","chatgpt"],"tagline":"Always-on ChatGPT agents with their own cloud computer.","description":"Always-on agents inside ChatGPT, announced at DevDay on September 29, 2026. Each dot runs on GPT-6 Astra with its own cloud computer and browser, connects to thousands of apps through plugins, and keeps working in the background. Rolling out first to Pro and Business Premium users.","pricingModel":"paid","openSource":false,"website":"https://chatgpt.com","launchedYear":2026,"platforms":["Web","Desktop","iOS","Android"],"features":["Always-on background agents","Own cloud computer & browser","App plugins"],"useCases":["agents","research","enterprise"],"technologies":["computer-use","agent-orchestration"],"relatedModelIds":["gpt-6-astra"],"popularity":60},{"id":"livekit-agents","name":"LiveKit Agents","vendor":"LiveKit","category":"voice-audio","tags":["voice agents"],"tagline":"Framework for real-time voice AI agents.","description":"Open-source framework and cloud for building low-latency voice and video agents over WebRTC.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://livekit.io","github":"https://github.com/livekit/agents","launchedYear":2024,"platforms":["Python","Node.js","Cloud"],"features":["WebRTC transport","Turn detection","Telephony"],"useCases":["realtime","agents"],"technologies":["realtime-voice","agent-orchestration"],"relatedModelIds":[],"popularity":60},{"id":"scale-ai","name":"Scale AI","vendor":"Scale AI","category":"data-ml","tags":["labeling","rlhf"],"tagline":"Data labeling and evaluation for frontier AI.","description":"Human data, RLHF, evaluation and data-engine services used by leading labs and enterprises.","pricingModel":"enterprise","openSource":false,"website":"https://scale.com","launchedYear":2016,"platforms":["Cloud"],"features":["RLHF data","Evaluation","Data engine"],"useCases":["enterprise"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":60},{"id":"granola","name":"Granola","vendor":"Granola","category":"productivity","tags":["meetings","notes"],"tagline":"AI notepad for meetings — no bot required.","description":"Transcribes meetings on-device audio and enhances your own notes into clean summaries.","pricingModel":"freemium","openSource":false,"website":"https://www.granola.ai","launchedYear":2024,"platforms":["macOS","Windows","iOS"],"features":["Bot-free capture","Note enhancement","Templates"],"useCases":["writing","extraction"],"technologies":[],"relatedModelIds":[],"popularity":60},{"id":"coderabbit","name":"CodeRabbit","vendor":"CodeRabbit","category":"coding-assistant","tags":["code review"],"tagline":"AI code reviews on every pull request.","description":"Automated, context-aware PR reviews for GitHub, GitLab and Azure DevOps with line-by-line suggestions.","pricingModel":"freemium","openSource":false,"website":"https://www.coderabbit.ai","launchedYear":2023,"platforms":["GitHub","GitLab","Azure DevOps","IDE"],"features":["PR summaries","Line-level review","Learns team conventions"],"useCases":["coding","enterprise"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":58},{"id":"opencode","name":"OpenCode","vendor":"SST","category":"coding-assistant","tags":["cli","agent","open source"],"tagline":"Open-source, provider-agnostic coding agent for the terminal.","description":"A terminal-first coding agent with a TUI, LSP integration and support for 75+ model providers, including local models.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://opencode.ai","github":"https://github.com/anomalyco/opencode","launchedYear":2025,"platforms":["CLI"],"features":["Any model provider","LSP-aware","Terminal UI"],"useCases":["coding","agents","on-device"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":[],"popularity":58},{"id":"zed","name":"Zed","vendor":"Zed Industries","category":"coding-assistant","tags":["ide","editor","open-source"],"tagline":"Fast open-source editor built in Rust, with agentic editing built in.","description":"A high-performance, multiplayer code editor written in Rust. It ships agentic editing with your choice of models and can host external agents such as Claude Code or Gemini CLI through the Agent Client Protocol it created.","pricingModel":"freemium","openSource":true,"license":"GPL-3.0","website":"https://zed.dev","github":"https://github.com/zed-industries/zed","launchedYear":2023,"platforms":["macOS","Linux","Windows"],"features":["Agent panel","Agent Client Protocol","Edit predictions","Real-time collaboration"],"useCases":["coding","agents"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":["claude-sonnet-5.5","gpt-6.1-sol"],"usage":{"appRank":27,"asOf":"2026-10-31"},"popularity":58},{"id":"mastra","name":"Mastra","vendor":"Mastra","category":"agent-framework","tags":["typescript"],"tagline":"The TypeScript agent framework.","description":"TypeScript framework for agents, workflows, RAG and evals with a local dev playground.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://mastra.ai","github":"https://github.com/mastra-ai/mastra","launchedYear":2024,"platforms":["TypeScript"],"features":["Workflows","Memory","Evals","Dev playground"],"useCases":["agents"],"technologies":["agent-orchestration","rag","agent-memory"],"relatedModelIds":[],"popularity":58},{"id":"e2b","name":"E2B","vendor":"E2B","category":"agent-infra","tags":["sandbox","code execution","micro vm"],"tagline":"Secure cloud sandboxes for running AI-generated code.","description":"Spins up isolated micro-VM sandboxes in milliseconds so agents can execute code, use a filesystem and run tools safely; includes a desktop sandbox for computer-use agents.","pricingModel":"freemium","openSource":true,"license":"Apache 2.0","website":"https://e2b.dev","github":"https://github.com/e2b-dev/E2B","docs":"https://e2b.dev/docs","launchedYear":2023,"platforms":["Cloud","Python","TypeScript","Self-host"],"features":["Code interpreter SDK","Fast-starting sandboxes","Desktop sandbox"],"useCases":["agents","coding"],"technologies":["computer-use","agent-orchestration"],"relatedModelIds":[],"popularity":58},{"id":"cerebras","name":"Cerebras Inference","vendor":"Cerebras","category":"inference-platform","tags":["fast","hardware"],"tagline":"Wafer-scale speed for open models.","description":"Inference API running on wafer-scale engines, offering thousands of tokens per second on popular open models.","pricingModel":"freemium","openSource":false,"website":"https://www.cerebras.ai","launchedYear":2024,"platforms":["API"],"features":["Wafer-scale chips","Thousands of tok/s"],"useCases":["realtime"],"technologies":["custom-silicon","speculative-decoding"],"relatedModelIds":[],"popularity":58},{"id":"promptfoo","name":"promptfoo","vendor":"promptfoo","category":"observability","tags":["testing","security"],"tagline":"Test and red-team your LLM apps.","description":"CLI and library for prompt testing, model comparison and automated red-teaming in CI.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://www.promptfoo.dev","github":"https://github.com/promptfoo/promptfoo","launchedYear":2023,"platforms":["CLI","CI"],"features":["Declarative tests","Red teaming","Model comparison"],"useCases":["enterprise"],"technologies":["llm-evals","guardrails"],"relatedModelIds":[],"popularity":58},{"id":"dify","name":"Dify","vendor":"LangGenius","category":"automation","tags":["low code","llm apps"],"tagline":"Open-source platform for building LLM apps and agent workflows.","description":"Visual workflow and agent builder with RAG pipelines, model management, tools/MCP and observability; self-host or use Dify Cloud.","pricingModel":"freemium","openSource":true,"website":"https://dify.ai","github":"https://github.com/langgenius/dify","launchedYear":2023,"platforms":["Cloud","Self-host"],"features":["Visual workflows","Knowledge bases (RAG)","Agent nodes"],"useCases":["agents","enterprise","chat"],"technologies":["agent-orchestration","rag","mcp"],"relatedModelIds":[],"popularity":58},{"id":"perplexity-sonar","name":"Perplexity Sonar API","vendor":"Perplexity","category":"search-api","tags":["search","grounding"],"tagline":"Search-grounded answers via API.","description":"API access to Perplexity’s search-grounded models with citations, including deep research.","pricingModel":"paid","openSource":false,"website":"https://docs.perplexity.ai","launchedYear":2024,"platforms":["API"],"features":["Citations","Deep research","Real-time web"],"useCases":["research"],"technologies":["rag"],"relatedModelIds":[],"popularity":58},{"id":"manus","name":"Manus","vendor":"Manus (Meta)","category":"chat-assistant","tags":["agent","general-agent"],"tagline":"General-purpose autonomous agent for end-to-end tasks.","description":"A general AI agent that plans and executes multi-step tasks — research, slides, websites, data analysis — in its own cloud sandbox. Acquired by Meta in December 2025; the subscription service continues, operated from Singapore. Credit-based billing.","pricingModel":"freemium","openSource":false,"website":"https://manus.im","launchedYear":2025,"platforms":["Web","iOS","Android"],"features":["Autonomous multi-step tasks","Cloud sandbox","Slides, sites and reports"],"useCases":["agents","research"],"technologies":["computer-use","agent-orchestration"],"relatedModelIds":[],"popularity":58},{"id":"heygen","name":"HeyGen","vendor":"HeyGen","category":"image-video","tags":["avatars","video","translation"],"tagline":"AI avatar videos, translation and voice.","description":"Creates presenter videos from scripts with stock or custom digital avatars, translates and lip-syncs videos into other languages, and offers its own video and voice models through an API.","pricingModel":"freemium","openSource":false,"website":"https://www.heygen.com","platforms":["Web","API"],"features":["Digital avatars","Video translation","Avatar API"],"useCases":["multimodal","enterprise"],"technologies":[],"relatedModelIds":[],"popularity":58},{"id":"amazon-sagemaker-ai","name":"Amazon SageMaker AI","vendor":"Amazon Web Services","category":"data-ml","tags":["mlops","training","aws"],"tagline":"AWS’s platform to build, train and deploy ML and foundation models.","description":"Managed notebooks, distributed training (HyperPod), fine-tuning, model hosting and MLOps on AWS, plus JumpStart for deploying open foundation models. Usage-based pricing.","pricingModel":"paid","openSource":false,"website":"https://aws.amazon.com/sagemaker/ai/","launchedYear":2017,"platforms":["AWS","Python"],"features":["HyperPod training","Model hosting","JumpStart models","MLOps"],"useCases":["enterprise"],"technologies":["fine-tuning"],"relatedModelIds":[],"popularity":58},{"id":"glean","name":"Glean","vendor":"Glean","category":"productivity","tags":["knowledge base","search"],"tagline":"Work AI and enterprise search.","description":"Permission-aware enterprise search and agents grounded across 100+ workplace apps.","pricingModel":"enterprise","openSource":false,"website":"https://www.glean.com","launchedYear":2019,"platforms":["Web","Slack","Browser"],"features":["Enterprise search","Agents","Permission-aware"],"useCases":["enterprise","research"],"technologies":["rag","vector-search"],"relatedModelIds":[],"popularity":58},{"id":"arize-phoenix","name":"Arize Phoenix","vendor":"Arize AI","category":"observability","tags":["tracing"],"tagline":"Open-source AI observability and evaluation.","description":"OpenTelemetry-native tracing and evaluation for LLM apps, runnable locally or in Arize’s cloud.","pricingModel":"open-source","openSource":true,"license":"Elastic 2.0","website":"https://phoenix.arize.com","github":"https://github.com/Arize-ai/phoenix","launchedYear":2023,"platforms":["Self-hosted","Cloud"],"features":["OTel tracing","Eval library","Datasets"],"useCases":["enterprise"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":56},{"id":"camunda","name":"Camunda","vendor":"Camunda","category":"decision-engine","tags":["dmn","bpmn","workflow"],"tagline":"Process orchestration with BPMN & DMN decisions.","description":"Orchestrates processes, people, systems and AI agents with BPMN workflows and DMN decision tables.","pricingModel":"freemium","openSource":false,"website":"https://camunda.com","github":"https://github.com/camunda/camunda","launchedYear":2013,"platforms":["Cloud","Self-managed"],"features":["DMN decision tables","BPMN orchestration","Agentic orchestration"],"useCases":["enterprise","agents"],"technologies":["decision-modeling","agent-orchestration"],"relatedModelIds":[],"popularity":56},{"id":"qwen-chat","name":"Qwen Chat","vendor":"Alibaba (Qwen)","category":"chat-assistant","tags":["assistant","chatbot"],"tagline":"Alibaba’s assistant for the Qwen model family.","description":"Chat with Qwen models on the web or mobile, with thinking mode, web search, image and video generation and document understanding.","pricingModel":"free","openSource":false,"website":"https://chat.qwen.ai","launchedYear":2025,"platforms":["Web","iOS","Android"],"features":["Thinking mode","Image & video generation","Web search"],"useCases":["chat","multimodal","coding"],"technologies":[],"relatedModelIds":["qwen3.8-max"],"popularity":56},{"id":"comet","name":"Comet","vendor":"Perplexity","category":"ai-browser","tags":["ai browser","browser agent"],"tagline":"Perplexity’s agentic browser.","description":"Chromium-based browser with Perplexity’s assistant built in: it answers about the current page, manages tabs and can carry out multi-step tasks on websites.","pricingModel":"freemium","openSource":false,"website":"https://www.perplexity.ai/comet","launchedYear":2025,"platforms":["macOS","Windows"],"features":["Page-aware assistant","Agentic browsing","Tab management"],"useCases":["agents","research"],"technologies":["computer-use","rag"],"relatedModelIds":[],"popularity":56},{"id":"kling-ai","name":"Kling AI","vendor":"Kuaishou","category":"image-video","tags":["video generation"],"tagline":"Kuaishou’s app and API for Kling video models.","description":"Generates and edits video and images with Kuaishou’s Kling models, including image-to-video, multi-shot scenes, lip sync and an Omni editing model, on the web or through an API.","pricingModel":"freemium","openSource":false,"website":"https://app.klingai.com","launchedYear":2024,"platforms":["Web","iOS","Android","API"],"features":["Text & image to video","Video editing","Lip sync"],"useCases":["multimodal"],"technologies":["diffusion"],"relatedModelIds":["kling-3"],"popularity":56},{"id":"assemblyai","name":"AssemblyAI","vendor":"AssemblyAI","category":"voice-audio","tags":["stt"],"tagline":"Speech AI models for transcription and understanding.","description":"Speech-to-text APIs with speaker diarization, streaming and audio intelligence features.","pricingModel":"freemium","openSource":false,"website":"https://www.assemblyai.com","launchedYear":2017,"platforms":["API"],"features":["Universal STT","Streaming","Diarization"],"useCases":["extraction","multimodal"],"technologies":[],"relatedModelIds":[],"popularity":56},{"id":"gamma","name":"Gamma","vendor":"Gamma","category":"productivity","tags":["presentations","slides"],"tagline":"Generate presentations, documents and sites from a prompt.","description":"Creates polished decks, documents and web pages from a prompt or outline, with AI editing, themes and export to PowerPoint and PDF.","pricingModel":"freemium","openSource":false,"website":"https://gamma.app","platforms":["Web"],"features":["Prompt to deck","AI editing","PPTX / PDF export"],"useCases":["writing"],"technologies":[],"relatedModelIds":[],"popularity":56},{"id":"warp","name":"Warp","vendor":"Warp","category":"coding-assistant","tags":["terminal","agent"],"tagline":"AI terminal turned agentic development environment.","description":"A modern terminal that has grown into an agentic development environment: run and manage multiple coding agents, launch cloud agents on Warp’s infrastructure or self-hosted, and share a team knowledge base. A standalone agent CLI works outside the desktop app.","pricingModel":"freemium","openSource":false,"website":"https://www.warp.dev","launchedYear":2022,"platforms":["macOS","Linux","Windows","CLI"],"features":["Multi-agent management","Cloud agents","Team knowledge base"],"useCases":["coding","agents"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":["claude-sonnet-5.5","gpt-6.1-sol"],"popularity":55},{"id":"redis-vector","name":"Redis (vector search)","vendor":"Redis","category":"vector-database","tags":["in-memory","cache"],"tagline":"In-memory vector search, semantic caching and agent memory.","description":"Redis adds vector similarity search, hybrid filtering and vector sets to its in-memory data store — popular for semantic caching of LLM responses, RAG and short-term agent memory where latency matters.","pricingModel":"freemium","openSource":false,"website":"https://redis.io","github":"https://github.com/redis/redis","platforms":["Cloud","Self-hosted"],"features":["In-memory vector search","Semantic caching","Hybrid filters"],"useCases":["realtime","high-volume"],"technologies":["vector-search","rag","agent-memory"],"relatedModelIds":[],"popularity":55},{"id":"ideogram","name":"Ideogram","vendor":"Ideogram","category":"image-video","tags":["image","design"],"tagline":"Image generation with excellent typography.","description":"Image model and app specializing in accurate text rendering for posters, logos and designs.","pricingModel":"freemium","openSource":false,"website":"https://ideogram.ai","launchedYear":2023,"platforms":["Web","iOS","API"],"features":["Typography","Canvas","Style codes"],"useCases":["image-generation"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":55},{"id":"luma-dream-machine","name":"Luma Dream Machine","vendor":"Luma AI","category":"image-video","tags":["video","creative"],"tagline":"Video and image generation app built on Luma’s Ray models.","description":"Luma AI’s creative app and API for video and image generation, powered by its Ray video models, which target physically plausible footage with native 1080p, 4K upscaling and, in newer versions, synchronized audio.","pricingModel":"freemium","openSource":false,"website":"https://lumalabs.ai","launchedYear":2024,"platforms":["Web","iOS","API"],"features":["Ray video models","Image generation","API access"],"useCases":["multimodal","image-generation"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":55},{"id":"otter","name":"Otter.ai","vendor":"Otter.ai","category":"productivity","tags":["meetings","notes"],"tagline":"AI meeting notes, transcripts and an agent that joins your calls.","description":"Records and transcribes meetings across Zoom, Meet and Teams, writes summaries and action items, and lets you ask questions across all past meetings.","pricingModel":"freemium","openSource":false,"website":"https://otter.ai","launchedYear":2016,"platforms":["Web","iOS","Android","Desktop"],"features":["Live transcription","Summaries & action items","Meeting Q&A"],"useCases":["extraction","enterprise"],"technologies":[],"relatedModelIds":[],"popularity":55},{"id":"mlx","name":"MLX","vendor":"Apple","category":"inference-platform","tags":["local inference","apple silicon"],"tagline":"Apple’s array framework for running and fine-tuning models on Apple silicon.","description":"An open-source machine-learning framework for Apple silicon with unified memory; its MLX-LM package runs and fine-tunes open LLMs locally on a Mac and powers many local-AI apps.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://ml-explore.github.io/mlx/","github":"https://github.com/ml-explore/mlx","launchedYear":2023,"platforms":["macOS","Python","Swift"],"features":["Apple silicon acceleration","MLX-LM inference","LoRA fine-tuning"],"useCases":["on-device"],"technologies":["quantization","fine-tuning"],"relatedModelIds":[],"popularity":54},{"id":"kimi","name":"Kimi","vendor":"Moonshot AI","category":"chat-assistant","tags":["assistant","chatbot"],"tagline":"Moonshot AI’s assistant with agent and research modes.","description":"Chat with Moonshot’s Kimi models, with deep research, agentic tasks that build slides and documents, and long-document reading.","pricingModel":"freemium","openSource":false,"website":"https://www.kimi.com","launchedYear":2023,"platforms":["Web","iOS","Android"],"features":["Deep research","Agent mode","Long-document reading"],"useCases":["chat","research","long-context"],"technologies":[],"relatedModelIds":["kimi-k3"],"popularity":54},{"id":"synthesia","name":"Synthesia","vendor":"Synthesia","category":"image-video","tags":["avatars","video","training"],"tagline":"AI video platform for business training and communications.","description":"Turns text, documents and slides into avatar-led videos in many languages, with brand kits, collaboration and enterprise security, aimed at training, onboarding and internal comms.","pricingModel":"freemium","openSource":false,"website":"https://www.synthesia.io","launchedYear":2017,"platforms":["Web","API"],"features":["AI avatars","Multilingual voiceover","Brand kits"],"useCases":["enterprise","multimodal"],"technologies":[],"relatedModelIds":[],"popularity":54},{"id":"muse-code","name":"Muse Code","vendor":"Meta","category":"coding-assistant","tags":["cli","agent","terminal"],"tagline":"Meta’s terminal coding agent, priced to undercut rivals.","description":"Meta’s terminal-based coding agent, launched in beta in August 2026 and out of beta around September 2026 with subscription plans alongside pay-as-you-go billing. It runs Meta’s Muse models, and Muse Code subscribers get exclusive access to Muse Wonder Full. An SDK in developer preview extends it beyond the CLI.","pricingModel":"paid","openSource":false,"website":"https://ai.meta.com","launchedYear":2026,"platforms":["CLI"],"features":["Terminal agent","Muse Wonder Full access","SDK (developer preview)"],"useCases":["coding","agents"],"technologies":["agent-orchestration"],"relatedModelIds":["muse-wonder","muse-spark-1.3"],"popularity":52},{"id":"trae","name":"TRAE","vendor":"ByteDance","category":"coding-assistant","tags":["ide","agentic coding"],"tagline":"ByteDance’s AI IDE with an autonomous SOLO mode.","description":"A VS Code-based AI IDE with chat, autocomplete and a SOLO mode that plans and builds longer tasks with tools and agents, plus a standalone SOLO client.","pricingModel":"freemium","openSource":false,"website":"https://www.trae.ai","launchedYear":2025,"platforms":["macOS","Windows","Web"],"features":["SOLO autonomous mode","AI autocomplete","Agent chat"],"useCases":["coding","agents"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":[],"popularity":52},{"id":"browser-use","name":"Browser Use","vendor":"Browser Use","category":"agent-infra","tags":["browser agent","web automation"],"tagline":"Open-source library that lets LLMs operate a web browser.","description":"Python library that turns a browser into an agent environment — the model sees the page, clicks, types and navigates — with a hosted cloud option.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://browser-use.com","github":"https://github.com/browser-use/browser-use","launchedYear":2024,"platforms":["Python","Cloud"],"features":["Any LLM provider","Multi-tab control","Hosted cloud"],"useCases":["agents"],"technologies":["computer-use"],"relatedModelIds":[],"popularity":52},{"id":"azure-ai-search","name":"Azure AI Search","vendor":"Microsoft","category":"vector-database","tags":["managed","azure"],"tagline":"Managed retrieval for RAG and agents on Azure.","description":"Microsoft’s managed search service with vector, hybrid and semantic ranking, integrated chunking and vectorisation, and agentic retrieval that plans multi-step queries for agents.","pricingModel":"paid","openSource":false,"website":"https://azure.microsoft.com/en-us/products/ai-services/ai-search","platforms":["Azure","API"],"features":["Hybrid & semantic ranking","Integrated vectorisation","Agentic retrieval"],"useCases":["enterprise","research"],"technologies":["vector-search","rag"],"relatedModelIds":[],"popularity":52},{"id":"sglang","name":"SGLang","vendor":"LMSYS / SGLang community","category":"inference-platform","tags":["serving","self-host","inference engine"],"tagline":"High-throughput serving engine for LLMs and VLMs.","description":"Fast open-source serving with RadixAttention prefix caching, speculative decoding, structured-output acceleration and large-scale expert parallelism for MoE models.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://docs.sglang.ai","github":"https://github.com/sgl-project/sglang","launchedYear":2024,"platforms":["Linux","NVIDIA","AMD","TPU"],"features":["RadixAttention caching","Expert parallelism","Fast JSON decoding"],"useCases":["high-volume","on-device","realtime"],"technologies":["speculative-decoding","constrained-decoding","quantization"],"relatedModelIds":[],"popularity":52},{"id":"runpod","name":"RunPod","vendor":"RunPod","category":"inference-platform","tags":["gpu","serverless"],"tagline":"GPU cloud with on-demand pods and serverless endpoints.","description":"A GPU cloud for training and inference: rent on-demand or spot GPU pods, or deploy autoscaling serverless endpoints (including vLLM templates) that bill per second.","pricingModel":"paid","openSource":false,"website":"https://www.runpod.io","launchedYear":2022,"platforms":["API","Web"],"features":["On-demand GPU pods","Serverless endpoints","Per-second billing"],"useCases":["high-volume"],"technologies":["fine-tuning"],"relatedModelIds":[],"popularity":52},{"id":"tensorrt-llm","name":"TensorRT-LLM","vendor":"NVIDIA","category":"inference-platform","tags":["inference engine","nvidia"],"tagline":"NVIDIA’s optimised LLM inference library for its GPUs.","description":"An open-source library for high-throughput, low-latency LLM serving on NVIDIA GPUs, with in-flight batching, paged KV cache, quantisation (FP8, FP4) and speculative decoding.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://nvidia.github.io/TensorRT-LLM","github":"https://github.com/NVIDIA/TensorRT-LLM","launchedYear":2023,"platforms":["Python","Linux","Self-host"],"features":["In-flight batching","FP8/FP4 quantisation","Speculative decoding"],"useCases":["high-volume"],"technologies":["quantization","speculative-decoding"],"relatedModelIds":[],"popularity":52},{"id":"portkey","name":"Portkey","vendor":"Portkey","category":"ai-gateway","tags":["gateway","router","llmops"],"tagline":"Production AI gateway with routing, guardrails, budgets and observability.","description":"An AI gateway and control plane for production LLM apps: conditional routing, retries and fallbacks, caching, guardrails, budgets and request logs/traces. The core gateway is open source; managed and enterprise plans add governance.","pricingModel":"freemium","openSource":true,"license":"MIT","website":"https://portkey.ai","github":"https://github.com/Portkey-AI/gateway","launchedYear":2023,"platforms":["API","Self-hosted"],"features":["Routing & fallbacks","Guardrails","Budgets","Logs & traces"],"useCases":["enterprise"],"technologies":["guardrails"],"relatedModelIds":[],"usage":{"appRank":16,"asOf":"2026-10-31"},"popularity":52},{"id":"wandb-weave","name":"W&B Weave","vendor":"Weights & Biases","category":"observability","tags":["evals"],"tagline":"Track and evaluate LLM applications.","description":"Lightweight toolkit from Weights & Biases for tracing, evaluating and iterating on LLM apps.","pricingModel":"freemium","openSource":false,"website":"https://wandb.ai/site/weave","launchedYear":2024,"platforms":["Python","TypeScript","Cloud"],"features":["Tracing","Scorers","Leaderboards"],"useCases":["enterprise"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":52},{"id":"crawl4ai","name":"Crawl4AI","vendor":"Crawl4AI","category":"search-api","tags":["scraping","crawler","open source"],"tagline":"Open-source crawler that turns websites into LLM-ready Markdown.","description":"A self-hosted Python crawler that renders pages in a real browser and outputs clean Markdown or structured extractions for RAG and agents. Free to run; you supply the compute and proxies.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://www.crawl4ai.com","github":"https://github.com/unclecode/crawl4ai","launchedYear":2024,"platforms":["Python","Docker","Self-host"],"features":["Markdown output","Browser rendering","Structured extraction"],"useCases":["extraction","research"],"technologies":["rag"],"relatedModelIds":[],"popularity":52},{"id":"le-chat","name":"Le Chat","vendor":"Mistral AI","category":"chat-assistant","tags":["assistant"],"tagline":"Mistral’s fast, European AI assistant.","description":"Assistant with flash answers, deep research, document understanding and enterprise deployment options.","pricingModel":"freemium","openSource":false,"website":"https://chat.mistral.ai","launchedYear":2024,"platforms":["Web","iOS","Android"],"features":["Flash answers","Deep research","On-prem enterprise"],"useCases":["chat","enterprise"],"technologies":["rag"],"relatedModelIds":["mistral-large-4","mistral-medium-3.5"],"popularity":52},{"id":"vapi","name":"Vapi","vendor":"Vapi","category":"voice-audio","tags":["voice agents","telephony"],"tagline":"Voice AI agents for developers.","description":"API platform for building, testing and deploying phone and web voice agents.","pricingModel":"paid","openSource":false,"website":"https://vapi.ai","launchedYear":2023,"platforms":["API"],"features":["Phone numbers","Bring any model","Testing"],"useCases":["realtime","agents"],"technologies":["realtime-voice"],"relatedModelIds":[],"popularity":52},{"id":"isaac-sim","name":"Isaac Sim","vendor":"NVIDIA","category":"physical-ai","tags":["robotics","simulation"],"tagline":"NVIDIA’s robotics simulator on Omniverse.","description":"Physically based simulation for designing, testing and training robots, with photorealistic sensors and synthetic data generation; Isaac Lab builds robot learning on top of it. Source is on GitHub under NVIDIA’s licence terms.","pricingModel":"free","openSource":false,"website":"https://developer.nvidia.com/isaac/sim","github":"https://github.com/isaac-sim/IsaacSim","platforms":["Linux","Windows","Python"],"features":["Physics simulation","Sensor simulation","Synthetic data"],"useCases":["research"],"technologies":[],"relatedModelIds":[],"popularity":52},{"id":"kiro","name":"Kiro","vendor":"AWS","category":"coding-assistant","tags":["ide","agent","specs"],"tagline":"Spec-driven agentic IDE from AWS.","description":"An agentic IDE that turns prompts into requirements, designs and task lists (specs) before writing code, with agent hooks that run on file events.","pricingModel":"freemium","openSource":false,"website":"https://kiro.dev","launchedYear":2025,"platforms":["macOS","Windows","Linux"],"features":["Spec-driven development","Agent hooks","MCP support"],"useCases":["coding","agents","enterprise"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":[],"popularity":50},{"id":"junie","name":"Junie","vendor":"JetBrains","category":"coding-assistant","tags":["ide","agent"],"tagline":"JetBrains’ coding agent that plans first and debugs with the real IDE debugger.","description":"JetBrains’ coding agent for its IDEs, out of beta since June 2026. It plans before coding, uses the IDE’s own debugger and inspections, and supports remote runs and project-aware code review. Usage is metered through JetBrains AI credits.","pricingModel":"freemium","openSource":false,"website":"https://www.jetbrains.com/junie/","launchedYear":2025,"platforms":["JetBrains"],"features":["Plan mode","IDE debugger integration","Code review","Bring your own model"],"useCases":["coding","agents"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":["claude-sonnet-5.5","gpt-6.1-sol","mellum-2.1"],"popularity":50},{"id":"browserbase","name":"Browserbase","vendor":"Browserbase","category":"agent-infra","tags":["headless browser","web automation"],"tagline":"Headless browsers in the cloud for AI agents.","description":"Managed fleets of headless Chrome sessions with stealth, session recording and live view, plus Stagehand — an open-source framework for driving browsers with natural language.","pricingModel":"freemium","openSource":false,"website":"https://www.browserbase.com","github":"https://github.com/browserbase/stagehand","launchedYear":2024,"platforms":["Cloud","TypeScript","Python"],"features":["Managed headless Chrome","Session replay","Stagehand SDK"],"useCases":["agents"],"technologies":["computer-use"],"relatedModelIds":[],"popularity":50},{"id":"mem0","name":"Mem0","vendor":"Mem0","category":"agent-infra","tags":["memory","personalization"],"tagline":"Memory layer for AI agents and assistants.","description":"Extracts, stores and retrieves user and session memories across conversations using vector and graph stores, as an open-source library or managed platform.","pricingModel":"freemium","openSource":true,"license":"Apache 2.0","website":"https://mem0.ai","github":"https://github.com/mem0ai/mem0","launchedYear":2024,"platforms":["Python","TypeScript","Cloud"],"features":["Long-term user memory","Graph memory","Managed or self-hosted"],"useCases":["agents","chat"],"technologies":["agent-memory","vector-search"],"relatedModelIds":[],"popularity":50},{"id":"haystack","name":"Haystack","vendor":"deepset","category":"llm-framework","tags":["rag","search"],"tagline":"Production-ready RAG pipelines.","description":"Open-source framework for building search, RAG and agent pipelines, with an enterprise platform.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://haystack.deepset.ai","github":"https://github.com/deepset-ai/haystack","launchedYear":2020,"platforms":["Python"],"features":["Pipelines","Evaluation","Enterprise platform"],"useCases":["research","enterprise"],"technologies":["rag"],"relatedModelIds":[],"popularity":50},{"id":"instructor","name":"Instructor","vendor":"Jason Liu & community","category":"llm-framework","tags":["structured output","pydantic"],"tagline":"Pydantic-typed structured outputs from any LLM.","description":"Patches LLM clients so responses are parsed and validated into Pydantic models, with automatic retries on validation errors; ports exist for TypeScript, Go, Ruby and more.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://python.useinstructor.com","github":"https://github.com/567-labs/instructor","launchedYear":2023,"platforms":["Python","TypeScript","Go","Ruby"],"features":["Pydantic validation","Automatic retries","Streaming partial objects"],"useCases":["extraction"],"technologies":["constrained-decoding"],"relatedModelIds":[],"popularity":50},{"id":"opensearch","name":"OpenSearch","vendor":"OpenSearch Software Foundation","category":"vector-database","tags":["search engine","hybrid search"],"tagline":"Open-source search engine with vector and hybrid search.","description":"A Linux Foundation search and analytics engine (forked from Elasticsearch) with k-NN vector search, hybrid lexical-plus-vector ranking and neural search plugins; also offered managed on AWS.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://opensearch.org","github":"https://github.com/opensearch-project/OpenSearch","launchedYear":2021,"platforms":["Self-host","Cloud"],"features":["k-NN vector search","Hybrid search","Neural search plugins"],"useCases":["enterprise","research"],"technologies":["vector-search","rag"],"relatedModelIds":[],"popularity":50},{"id":"cloudflare-workers-ai","name":"Workers AI","vendor":"Cloudflare","category":"inference-platform","tags":["serverless","edge","api"],"tagline":"Serverless GPU inference on Cloudflare’s global network.","description":"Run open models — LLMs, embeddings, speech, image and Cloudflare’s own Clef decision models — on serverless GPUs across Cloudflare’s network, called from Workers or a REST API and billed per use.","pricingModel":"freemium","openSource":false,"website":"https://developers.cloudflare.com/workers-ai/","launchedYear":2023,"platforms":["API","Workers"],"features":["Serverless GPUs at the edge","Open-model catalog","Clef decision models"],"useCases":["high-volume","realtime"],"technologies":[],"relatedModelIds":["clef","clef-flash","clef-omni","granite-4.0-h-micro"],"popularity":50},{"id":"deepinfra","name":"DeepInfra","vendor":"DeepInfra","category":"inference-platform","tags":["serverless","api","open-models"],"tagline":"Low-cost, OpenAI-compatible API for popular open models.","description":"A serverless inference provider hosting a broad catalog of open-weight models behind an OpenAI-compatible API, known for aggressive per-token pricing; also offers dedicated GPU deployments.","pricingModel":"paid","openSource":false,"website":"https://deepinfra.com","platforms":["API"],"features":["OpenAI-compatible API","Large open-model catalog","Dedicated deployments"],"useCases":["high-volume"],"technologies":[],"relatedModelIds":["deepseek-v4.1-flash","gpt-oss-120b","llama-4-scout","qwen3.6-35b-a3b"],"popularity":50},{"id":"helicone","name":"Helicone","vendor":"Helicone","category":"observability","tags":["gateway"],"tagline":"LLM observability via a one-line proxy.","description":"Open-source gateway and observability: logging, caching, rate limiting and cost tracking.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://www.helicone.ai","github":"https://github.com/Helicone/helicone","launchedYear":2023,"platforms":["Cloud","Self-hosted"],"features":["Proxy logging","Caching","Cost tracking"],"useCases":["enterprise","high-volume"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":50},{"id":"drools","name":"Drools","vendor":"Apache KIE","category":"decision-engine","tags":["rules engine","java","dmn"],"tagline":"The classic Java business rules management system.","description":"Open-source rules engine (Apache KIE) with DRL rules, DMN support and complex event processing.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://www.drools.org","github":"https://github.com/apache/incubator-kie","launchedYear":2001,"platforms":["Java"],"features":["DRL & DMN","Rete-based inference","Complex event processing"],"useCases":["enterprise"],"technologies":["decision-modeling"],"relatedModelIds":[],"popularity":50},{"id":"langflow","name":"Langflow","vendor":"DataStax (IBM)","category":"automation","tags":["low code","visual builder"],"tagline":"Visual builder for agents and RAG flows.","description":"Drag-and-drop editor for LLM, RAG and multi-agent flows that can be exported as APIs or MCP servers; Python under the hood.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://www.langflow.org","github":"https://github.com/langflow-ai/langflow","launchedYear":2023,"platforms":["Self-host","Desktop","Cloud"],"features":["Visual flows","Flows as APIs / MCP servers","Custom Python components"],"useCases":["agents","research"],"technologies":["agent-orchestration","rag","mcp"],"relatedModelIds":[],"popularity":50},{"id":"brave-search-api","name":"Brave Search API","vendor":"Brave","category":"search-api","tags":["search"],"tagline":"Independent web index via API.","description":"Web search API backed by Brave’s own independent index, popular for LLM grounding.","pricingModel":"freemium","openSource":false,"website":"https://brave.com/search/api/","launchedYear":2023,"platforms":["API"],"features":["Independent index","AI grounding endpoint"],"useCases":["research"],"technologies":["rag"],"relatedModelIds":[],"popularity":50},{"id":"bright-data","name":"Bright Data","vendor":"Bright Data","category":"search-api","tags":["scraping","proxies","datasets"],"tagline":"Web data, unblocking and scraping infrastructure for AI.","description":"Proxy network, unblocker, scraping browser, SERP API and datasets for collecting web data at scale, plus a Web MCP server that gives agents live search and page access on hard-to-scrape sites.","pricingModel":"freemium","openSource":false,"website":"https://brightdata.com","platforms":["API","MCP"],"features":["Web unblocker","Scraping browser","SERP API","Web MCP server"],"useCases":["extraction","agents","enterprise"],"technologies":["mcp"],"relatedModelIds":[],"popularity":50},{"id":"poe","name":"Poe","vendor":"Quora","category":"chat-assistant","tags":["assistant","multi-model"],"tagline":"One subscription for many AI models and bots.","description":"Quora’s app for chatting with models from many providers, plus community-built bots and apps, under one subscription with a compute-points system.","pricingModel":"freemium","openSource":false,"website":"https://poe.com","launchedYear":2023,"platforms":["Web","iOS","Android","macOS","Windows"],"features":["Many models in one app","Custom bots","Group chats"],"useCases":["chat"],"technologies":[],"relatedModelIds":[],"popularity":50},{"id":"leonardo-ai","name":"Leonardo.Ai","vendor":"Leonardo.Ai (Canva)","category":"image-video","tags":["image","creative"],"tagline":"High-volume image and video generation for creators and teams.","description":"A creative platform, owned by Canva, for generating and editing images and short videos at volume, with fine-tuned styles, consistent characters and access to several third-party models.","pricingModel":"freemium","openSource":false,"website":"https://leonardo.ai","launchedYear":2022,"platforms":["Web","iOS","API"],"features":["Custom styles","Image + video","Realtime canvas"],"useCases":["image-generation","multimodal"],"technologies":["diffusion","fine-tuning"],"relatedModelIds":[],"popularity":50},{"id":"trl","name":"TRL","vendor":"Hugging Face","category":"data-ml","tags":["rlhf","post-training"],"tagline":"Post-training library: SFT, DPO, GRPO and RL for LLMs.","description":"Hugging Face’s Transformer Reinforcement Learning library with trainers for supervised fine-tuning, preference optimisation and RL with verifiable rewards — the toolkit behind many open reasoning models.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://huggingface.co/docs/trl","github":"https://github.com/huggingface/trl","platforms":["Python"],"features":["SFT / DPO / GRPO trainers","PEFT integration","vLLM generation"],"useCases":["research","reasoning"],"technologies":["fine-tuning","reasoning"],"relatedModelIds":[],"popularity":50},{"id":"pi","name":"Pi","vendor":"Earendil Works","category":"coding-assistant","tags":["terminal","byok"],"tagline":"Minimal, extensible terminal coding agent.","description":"A deliberately small coding-agent harness for the terminal: strong defaults, no built-in sub-agents or plan mode, and everything else added through extensions, skills, prompt templates and shareable packages. Runs interactively, in print/JSON mode, over RPC or embedded through its TypeScript SDK.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://pi.dev","github":"https://github.com/earendil-works/pi","launchedYear":2025,"platforms":["CLI"],"features":["Extensions and packages","RPC and SDK","Any model"],"useCases":["coding","agents"],"technologies":["agent-orchestration"],"relatedModelIds":[],"usage":{"appRank":4,"asOf":"2026-10-31"},"popularity":48},{"id":"amp","name":"Amp","vendor":"Amp","category":"coding-assistant","tags":["cli","agent"],"tagline":"Frontier coding agent for the terminal and your editor.","description":"An agentic coding tool originally built at Sourcegraph and spun out as an independent company in December 2025. It runs in the terminal and in VS Code, Cursor, Windsurf, JetBrains IDEs and Neovim.","pricingModel":"freemium","openSource":false,"website":"https://ampcode.com","launchedYear":2025,"platforms":["CLI","VS Code","JetBrains","Neovim"],"features":["Terminal + editor agent","Subagents","Thread sharing"],"useCases":["coding","agents"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":["claude-opus-5.5","gpt-6.1-sol"],"popularity":48},{"id":"turbopuffer","name":"turbopuffer","vendor":"turbopuffer","category":"vector-database","tags":["serverless"],"tagline":"Serverless vector and full-text search on object storage.","description":"Search engine built on object storage for very low cost at large scale; used by several leading AI products.","pricingModel":"paid","openSource":false,"website":"https://turbopuffer.com","launchedYear":2023,"platforms":["Cloud"],"features":["Object-storage native","Full-text + vector","Low cost at scale"],"useCases":["long-context","high-volume"],"technologies":["vector-search"],"relatedModelIds":[],"popularity":48},{"id":"mongodb-atlas-vector-search","name":"MongoDB Atlas Vector Search","vendor":"MongoDB","category":"vector-database","tags":["vector db","document db"],"tagline":"Vector search inside your operational MongoDB database.","description":"Index and query embeddings alongside documents in MongoDB Atlas, with hybrid search and Voyage AI embedding and reranking models available natively.","pricingModel":"freemium","openSource":false,"website":"https://www.mongodb.com/products/platform/atlas-vector-search","launchedYear":2023,"platforms":["Cloud"],"features":["Vectors next to operational data","Hybrid search","Voyage AI models"],"useCases":["enterprise","research"],"technologies":["vector-search","rag"],"relatedModelIds":["voyage-4-large"],"popularity":48},{"id":"nvidia-nim","name":"NVIDIA NIM","vendor":"NVIDIA","category":"inference-platform","tags":["microservices","self-host","gpu"],"tagline":"Prebuilt, optimised inference microservices for NVIDIA GPUs.","description":"Containerised model servers with TensorRT-LLM optimisations and OpenAI-compatible APIs, runnable on any NVIDIA GPU or tried for free on build.nvidia.com.","pricingModel":"enterprise","openSource":false,"website":"https://build.nvidia.com","docs":"https://docs.nvidia.com/nim/","launchedYear":2024,"platforms":["Cloud","On-prem","Kubernetes"],"features":["Optimised containers","OpenAI-compatible API","Free hosted trials"],"useCases":["enterprise","on-device"],"technologies":["quantization","speculative-decoding"],"relatedModelIds":["nemotron-3-ultra","cosmos-3"],"popularity":48},{"id":"cloudflare-ai-gateway","name":"Cloudflare AI Gateway","vendor":"Cloudflare","category":"ai-gateway","tags":["gateway","edge"],"tagline":"Edge gateway for caching, rate-limiting and observing AI API calls.","description":"A managed gateway on Cloudflare’s network that sits in front of model providers to add caching, rate limiting, retries and model fallbacks, plus analytics and logging. Closed source and not self-hostable; a free tier covers basic use.","pricingModel":"freemium","openSource":false,"website":"https://developers.cloudflare.com/ai-gateway/","launchedYear":2023,"platforms":["API"],"features":["Edge caching","Rate limiting","Fallbacks","Analytics & logs"],"useCases":["high-volume","enterprise"],"technologies":[],"relatedModelIds":[],"popularity":48},{"id":"genspark","name":"Genspark","vendor":"Genspark","category":"chat-assistant","tags":["agent","general-agent"],"tagline":"Super Agent workspace for research, slides, docs and calls.","description":"An AI agent workspace whose Super Agent combines many models and tools to research, build slides, sheets and docs, and even place phone calls on your behalf.","pricingModel":"freemium","openSource":false,"website":"https://www.genspark.ai","platforms":["Web","iOS","Android"],"features":["Super Agent","AI slides, sheets and docs","Deep research"],"useCases":["agents","research","writing"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":48},{"id":"fireflies","name":"Fireflies.ai","vendor":"Fireflies.ai","category":"productivity","tags":["meetings","transcription"],"tagline":"AI meeting notetaker, transcription and search.","description":"Joins calls on Zoom, Meet and Teams to record, transcribe and summarise meetings, with searchable transcripts and CRM integrations.","pricingModel":"freemium","openSource":false,"website":"https://fireflies.ai","platforms":["Web","Zoom","Google Meet","Teams"],"features":["Meeting transcription","Summaries & action items","CRM sync"],"useCases":["extraction","enterprise"],"technologies":[],"relatedModelIds":[],"popularity":48},{"id":"mujoco","name":"MuJoCo","vendor":"Google DeepMind","category":"physical-ai","tags":["physics engine","simulation"],"tagline":"Fast, accurate physics engine for robotics research.","description":"Multi-joint dynamics with contact — the standard physics engine for robotics and RL research — with MJX for GPU/TPU-accelerated simulation via JAX.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://mujoco.org","github":"https://github.com/google-deepmind/mujoco","launchedYear":2012,"platforms":["Python","C","Linux","macOS","Windows"],"features":["Contact-rich physics","MJX on accelerators","Model zoo (Menagerie)"],"useCases":["research","math"],"technologies":[],"relatedModelIds":[],"popularity":48},{"id":"google-jules","name":"Jules","vendor":"Google","category":"coding-assistant","tags":["cloud agent","github"],"tagline":"Asynchronous coding agent that works on your GitHub repos.","description":"Clones your repository into a cloud VM, plans and implements changes such as bug fixes, tests and dependency bumps, and opens a pull request for review.","pricingModel":"freemium","openSource":false,"website":"https://jules.google","launchedYear":2025,"platforms":["Web","CLI"],"features":["Async background tasks","Plan review","Pull requests"],"useCases":["coding","agents"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":46},{"id":"openhands","name":"OpenHands","vendor":"All Hands AI","category":"coding-assistant","tags":["agent","open-source"],"tagline":"Open-source platform for autonomous software-engineering agents.","description":"An open-source platform (formerly OpenDevin) for autonomous coding agents that write code, run commands and browse the web in a sandbox. Self-host it or use the hosted OpenHands Cloud.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://www.all-hands.dev","github":"https://github.com/OpenHands/OpenHands","launchedYear":2024,"platforms":["Web","CLI","Self-hosted"],"features":["Sandboxed agent runtime","GitHub/GitLab integration","Cloud or self-hosted"],"useCases":["coding","agents"],"technologies":["agent-orchestration","computer-use"],"relatedModelIds":["claude-sonnet-5.5","qwen3.8-max"],"usage":{"appRank":12,"asOf":"2026-10-31"},"popularity":46},{"id":"genkit","name":"Genkit","vendor":"Google","category":"agent-framework","tags":["firebase","typescript","go"],"tagline":"Google’s open-source framework for AI-powered apps.","description":"Builds flows, tool-calling agents and RAG in JavaScript/TypeScript, Go and Python, with a local developer UI for tracing and plugins for Gemini and other model providers. Deploys to Firebase, Cloud Run or any host.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://genkit.dev","github":"https://github.com/genkit-ai/genkit","launchedYear":2024,"platforms":["TypeScript","Go","Python"],"features":["Flows","Tool calling","Developer UI","Provider plugins"],"useCases":["agents","chat"],"technologies":["agent-orchestration","rag"],"relatedModelIds":[],"popularity":46},{"id":"composio","name":"Composio","vendor":"Composio","category":"agent-infra","tags":["tool integrations","mcp","auth"],"tagline":"Hundreds of authenticated tool integrations for agents.","description":"Gives agents ready-made, OAuth-managed actions across SaaS apps (GitHub, Slack, Gmail…), usable from most agent frameworks or as MCP servers.","pricingModel":"freemium","openSource":false,"website":"https://composio.dev","github":"https://github.com/ComposioHQ/composio","platforms":["Cloud","Python","TypeScript"],"features":["Managed OAuth","Large tool catalog","MCP servers"],"useCases":["agents","enterprise"],"technologies":["mcp","agent-orchestration"],"relatedModelIds":[],"popularity":46},{"id":"spring-ai","name":"Spring AI","vendor":"Broadcom (Spring)","category":"llm-framework","tags":["java","spring"],"tagline":"AI application framework for Java and Spring Boot.","description":"Brings portable chat, embedding and image model APIs, vector-store integrations, tool calling, MCP and RAG advisors to Spring Boot applications.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://spring.io/projects/spring-ai","github":"https://github.com/spring-projects/spring-ai","launchedYear":2023,"platforms":["Java"],"features":["Portable model APIs","Vector store integrations","MCP support"],"useCases":["enterprise","chat"],"technologies":["rag","mcp"],"relatedModelIds":[],"popularity":46},{"id":"vercel-ai-gateway","name":"Vercel AI Gateway","vendor":"Vercel","category":"ai-gateway","tags":["gateway","router"],"tagline":"One endpoint for hundreds of models, with no markup on tokens.","description":"Vercel’s gateway gives one API and one bill for models from many providers, with automatic fallbacks and usage monitoring, and plugs straight into the AI SDK. Pay-as-you-go with no token markup and a small monthly free credit; tied to a Vercel team account.","pricingModel":"freemium","openSource":false,"website":"https://vercel.com/ai-gateway","launchedYear":2025,"platforms":["API"],"features":["No token markup","Fallbacks","AI SDK integration","Bring your own keys"],"useCases":["high-volume"],"technologies":[],"relatedModelIds":[],"popularity":46},{"id":"ragas","name":"Ragas","vendor":"Exploding Gradients","category":"observability","tags":["evals","rag"],"tagline":"Evaluation metrics for RAG pipelines and agents.","description":"Library of reference-free metrics — faithfulness, answer relevance, context precision/recall, agent goal accuracy — plus synthetic test-set generation.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://www.ragas.io","github":"https://github.com/vibrantlabsai/ragas","launchedYear":2023,"platforms":["Python"],"features":["RAG metrics","Test-set generation","Framework integrations"],"useCases":["research","agents"],"technologies":["llm-evals","rag"],"relatedModelIds":[],"popularity":46},{"id":"datadog-llm-observability","name":"Datadog LLM Observability","vendor":"Datadog","category":"observability","tags":["tracing","apm"],"tagline":"LLM and agent tracing inside the Datadog APM stack.","description":"Traces LLM calls and agent steps end to end, tracks cost, latency and errors, and runs quality and security evaluations, all alongside existing Datadog infrastructure and application monitoring.","pricingModel":"paid","openSource":false,"website":"https://www.datadoghq.com/product/llm-observability/","launchedYear":2024,"platforms":["Cloud","Python","TypeScript"],"features":["Agent tracing","Cost & latency tracking","Quality & security evals"],"useCases":["enterprise"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":46},{"id":"nemo-guardrails","name":"NeMo Guardrails","vendor":"NVIDIA","category":"guardrails","tags":["guardrails","safety"],"tagline":"Open-source toolkit for programmable LLM guardrails.","description":"Adds input, output, dialog and retrieval rails around LLM apps — topic control, jailbreak and injection detection, fact-checking — configured in YAML and the Colang language.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://github.com/NVIDIA-NeMo/Guardrails","github":"https://github.com/NVIDIA-NeMo/Guardrails","launchedYear":2023,"platforms":["Python"],"features":["Colang dialog rails","Jailbreak detection","Works with any LLM"],"useCases":["enterprise","chat"],"technologies":["guardrails"],"relatedModelIds":["nemotron-3.5-content-safety"],"popularity":46},{"id":"gorules","name":"GoRules","vendor":"GoRules","category":"decision-engine","tags":["rules engine","decision api","jdm"],"tagline":"Open-source business rules engine (ZEN) with a visual editor.","description":"High-performance rules engine written in Rust with JSON decision models (JDM), decision tables and a decision API; embeddable in Node, Python, Go and more.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://gorules.io","github":"https://github.com/gorules/zen","launchedYear":2022,"platforms":["Rust","Node.js","Python","Go","Cloud"],"features":["Decision tables","Embeddable ZEN engine","Decision API","Visual graph editor"],"useCases":["enterprise","realtime"],"technologies":["decision-modeling"],"relatedModelIds":[],"popularity":46},{"id":"pipecat","name":"Pipecat","vendor":"Daily","category":"voice-audio","tags":["voice agents","framework"],"tagline":"Open-source framework for real-time voice and multimodal agents.","description":"Composable pipelines that wire speech-to-text, LLMs and text-to-speech (or speech-to-speech models) with transport, turn detection and interruptions.","pricingModel":"open-source","openSource":true,"license":"BSD-2-Clause","website":"https://www.pipecat.ai","github":"https://github.com/pipecat-ai/pipecat","launchedYear":2024,"platforms":["Python","Web","iOS","Android"],"features":["Pluggable STT/LLM/TTS","Turn detection","WebRTC transport"],"useCases":["realtime","agents","chat"],"technologies":["realtime-voice","agent-orchestration"],"relatedModelIds":[],"popularity":46},{"id":"lerobot","name":"LeRobot","vendor":"Hugging Face","category":"physical-ai","tags":["robotics","datasets","imitation learning"],"tagline":"Open-source models, datasets and tools for real-world robotics.","description":"PyTorch library with pretrained policies, a shared dataset format and hub, and recipes for training and running VLAs on affordable robot arms.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://huggingface.co/lerobot","github":"https://github.com/huggingface/lerobot","launchedYear":2024,"platforms":["Python"],"features":["LeRobotDataset format","Pretrained policies","Low-cost hardware support"],"useCases":["agents","research","on-device"],"technologies":["vla","fine-tuning"],"relatedModelIds":["pi-0.5"],"popularity":46},{"id":"continue","name":"Continue","vendor":"Continue","category":"coding-assistant","tags":["ide","open-source"],"tagline":"Open-source, model-agnostic coding assistant and agent.","description":"An open-source AI coding assistant for VS Code and JetBrains, plus a CLI, that works with any model — hosted or local — and lets teams share custom assistants, rules and checks.","pricingModel":"open-source","openSource":true,"license":"Apache-2.0","website":"https://www.continue.dev","github":"https://github.com/continuedev/continue","launchedYear":2023,"platforms":["VS Code","JetBrains","CLI"],"features":["Any model, including local","Custom assistants","Agent mode"],"useCases":["coding"],"technologies":["mcp"],"relatedModelIds":["qwen3.6-35b-a3b","claude-sonnet-5.5"],"popularity":45},{"id":"azure-apim-ai-gateway","name":"Azure API Management AI gateway","vendor":"Microsoft","category":"ai-gateway","tags":["gateway","api management","cloud"],"tagline":"AI gateway policies built into Azure API Management.","description":"Capabilities in Azure API Management for governing model, MCP and agent APIs: token limits and quotas per consumer, semantic caching, load balancing with circuit breakers, content-safety checks, and token metrics in Azure Monitor. Works with Microsoft Foundry and other providers such as Amazon Bedrock; a unified OpenAI-compatible model API is in preview.","pricingModel":"paid","openSource":false,"website":"https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities","docs":"https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities","platforms":["Azure"],"features":["Token limits & quotas","Semantic caching","Load balancing","Content safety"],"useCases":["enterprise"],"technologies":["mcp","guardrails"],"relatedModelIds":[],"popularity":45},{"id":"strix","name":"Strix","vendor":"Strix","category":"coding-assistant","tags":["security","pentesting","byok"],"tagline":"Open-source AI agents that pentest your app and prove each finding.","description":"Teams of autonomous agents run your application, probe it like an attacker and confirm each vulnerability with a working proof of concept before reporting it, then suggest patches. Runs from a CLI with Docker against a local folder, a repo or a live site, and in CI on pull requests; a hosted version is also offered. Bring your own model provider.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://www.strix.ai","github":"https://github.com/usestrix/strix","launchedYear":2025,"platforms":["CLI","GitHub Actions"],"features":["Validated proofs of concept","Multi-agent testing","CI integration"],"useCases":["coding","agents","enterprise"],"technologies":["agent-orchestration"],"relatedModelIds":[],"usage":{"appRank":11,"asOf":"2026-10-31"},"popularity":44},{"id":"kilo-code","name":"Kilo Code","vendor":"Kilo Code","category":"coding-assistant","tags":["ide","open-source","agent"],"tagline":"Open-source agentic coding with an orchestrator and hundreds of models.","description":"An open-source agentic coding extension for VS Code and JetBrains IDEs (also usable in Cursor and Windsurf). Its Orchestrator mode splits work across specialist sub-agents, and it supports hundreds of models with bring-your-own keys.","pricingModel":"open-source","openSource":true,"license":"Apache-2.0","website":"https://kilo.ai","github":"https://github.com/Kilo-Org/kilocode","launchedYear":2025,"platforms":["VS Code","JetBrains","CLI"],"features":["Orchestrator mode","500+ models","Bring your own key"],"useCases":["coding","agents"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":["claude-sonnet-5.5","glm-5.3","kimi-k3"],"usage":{"appRank":3,"asOf":"2026-10-31"},"popularity":44},{"id":"augment-code","name":"Augment Code","vendor":"Augment Code","category":"coding-assistant","tags":["agentic coding","large codebases"],"tagline":"Coding agents grounded in a deep context engine for large codebases.","description":"Agents for the editor, terminal and cloud that draw on Augment’s Context Engine, which indexes large codebases, plus AI pull-request review. Paid plans only.","pricingModel":"paid","openSource":false,"website":"https://www.augmentcode.com","platforms":["VS Code","JetBrains","CLI","Cloud"],"features":["Context Engine","CLI agent","Code review","Cloud agents"],"useCases":["coding","agents","enterprise"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":[],"popularity":44},{"id":"qwen-code","name":"Qwen Code","vendor":"Alibaba (Qwen)","category":"coding-assistant","tags":["cli","terminal"],"tagline":"Open-source terminal coding agent tuned for Qwen models.","description":"A command-line coding agent, adapted from Gemini CLI, that reads and edits code, runs commands and works with Qwen coder models or any OpenAI-compatible endpoint.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://qwenlm.github.io/qwen-code-docs/en/users/overview","github":"https://github.com/QwenLM/qwen-code","launchedYear":2025,"platforms":["CLI"],"features":["Terminal agent","OpenAI-compatible endpoints","MCP support"],"useCases":["coding","agents"],"technologies":["mcp"],"relatedModelIds":[],"popularity":44},{"id":"smolagents","name":"smolagents","vendor":"Hugging Face","category":"agent-framework","tags":["agents","code agent"],"tagline":"Minimal agents that think in code.","description":"A small Python library whose CodeAgent writes actions as Python snippets rather than JSON tool calls, runnable in sandboxes, with any model on the Hub or via API.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://huggingface.co/docs/smolagents","github":"https://github.com/huggingface/smolagents","launchedYear":2024,"platforms":["Python"],"features":["Code agents","Any LLM","Sandboxed execution"],"useCases":["agents","coding"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":44},{"id":"daytona","name":"Daytona","vendor":"Daytona","category":"agent-infra","tags":["sandbox","code execution"],"tagline":"Elastic sandboxes for AI code execution.","description":"Runs AI-generated code in fast, stateful sandboxes with filesystem, git and process APIs. The AGPL-licensed public repository was archived in 2026 and development continues in a private codebase, so new releases are hosted only.","pricingModel":"freemium","openSource":false,"website":"https://www.daytona.io","github":"https://github.com/daytonaio/daytona","platforms":["Cloud","Python","TypeScript"],"features":["Stateful sandboxes","Git & LSP APIs","Snapshots"],"useCases":["agents","coding"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":44},{"id":"outlines","name":"Outlines","vendor":".txt (dottxt)","category":"llm-framework","tags":["structured output","json"],"tagline":"Guaranteed structured generation with regex, JSON Schema and grammars.","description":"Constrains token sampling so outputs always match a JSON schema, regex or context-free grammar; works with transformers, vLLM, llama.cpp and hosted APIs.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://dottxt-ai.github.io/outlines/","github":"https://github.com/dottxt-ai/outlines","launchedYear":2023,"platforms":["Python"],"features":["JSON Schema / Pydantic","Regex & CFG constraints","Many backends"],"useCases":["extraction","agents"],"technologies":["constrained-decoding"],"relatedModelIds":[],"popularity":44},{"id":"deepeval","name":"DeepEval","vendor":"Confident AI","category":"observability","tags":["evals","testing"],"tagline":"Pytest-style unit testing for LLM outputs.","description":"Open-source framework with 30+ LLM-as-judge metrics (G-Eval, hallucination, RAG, agent metrics) that run like unit tests in CI, plus the Confident AI platform.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://deepeval.com","github":"https://github.com/confident-ai/deepeval","launchedYear":2023,"platforms":["Python","CI"],"features":["Pytest integration","G-Eval & RAG metrics","Red-teaming module"],"useCases":["coding","enterprise"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":44},{"id":"guardrails-ai","name":"Guardrails AI","vendor":"Guardrails AI","category":"guardrails","tags":["guardrails","validation"],"tagline":"Validators that check and correct LLM inputs and outputs.","description":"Python framework plus a hub of reusable validators (PII, toxicity, competitor mentions, schema checks) that run around LLM calls and can re-ask or fix failures.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://www.guardrailsai.com","github":"https://github.com/guardrails-ai/guardrails","launchedYear":2023,"platforms":["Python","Server"],"features":["Validator hub","Structured output checks","Guardrails server"],"useCases":["enterprise","extraction"],"technologies":["guardrails","constrained-decoding"],"relatedModelIds":[],"popularity":44},{"id":"amazon-bedrock-guardrails","name":"Amazon Bedrock Guardrails","vendor":"Amazon Web Services","category":"guardrails","tags":["ai security","aws"],"tagline":"Managed safety policies for generative AI on AWS.","description":"Configurable content filters, denied topics, sensitive-information redaction, prompt-attack detection and contextual grounding checks, applied to Bedrock models or any model through an API. Usage-based AWS pricing.","pricingModel":"paid","openSource":false,"website":"https://aws.amazon.com/bedrock/guardrails/","launchedYear":2024,"platforms":["AWS","API"],"features":["Content filters","PII redaction","Prompt-attack detection","Grounding checks"],"useCases":["enterprise"],"technologies":["guardrails"],"relatedModelIds":[],"popularity":44},{"id":"parallel","name":"Parallel","vendor":"Parallel Web Systems","category":"search-api","tags":["web search","agents"],"tagline":"Web search and research APIs built for AI agents.","description":"Search, extract and deep-research APIs that run on Parallel’s own web index and return ranked, token-efficient excerpts for agents rather than links for people. Usage-based, with free starting credits.","pricingModel":"freemium","openSource":false,"website":"https://parallel.ai","docs":"https://docs.parallel.ai","launchedYear":2025,"platforms":["API","MCP"],"features":["Search API","Extract API","Deep research tasks"],"useCases":["research","agents"],"technologies":["rag","mcp"],"relatedModelIds":[],"popularity":44},{"id":"krea","name":"Krea","vendor":"Krea AI","category":"image-video","tags":["image","video","creative suite"],"tagline":"Real-time AI image and video creation suite.","description":"Creative tool with real-time generation, upscaling, video and training of custom styles, offering Krea’s own models alongside third-party ones.","pricingModel":"freemium","openSource":false,"website":"https://www.krea.ai","platforms":["Web"],"features":["Real-time canvas","Upscaler","Many models in one place"],"useCases":["image-generation"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":44},{"id":"label-studio","name":"Label Studio","vendor":"HumanSignal","category":"data-ml","tags":["labeling","annotation"],"tagline":"Open-source data labelling for text, images, audio and LLM outputs.","description":"Configurable annotation UI for any data type, with ML-assisted pre-labelling and templates for LLM evaluation and RLHF preference data.","pricingModel":"freemium","openSource":true,"license":"Apache 2.0","website":"https://labelstud.io","github":"https://github.com/HumanSignal/label-studio","launchedYear":2019,"platforms":["Self-host","Cloud"],"features":["Any data type","ML-assisted labelling","LLM eval templates"],"useCases":["extraction","research"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":44},{"id":"grok-build","name":"Grok Build","vendor":"xAI (SpaceXAI)","category":"coding-assistant","tags":["cli","agent","terminal"],"tagline":"xAI’s open-source terminal coding agent.","description":"xAI’s first terminal coding agent, released in beta in May 2026 and open-sourced under Apache-2.0 in July 2026. It offers a plan mode with step-by-step approval, diffs before every change, parallel sub-agents for larger tasks and a headless mode for scripts. Its early data-upload feature has been off by default since July 2026.","pricingModel":"open-source","openSource":true,"license":"Apache-2.0","website":"https://github.com/xai-org/grok-build","github":"https://github.com/xai-org/grok-build","launchedYear":2026,"platforms":["CLI"],"features":["Plan mode with approvals","Diff before every change","Parallel sub-agents"],"useCases":["coding","agents"],"technologies":["agent-orchestration"],"relatedModelIds":["grok-4.7"],"popularity":42},{"id":"goose","name":"goose","vendor":"Block","category":"coding-assistant","tags":["agent","open-source","cli"],"tagline":"Open-source, extensible on-machine AI agent.","description":"An open-source agent from Block that runs on your machine with any LLM. It installs dependencies, runs shell commands, edits files and runs tests autonomously, and is extended through MCP servers. Available as a desktop app and CLI.","pricingModel":"open-source","openSource":true,"license":"Apache-2.0","website":"https://block.github.io/goose/","github":"https://github.com/aaif-goose/goose","launchedYear":2025,"platforms":["Desktop","CLI"],"features":["Any LLM","MCP extensions","Autonomous shell and file actions"],"useCases":["coding","agents"],"technologies":["mcp","agent-orchestration"],"relatedModelIds":["claude-sonnet-5.5","gpt-oss-120b"],"usage":{"appRank":44,"asOf":"2026-10-31"},"popularity":42},{"id":"langchain4j","name":"LangChain4j","vendor":"LangChain4j","category":"llm-framework","tags":["java"],"tagline":"LLM integration library for Java.","description":"A Java library with a unified API over many model providers and vector stores, AI services, tool calling, agents and RAG; integrates with Quarkus and Spring Boot.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://docs.langchain4j.dev","github":"https://github.com/langchain4j/langchain4j","launchedYear":2023,"platforms":["Java"],"features":["Unified model API","AI services","RAG & tools"],"useCases":["enterprise","chat"],"technologies":["rag"],"relatedModelIds":[],"popularity":42},{"id":"lancedb","name":"LanceDB","vendor":"LanceDB","category":"vector-database","tags":["vector db","embedded","multimodal"],"tagline":"Embedded, multimodal vector database on the Lance columnar format.","description":"Serverless/embedded vector search over the open Lance format — store vectors alongside images, video and metadata on local disk or object storage.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://lancedb.com","github":"https://github.com/lancedb/lancedb","launchedYear":2023,"platforms":["Python","TypeScript","Rust","Cloud"],"features":["Embedded (no server)","Multimodal data","Full-text + vector search"],"useCases":["research","multimodal","on-device"],"technologies":["vector-search","rag"],"relatedModelIds":[],"popularity":42},{"id":"jina-reader","name":"Jina Reader","vendor":"Jina AI (Elastic)","category":"search-api","tags":["crawler","markdown","grounding"],"tagline":"Turn any URL into LLM-ready markdown by prefixing r.jina.ai.","description":"Fetches and cleans web pages and PDFs into markdown for LLM input, plus a search endpoint (s.jina.ai) for grounding; Jina also offers embedding and reranker models.","pricingModel":"freemium","openSource":false,"website":"https://jina.ai/reader","github":"https://github.com/jina-ai/reader","launchedYear":2024,"platforms":["API"],"features":["URL → markdown","Search endpoint","PDF & image captions"],"useCases":["research","agents"],"technologies":["rag"],"relatedModelIds":[],"popularity":42},{"id":"pika","name":"Pika","vendor":"Pika Labs","category":"image-video","tags":["video generation","creative"],"tagline":"Playful AI video generation and effects.","description":"A consumer video app for generating and remixing short clips from text or images, with effects such as object swaps and stylised transitions.","pricingModel":"freemium","openSource":false,"website":"https://pika.art","launchedYear":2023,"platforms":["Web","iOS"],"features":["Text & image to video","Video effects","Remixing"],"useCases":["multimodal"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":42},{"id":"axolotl","name":"Axolotl","vendor":"Axolotl AI","category":"data-ml","tags":["fine tuning","training"],"tagline":"Config-driven fine-tuning for open LLMs.","description":"YAML-configured full fine-tuning, LoRA/QLoRA, preference tuning (DPO, GRPO) and multi-GPU training for most open model families.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://axolotl.ai","github":"https://github.com/axolotl-ai-cloud/axolotl","launchedYear":2023,"platforms":["Python","Linux"],"features":["LoRA / QLoRA","DPO & GRPO","Multi-GPU (FSDP, DeepSpeed)"],"useCases":["research","on-device"],"technologies":["fine-tuning","quantization"],"relatedModelIds":[],"popularity":42},{"id":"factory","name":"Factory","vendor":"Factory","category":"coding-assistant","tags":["agent","enterprise"],"tagline":"“Droid” agents for end-to-end software engineering.","description":"Factory’s Droids are autonomous agents for end-to-end engineering work — from tickets to pull requests — usable from the terminal, IDE, web and team chat, with native AGENTS.md support.","pricingModel":"paid","openSource":false,"website":"https://factory.ai","platforms":["CLI","IDE","Web","Slack"],"features":["Autonomous Droids","AGENTS.md support","Ticket-to-PR workflows"],"useCases":["coding","agents","enterprise"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":["claude-opus-5.5","gpt-6.1-sol"],"popularity":40},{"id":"letta","name":"Letta","vendor":"Letta","category":"agent-infra","tags":["memory","stateful agents","memgpt"],"tagline":"Stateful agents with self-editing memory (formerly MemGPT).","description":"Platform and open-source server for long-lived agents whose memory blocks persist and are edited by the agent itself, based on the MemGPT research.","pricingModel":"freemium","openSource":true,"license":"Apache 2.0","website":"https://www.letta.com","github":"https://github.com/letta-ai/letta","launchedYear":2023,"platforms":["Cloud","Self-host","Python","TypeScript"],"features":["Self-editing memory","Agent development environment","REST API"],"useCases":["agents","long-context"],"technologies":["agent-memory","agent-orchestration"],"relatedModelIds":[],"usage":{"appRank":30,"asOf":"2026-10-31"},"popularity":40},{"id":"vercel-sandbox","name":"Vercel Sandbox","vendor":"Vercel","category":"agent-infra","tags":["sandbox","code execution","micro vm"],"tagline":"Isolated Linux microVMs for running untrusted and AI-generated code.","description":"Each sandbox is its own Firecracker microVM with a dedicated kernel, driven from an SDK or the Vercel CLI. Network egress is firewalled and can inject credentials, snapshots restore a prepared filesystem, and drives keep files across runs. Billed on active CPU; limits vary by Vercel plan.","pricingModel":"freemium","openSource":false,"website":"https://vercel.com/sandbox","github":"https://github.com/vercel/sandbox","docs":"https://vercel.com/docs/vercel-sandbox","platforms":["Cloud","TypeScript","CLI"],"features":["Firecracker microVMs","Egress firewall","Snapshots","Persistent drives"],"useCases":["agents","coding"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":40},{"id":"trigger-dev","name":"Trigger.dev","vendor":"Trigger.dev","category":"agent-infra","tags":["background jobs","typescript"],"tagline":"Background jobs and long-running AI tasks in TypeScript.","description":"Runs TypeScript tasks with no timeouts, retries, queues and realtime progress streaming, which makes it a common home for agent runs and AI pipelines. Open source and self-hostable, with a managed cloud.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://trigger.dev","github":"https://github.com/triggerdotdev/trigger.dev","launchedYear":2022,"platforms":["TypeScript","Cloud","Self-host"],"features":["No timeouts","Retries & queues","Realtime streams"],"useCases":["agents"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":40},{"id":"baseten","name":"Baseten","vendor":"Baseten","category":"inference-platform","tags":["serving","gpu"],"tagline":"Production inference platform for custom and open models.","description":"Deploy open, fine-tuned or custom models as autoscaling APIs with optimised runtimes, or call hosted Model APIs for popular open models.","pricingModel":"paid","openSource":false,"website":"https://www.baseten.co","platforms":["Cloud"],"features":["Truss packaging","Autoscaling GPUs","Model APIs"],"useCases":["high-volume","enterprise"],"technologies":["speculative-decoding","quantization"],"relatedModelIds":[],"popularity":40},{"id":"kong-ai-gateway","name":"Kong AI Gateway","vendor":"Kong","category":"ai-gateway","tags":["gateway","api management","self-hosted"],"tagline":"AI plugins that turn the Kong API gateway into a multi-LLM gateway.","description":"A set of plugins for Kong Gateway that proxy requests to many LLM providers behind one API, with prompt templates, prompt guards and request/response transforms. Fits teams that already run Kong for their APIs; the plugins ship in the open-source gateway, and Kong’s commercial platform adds enterprise governance.","pricingModel":"freemium","openSource":true,"license":"Apache 2.0","website":"https://konghq.com/products/kong-ai-gateway","github":"https://github.com/Kong/kong","launchedYear":2024,"platforms":["Self-hosted","Kubernetes","Cloud"],"features":["Multi-LLM proxy","Prompt guard","Prompt templates","Request transforms"],"useCases":["enterprise"],"technologies":["guardrails"],"relatedModelIds":[],"popularity":40},{"id":"apigee-ai-gateway","name":"Apigee AI gateway","vendor":"Google Cloud","category":"ai-gateway","tags":["gateway","api management","cloud"],"tagline":"AI gateway policies in Google Cloud’s Apigee API platform.","description":"Apigee features for governing AI traffic: LLM token-limit policies, semantic caching, Model Armor checks for prompt injection and sensitive data, and MCP support with tool access managed through API products. Fits organisations already standardised on Apigee.","pricingModel":"paid","openSource":false,"website":"https://docs.cloud.google.com/apigee/docs/api-platform/get-started/ai-capabilities","docs":"https://docs.cloud.google.com/apigee/docs/api-platform/get-started/ai-capabilities","platforms":["Google Cloud"],"features":["Token limits","Semantic caching","Model Armor","MCP policies"],"useCases":["enterprise"],"technologies":["mcp","guardrails"],"relatedModelIds":[],"popularity":40},{"id":"opik","name":"Opik","vendor":"Comet","category":"observability","tags":["tracing","evals"],"tagline":"Open-source LLM tracing, evaluation and optimisation.","description":"Logs traces of LLM apps and agents, runs LLM-as-judge and heuristic metrics, and includes prompt and agent optimisers; self-host or use Comet’s cloud.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://www.comet.com/site/products/opik/","github":"https://github.com/comet-ml/opik","launchedYear":2024,"platforms":["Python","TypeScript","Cloud","Self-host"],"features":["Tracing","LLM-as-judge metrics","Prompt optimiser"],"useCases":["agents","enterprise"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":40},{"id":"lakera-guard","name":"Lakera Guard","vendor":"Lakera (Check Point)","category":"guardrails","tags":["ai security","prompt injection","llm firewall"],"tagline":"Real-time prompt-injection and data-leak protection API.","description":"A low-latency API that screens prompts and responses for prompt injection, jailbreaks, PII and harmful content; Lakera is also known for the Gandalf prompt-injection game.","pricingModel":"enterprise","openSource":false,"website":"https://www.lakera.ai","platforms":["Cloud","API"],"features":["Prompt-injection detection","PII & data leak checks","Policy dashboard"],"useCases":["enterprise","realtime"],"technologies":["guardrails"],"relatedModelIds":[],"popularity":40},{"id":"pyrit","name":"PyRIT","vendor":"Microsoft","category":"guardrails","tags":["red teaming","ai security"],"tagline":"Python Risk Identification Tool for red-teaming generative AI.","description":"Microsoft’s open-source framework for automating red-team attacks — jailbreaks, prompt injection, harmful content — against models and AI apps, with scorers and multi-turn attack strategies.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://microsoft.github.io/PyRIT","github":"https://github.com/microsoft/PyRIT","launchedYear":2024,"platforms":["Python"],"features":["Attack orchestrators","Multi-turn strategies","Scorers"],"useCases":["enterprise"],"technologies":["guardrails","llm-evals"],"relatedModelIds":[],"popularity":40},{"id":"fico-decision","name":"FICO Platform","vendor":"FICO","category":"decision-engine","tags":["rules engine","fintech"],"tagline":"Enterprise decision management and optimization.","description":"FICO’s platform for decision modeling, business rules (Blaze Advisor), optimization and analytics at bank scale.","pricingModel":"enterprise","openSource":false,"website":"https://www.fico.com/en/fico-platform","launchedYear":2019,"platforms":["Cloud","On-prem"],"features":["Business rules","Optimization","Decision analytics"],"useCases":["enterprise"],"technologies":["decision-modeling"],"relatedModelIds":[],"popularity":40},{"id":"dia","name":"Dia","vendor":"The Browser Company (Atlassian)","category":"ai-browser","tags":["ai browser"],"tagline":"AI-first browser from the makers of Arc.","description":"A browser built around a chat assistant that works across your open tabs, with reusable “skills” for writing, shopping and research.","pricingModel":"freemium","openSource":false,"website":"https://www.diabrowser.com","launchedYear":2025,"platforms":["macOS"],"features":["Chat with your tabs","Skills","Writing help"],"useCases":["chat","research","writing"],"technologies":[],"relatedModelIds":[],"popularity":40},{"id":"cartesia","name":"Cartesia","vendor":"Cartesia","category":"voice-audio","tags":["tts","voice api"],"tagline":"Ultra-low-latency voice API for real-time agents.","description":"Streaming text-to-speech (Sonic) and speech-to-text APIs with voice cloning, built for conversational agents.","pricingModel":"freemium","openSource":false,"website":"https://cartesia.ai","launchedYear":2024,"platforms":["API","Python","TypeScript"],"features":["Streaming TTS","Voice cloning","Speech-to-text"],"useCases":["realtime","agents"],"technologies":["realtime-voice"],"relatedModelIds":["sonic-3.6"],"popularity":40},{"id":"retell-ai","name":"Retell AI","vendor":"Retell AI","category":"voice-audio","tags":["voice-agents","telephony"],"tagline":"Build, test and deploy AI phone agents.","description":"A platform for production voice agents on phone calls: low-latency turn-taking, telephony and SIP integration, call transfer, batch outbound calling, testing and analytics, with a choice of LLMs and voices.","pricingModel":"paid","openSource":false,"website":"https://www.retellai.com","platforms":["API","Web"],"features":["Telephony & SIP","Turn-taking","Agent testing","Call analytics"],"useCases":["realtime","agents","enterprise"],"technologies":["realtime-voice"],"relatedModelIds":[],"popularity":40},{"id":"fish-audio","name":"Fish Audio","vendor":"Fish Audio","category":"voice-audio","tags":["tts","voice cloning"],"tagline":"Expressive text-to-speech and voice cloning.","description":"A TTS and voice-cloning platform with a large community voice library and an API, built on Fish Audio’s own speech models; the Fish Speech model code is published on GitHub.","pricingModel":"freemium","openSource":false,"website":"https://fish.audio","github":"https://github.com/fishaudio/fish-speech","platforms":["Web","API"],"features":["Voice cloning","Community voice library","TTS API"],"useCases":["realtime","multimodal"],"technologies":["realtime-voice"],"relatedModelIds":[],"popularity":40},{"id":"jasper","name":"Jasper","vendor":"Jasper","category":"productivity","tags":["marketing","content"],"tagline":"AI content platform for marketing teams.","description":"Generates on-brand marketing content with brand voice, style guides and campaign workflows, and runs marketing agents for teams. Paid plans with a free trial.","pricingModel":"paid","openSource":false,"website":"https://www.jasper.ai","launchedYear":2021,"platforms":["Web"],"features":["Brand voice","Marketing agents","Campaign workflows"],"useCases":["writing","enterprise"],"technologies":[],"relatedModelIds":[],"popularity":40},{"id":"isaac-lab","name":"Isaac Lab","vendor":"NVIDIA","category":"physical-ai","tags":["simulation","reinforcement learning","robotics"],"tagline":"GPU-accelerated robot learning framework on Isaac Sim.","description":"Open-source framework for training robot policies with reinforcement and imitation learning in massively parallel, physically accurate simulation built on NVIDIA Isaac Sim.","pricingModel":"open-source","openSource":true,"license":"BSD-3-Clause","website":"https://developer.nvidia.com/isaac/lab","github":"https://github.com/isaac-sim/IsaacLab","platforms":["Linux","Windows","Python"],"features":["Parallel GPU simulation","RL & imitation learning","Sim-to-real workflows"],"useCases":["agents","research"],"technologies":["vla"],"relatedModelIds":["gr00t-n1.7","cosmos-3"],"popularity":40},{"id":"strands-agents","name":"Strands Agents","vendor":"AWS","category":"agent-framework","tags":["agents","aws"],"tagline":"Model-driven open-source agent SDK from AWS.","description":"Build agents by giving a model a prompt and tools and letting it plan the loop; native MCP support, multi-agent patterns and deployment to AWS.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://strandsagents.com","github":"https://github.com/strands-agents/harness-sdk","launchedYear":2025,"platforms":["Python"],"features":["Model-driven loop","MCP tools","Multi-agent"],"useCases":["agents","enterprise"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":[],"popularity":38},{"id":"bifrost","name":"Bifrost","vendor":"Maxim AI","category":"ai-gateway","tags":["gateway","self-hosted","mcp gateway"],"tagline":"Fast open-source gateway in Go with budgets, virtual keys and an MCP gateway.","description":"A self-hosted gateway that puts many providers behind one OpenAI-compatible API, with provider fallback, load balancing, semantic caching, virtual keys and budgets. It can also front MCP tool servers, and exports traces over OpenTelemetry. An enterprise edition adds governance such as SSO and audit logs.","pricingModel":"freemium","openSource":true,"license":"Apache 2.0","website":"https://www.getmaxim.ai/bifrost","github":"https://github.com/maximhq/bifrost","launchedYear":2025,"platforms":["Self-hosted","Docker","Linux","macOS","Windows"],"features":["OpenAI-compatible API","Fallbacks","Virtual keys & budgets","MCP gateway"],"useCases":["high-volume","enterprise"],"technologies":["mcp"],"relatedModelIds":[],"popularity":38},{"id":"decisionrules","name":"DecisionRules","vendor":"DecisionRules","category":"decision-engine","tags":["rules engine","decision api","no code"],"tagline":"No-code business rules engine with a decision API.","description":"Cloud rules engine where business users author decision tables, trees and flows, exposed as a REST decision API.","pricingModel":"freemium","openSource":false,"website":"https://www.decisionrules.io","launchedYear":2020,"platforms":["Cloud","On-prem"],"features":["Decision tables & trees","REST decision API","Versioning & audit"],"useCases":["enterprise"],"technologies":["decision-modeling"],"relatedModelIds":[],"popularity":38},{"id":"lindy","name":"Lindy","vendor":"Lindy","category":"automation","tags":["no-code","agents"],"tagline":"AI employees for email, meetings, sales and support.","description":"A no-code platform for building AI agents (“Lindies”) that handle email triage, scheduling, meeting notes, lead outreach and support across thousands of app integrations.","pricingModel":"freemium","openSource":false,"website":"https://www.lindy.ai","launchedYear":2023,"platforms":["Web"],"features":["Agent templates","Email & calendar actions","App integrations"],"useCases":["agents","enterprise"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":38},{"id":"voiceflow","name":"Voiceflow","vendor":"Voiceflow","category":"automation","tags":["customer support","conversational ai"],"tagline":"Build and manage customer-experience agents for chat and voice.","description":"A collaborative platform for designing, deploying and monitoring AI agents across web chat, phone and messaging channels, aimed at customer-support teams and agencies.","pricingModel":"paid","openSource":false,"website":"https://www.voiceflow.com","launchedYear":2019,"platforms":["Web","API"],"features":["Visual agent designer","Chat & voice channels","Analytics"],"useCases":["chat","agents","enterprise"],"technologies":["agent-orchestration","realtime-voice"],"relatedModelIds":[],"popularity":38},{"id":"recraft","name":"Recraft","vendor":"Recraft","category":"image-video","tags":["image","design","vector"],"tagline":"Image generation for designers, including true vector output.","description":"A design-focused image generator with its own Recraft models, known for brand-consistent styles and native vector (SVG) output, plus mockups and editing tools; also available via API.","pricingModel":"freemium","openSource":false,"website":"https://www.recraft.ai","platforms":["Web","API"],"features":["Vector (SVG) output","Brand styles","Mockups"],"useCases":["image-generation"],"technologies":["diffusion"],"relatedModelIds":[],"popularity":38},{"id":"hume-ai","name":"Hume AI","vendor":"Hume AI","category":"voice-audio","tags":["voice","tts","api"],"tagline":"Emotionally expressive voice AI: speech-to-speech and TTS.","description":"Voice AI APIs focused on expressiveness: the Empathic Voice Interface (EVI) for speech-to-speech conversations and the Octave text-to-speech models, which take acting instructions for tone and emotion.","pricingModel":"freemium","openSource":false,"website":"https://www.hume.ai","platforms":["API"],"features":["Speech-to-speech (EVI)","Instructable TTS (Octave)","Voice design"],"useCases":["realtime","chat"],"technologies":["realtime-voice"],"relatedModelIds":[],"popularity":38},{"id":"qodo","name":"Qodo","vendor":"Qodo","category":"coding-assistant","tags":["code review","code quality"],"tagline":"Agentic code review and code-quality rules for teams.","description":"Reviews pull requests with agents that enforce team rules, and brings the same checks into VS Code and JetBrains IDEs. Paid team and enterprise plans with a 14-day trial; free for qualifying open-source projects.","pricingModel":"paid","openSource":false,"website":"https://www.qodo.ai","platforms":["VS Code","JetBrains","GitHub","GitLab"],"features":["Agentic PR review","Rules system","IDE integration"],"useCases":["coding","enterprise"],"technologies":[],"relatedModelIds":[],"popularity":36},{"id":"zep","name":"Zep","vendor":"Zep","category":"agent-infra","tags":["memory","knowledge graph"],"tagline":"Temporal knowledge-graph memory for agents.","description":"Builds a time-aware knowledge graph of users and business data for agent context; its graph engine, Graphiti, is open source.","pricingModel":"freemium","openSource":true,"license":"Apache 2.0","website":"https://www.getzep.com","github":"https://github.com/getzep/graphiti","platforms":["Cloud","Python","TypeScript","Go"],"features":["Temporal knowledge graph","Graphiti engine","Context assembly"],"useCases":["agents","enterprise"],"technologies":["agent-memory","rag"],"relatedModelIds":[],"popularity":36},{"id":"smithery","name":"Smithery","vendor":"Smithery","category":"agent-infra","tags":["mcp","registry"],"tagline":"Registry and hosting for MCP servers.","description":"Discover, install and host Model Context Protocol servers, with a CLI and gateway for connecting them to MCP clients.","pricingModel":"freemium","openSource":false,"website":"https://smithery.ai","platforms":["Cloud","CLI"],"features":["MCP server registry","Hosted MCP servers","CLI installer"],"useCases":["agents","coding"],"technologies":["mcp"],"relatedModelIds":[],"popularity":36},{"id":"baml","name":"BAML","vendor":"Boundary","category":"llm-framework","tags":["structured output","dsl"],"tagline":"A typed language for defining and testing LLM functions.","description":"Write prompts as typed functions in BAML files and generate clients for Python, TypeScript, Ruby and more; schema-aligned parsing recovers structured data even from imperfect model output.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://www.boundaryml.com","github":"https://github.com/BoundaryML/baml","platforms":["Python","TypeScript","Ruby","Go","VS Code"],"features":["Typed prompt functions","Schema-aligned parsing","Prompt playground"],"useCases":["extraction","agents"],"technologies":["constrained-decoding"],"relatedModelIds":[],"popularity":36},{"id":"vespa","name":"Vespa","vendor":"Vespa.ai","category":"vector-database","tags":["hybrid-search","open-source"],"tagline":"Open-source engine for search, recommendation and RAG at scale.","description":"An open-source serving engine that combines vector search, lexical search, structured filtering and machine-learned ranking — including multi-vector (ColBERT-style) retrieval — over large datasets in real time. Self-host or use Vespa Cloud.","pricingModel":"open-source","openSource":true,"license":"Apache-2.0","website":"https://vespa.ai","github":"https://github.com/vespa-engine/vespa","launchedYear":2017,"platforms":["Cloud","Self-hosted"],"features":["Hybrid search","Multi-vector retrieval","ML ranking"],"useCases":["research","enterprise","high-volume"],"technologies":["vector-search","rag"],"relatedModelIds":["pplx-embed-v2-late-9b"],"popularity":36},{"id":"nebius-token-factory","name":"Nebius Token Factory","vendor":"Nebius","category":"inference-platform","tags":["open models","api","gpu cloud"],"tagline":"Hosted inference and fine-tuning for open models.","description":"Nebius’s managed platform (formerly AI Studio) serving popular open-weight models through an OpenAI-compatible API, with fine-tuning and dedicated endpoints on Nebius’s own GPU cloud. Pay-as-you-go.","pricingModel":"paid","openSource":false,"website":"https://nebius.com/token-factory","platforms":["API"],"features":["Open-model API","Fine-tuning","Dedicated endpoints"],"useCases":["high-volume"],"technologies":["fine-tuning"],"relatedModelIds":[],"popularity":36},{"id":"agentgateway","name":"agentgateway","vendor":"Linux Foundation","category":"ai-gateway","tags":["gateway","mcp gateway","kubernetes","self-hosted"],"tagline":"Open-source proxy for LLM, MCP and agent-to-agent traffic in one place.","description":"A vendor-neutral gateway that handles model calls, MCP tool servers and A2A agent traffic alongside ordinary HTTP and gRPC, so one data plane covers AI and API traffic. Adds auth, observability and multi-tenancy; runs standalone or on Kubernetes. Started by Solo.io and now hosted by the Linux Foundation.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://agentgateway.dev","github":"https://github.com/agentgateway/agentgateway","docs":"https://agentgateway.dev/docs/","launchedYear":2025,"platforms":["Self-hosted","Kubernetes"],"features":["LLM gateway","MCP gateway","A2A traffic","Multi-tenancy"],"useCases":["enterprise","agents"],"technologies":["mcp"],"relatedModelIds":[],"popularity":36},{"id":"galileo","name":"Galileo","vendor":"Galileo","category":"observability","tags":["evals","monitoring"],"tagline":"Evaluation, observability and guardrails for AI agents.","description":"Evaluates and monitors agents and LLM apps with research-backed metrics and small evaluator models, and can turn those evaluators into runtime guardrails.","pricingModel":"paid","openSource":false,"website":"https://galileo.ai","platforms":["Cloud","Python","TypeScript"],"features":["Agent evaluation","Production monitoring","Runtime guardrails"],"useCases":["enterprise","agents"],"technologies":["llm-evals","guardrails"],"relatedModelIds":[],"popularity":36},{"id":"gumloop","name":"Gumloop","vendor":"Gumloop","category":"automation","tags":["no-code","workflows"],"tagline":"No-code AI automations and agents on a visual canvas.","description":"A no-code platform for building AI workflows and agents by connecting LLM steps, scrapers and app integrations on a drag-and-drop canvas, with triggers and scheduling.","pricingModel":"freemium","openSource":false,"website":"https://www.gumloop.com","platforms":["Web"],"features":["Visual workflow canvas","AI agents","App integrations"],"useCases":["agents","extraction"],"technologies":["agent-orchestration","mcp"],"relatedModelIds":[],"popularity":36},{"id":"relevance-ai","name":"Relevance AI","vendor":"Relevance AI","category":"automation","tags":["no code","ai workforce"],"tagline":"Build an “AI workforce” of agents for business teams.","description":"A no-code platform for role-based agents (sales, support, operations) that use tools and CRM integrations and work alongside people. Sold as an enterprise plan.","pricingModel":"enterprise","openSource":false,"website":"https://relevanceai.com","platforms":["Web"],"features":["No-code agents","Tool & CRM integrations","Multi-agent teams"],"useCases":["agents","enterprise"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":36},{"id":"vercel-workflow-sdk","name":"Workflow SDK","vendor":"Vercel","category":"agent-infra","tags":["durable execution","workflows","typescript"],"tagline":"Durable functions for long-running TypeScript apps and agents.","description":"Marks TypeScript functions with \"use workflow\" and \"use step\" so they retry, persist state and resume across stateless invocations, which lets agents run for hours without hitting serverless timeouts. Open source and portable; runs on Vercel or any Node-compatible host.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://workflow-sdk.dev","github":"https://github.com/vercel/workflow","launchedYear":2025,"platforms":["TypeScript","Self-host"],"features":["Durable steps","Automatic retries","Suspend & resume","Built-in observability"],"useCases":["agents"],"technologies":["agent-orchestration"],"relatedModelIds":[],"popularity":34},{"id":"sambanova-cloud","name":"SambaNova Cloud","vendor":"SambaNova","category":"inference-platform","tags":["fast inference","api"],"tagline":"Fast inference on SambaNova’s RDU chips.","description":"Hosted API for open models running on SambaNova’s custom Reconfigurable Dataflow Units, focused on high output speed for large models.","pricingModel":"freemium","openSource":false,"website":"https://cloud.sambanova.ai","launchedYear":2024,"platforms":["Cloud","On-prem"],"features":["Custom RDU hardware","OpenAI-compatible API"],"useCases":["realtime","high-volume"],"technologies":["custom-silicon"],"relatedModelIds":[],"popularity":34},{"id":"novita-ai","name":"Novita AI","vendor":"Novita AI","category":"inference-platform","tags":["open models","api","gpu cloud"],"tagline":"Low-cost APIs and GPUs for open models.","description":"Serverless APIs for open-weight LLMs, image and video models, plus GPU instances and sandboxes, priced pay-as-you-go.","pricingModel":"paid","openSource":false,"website":"https://novita.ai","platforms":["API","Cloud"],"features":["Open-model APIs","GPU instances","Agent sandboxes"],"useCases":["high-volume"],"technologies":[],"relatedModelIds":[],"popularity":34},{"id":"envoy-ai-gateway","name":"Envoy AI Gateway","vendor":"Envoy Proxy","category":"ai-gateway","tags":["gateway","kubernetes","self-hosted"],"tagline":"Open-source, Kubernetes-native LLM gateway built on Envoy.","description":"An Envoy project that routes app traffic to generative AI services: translates between provider API formats, handles upstream auth and failover, and enforces token-based rate limits. Runs on Kubernetes through Envoy Gateway.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://aigateway.envoyproxy.io","github":"https://github.com/envoyproxy/ai-gateway","docs":"https://aigateway.envoyproxy.io/docs","launchedYear":2025,"platforms":["Kubernetes","Self-hosted"],"features":["Provider API translation","Token rate limits","Failover","Upstream auth"],"useCases":["enterprise","high-volume"],"technologies":[],"relatedModelIds":[],"popularity":34},{"id":"taktile","name":"Taktile","vendor":"Taktile","category":"decision-engine","tags":["decisioning","fintech","risk"],"tagline":"Decision platform for risk and credit teams.","description":"Agentic decision platform for financial services — credit, fraud and KYC decisions with AI agents, data integrations and experimentation.","pricingModel":"enterprise","openSource":false,"website":"https://taktile.com","launchedYear":2020,"platforms":["Cloud"],"features":["Credit & fraud decisioning","AI agents","Experimentation"],"useCases":["enterprise"],"technologies":["decision-modeling"],"relatedModelIds":[],"popularity":34},{"id":"activepieces","name":"Activepieces","vendor":"Activepieces","category":"automation","tags":["open-source","workflows"],"tagline":"Open-source automation with AI steps and MCP servers.","description":"An open-source, self-hostable alternative to Zapier with a visual flow builder, hundreds of integrations (“pieces”), AI agent steps, and the ability to expose pieces as MCP servers.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://www.activepieces.com","github":"https://github.com/activepieces/activepieces","launchedYear":2023,"platforms":["Web","Self-hosted"],"features":["Visual flow builder","Pieces as MCP servers","Self-hosting"],"useCases":["agents","enterprise"],"technologies":["mcp","agent-orchestration"],"relatedModelIds":[],"popularity":34},{"id":"vellum","name":"Vellum","vendor":"Vellum","category":"automation","tags":["agent builder","low code"],"tagline":"Describe an agent in plain language and Vellum builds it.","description":"Turns natural-language prompts into agents and workflows, with a visual editor, an SDK for engineers, and built-in evaluations and versioning. Paid plans; new accounts get starter credits.","pricingModel":"paid","openSource":false,"website":"https://www.vellum.ai","platforms":["Web","Python","TypeScript"],"features":["Prompt-to-agent builder","Visual workflows","Evals & versioning"],"useCases":["agents","enterprise"],"technologies":["agent-orchestration","llm-evals"],"relatedModelIds":[],"popularity":34},{"id":"speechmatics","name":"Speechmatics","vendor":"Speechmatics","category":"voice-audio","tags":["stt","api"],"tagline":"Accurate speech-to-text in many languages, real-time or batch.","description":"A long-standing speech recognition provider offering real-time and batch transcription across dozens of languages, with diarization and translation, deployable in the cloud or on-premises, plus voice-agent APIs.","pricingModel":"freemium","openSource":false,"website":"https://www.speechmatics.com","platforms":["API","On-prem"],"features":["Real-time + batch STT","Dozens of languages","On-prem deployment"],"useCases":["extraction","realtime","enterprise"],"technologies":["realtime-voice"],"relatedModelIds":[],"popularity":34},{"id":"argilla","name":"Argilla","vendor":"Hugging Face","category":"data-ml","tags":["data labeling","datasets"],"tagline":"Open-source data curation and annotation for AI datasets.","description":"Collaborative labelling and feedback collection for building high-quality datasets for fine-tuning and evaluation, integrated with the Hugging Face Hub.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://argilla-io.github.io/argilla/latest/","github":"https://github.com/argilla-io/argilla","launchedYear":2021,"platforms":["Python","Self-host"],"features":["Annotation UI","Feedback datasets","Hugging Face Hub integration"],"useCases":["extraction"],"technologies":["fine-tuning","llm-evals"],"relatedModelIds":[],"popularity":34},{"id":"openpi","name":"openpi","vendor":"Physical Intelligence","category":"physical-ai","tags":["robotics","vla"],"tagline":"Open-source π0 / π0.5 robot foundation models and training code.","description":"Checkpoints and JAX/PyTorch code to run, serve and fine-tune Physical Intelligence’s π0, π0-FAST and π0.5 vision-language-action models on your own robot data.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://www.physicalintelligence.company","github":"https://github.com/Physical-Intelligence/openpi","launchedYear":2025,"platforms":["Python","Linux"],"features":["Base & fine-tuned checkpoints","LoRA fine-tuning","Policy server"],"useCases":["agents","research"],"technologies":["vla","fine-tuning"],"relatedModelIds":["pi-0.5"],"popularity":34},{"id":"apisix-ai-gateway","name":"Apache APISIX AI Gateway","vendor":"Apache Software Foundation","category":"ai-gateway","tags":["gateway","api management","self-hosted"],"tagline":"AI plugins for the Apache APISIX API gateway.","description":"Plugins that add LLM proxying to APISIX: routing and load balancing across model instances, token-based rate limits, regex prompt guards, response caching (exact or semantic) and token/latency logging. A natural fit if APISIX already fronts your APIs.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://apisix.apache.org/ai-gateway/","github":"https://github.com/apache/apisix","platforms":["Self-hosted","Kubernetes"],"features":["Multi-model load balancing","Token rate limits","Prompt guard","AI cache"],"useCases":["enterprise","high-volume"],"technologies":["guardrails"],"relatedModelIds":[],"popularity":33},{"id":"steel","name":"Steel","vendor":"Steel","category":"agent-infra","tags":["headless browser","browser automation"],"tagline":"Open-source browser API for AI agents.","description":"Hosted headless browsers for agents, with sessions, proxies, CAPTCHA handling and live viewing; the browser API is open source and can be self-hosted.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://steel.dev","github":"https://github.com/steel-dev/steel-browser","launchedYear":2024,"platforms":["Cloud","Python","TypeScript","Self-host"],"features":["Browser sessions","Proxies & CAPTCHA handling","Live session viewer"],"useCases":["agents"],"technologies":["computer-use"],"relatedModelIds":[],"popularity":32},{"id":"truefoundry-ai-gateway","name":"TrueFoundry AI Gateway","vendor":"TrueFoundry","category":"ai-gateway","tags":["gateway","router"],"tagline":"Enterprise AI gateway with routing, guardrails and per-team limits.","description":"An OpenAI-compatible gateway across many providers for chat, embeddings, images, audio and rerank, with weighted/latency/priority routing, retries, semantic caching, rate limits per user or app, guardrails and usage analytics. Managed SaaS with a free developer tier; VPC and on-prem deployment come with Enterprise.","pricingModel":"freemium","openSource":false,"website":"https://www.truefoundry.com/ai-gateway","docs":"https://www.truefoundry.com/docs/ai-gateway","platforms":["API","Self-hosted"],"features":["Latency-based routing","Semantic caching","Rate limits","Guardrails"],"useCases":["enterprise"],"technologies":["guardrails"],"relatedModelIds":[],"popularity":32},{"id":"garak","name":"garak","vendor":"NVIDIA","category":"guardrails","tags":["red teaming","vulnerability scanning"],"tagline":"LLM vulnerability scanner for red-teaming.","description":"Probes a model or endpoint for jailbreaks, prompt injection, data leakage, hallucination and toxicity with hundreds of attack probes, then reports what got through.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://github.com/NVIDIA/garak","github":"https://github.com/NVIDIA/garak","launchedYear":2023,"platforms":["Python","CLI"],"features":["Attack probe library","Any model endpoint","Reports"],"useCases":["enterprise"],"technologies":["guardrails","llm-evals"],"relatedModelIds":[],"popularity":32},{"id":"google-model-armor","name":"Model Armor","vendor":"Google Cloud","category":"guardrails","tags":["ai security","google cloud"],"tagline":"Screens prompts and responses for injection, data leaks and harmful content.","description":"A Google Cloud service that inspects LLM inputs and outputs for prompt injection and jailbreaks, sensitive data, malicious URLs and responsible-AI policy violations, independent of which model you use.","pricingModel":"paid","openSource":false,"website":"https://cloud.google.com/security/products/model-armor","launchedYear":2025,"platforms":["Google Cloud","API"],"features":["Prompt-injection detection","Sensitive data protection","Malicious URL detection"],"useCases":["enterprise"],"technologies":["guardrails"],"relatedModelIds":[],"popularity":32},{"id":"bland-ai","name":"Bland AI","vendor":"Bland","category":"voice-audio","tags":["voice agents","phone"],"tagline":"Enterprise AI phone calls at scale.","description":"A platform for programmable AI phone agents that handle high call volumes, with conversational pathways, its own voice stack and self-hosted deployment for enterprises.","pricingModel":"freemium","openSource":false,"website":"https://www.bland.ai","platforms":["API","Web"],"features":["Conversational pathways","High-volume calling","Self-hosted option"],"useCases":["realtime","enterprise"],"technologies":["realtime-voice"],"relatedModelIds":[],"popularity":32},{"id":"vercel-chat-sdk","name":"Chat SDK","vendor":"Vercel","category":"agent-framework","tags":["chatbots","slack","typescript"],"tagline":"One TypeScript bot for every chat platform.","description":"A unified TypeScript SDK for chat bots and agents: write handlers once and run them on Slack, Microsoft Teams, Google Chat, Discord, Telegram and WhatsApp through adapters, with JSX cards and AI responses streamed into threads.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://chat-sdk.dev","github":"https://github.com/vercel/chat","launchedYear":2025,"platforms":["TypeScript"],"features":["Platform adapters","JSX cards","Streaming replies","Type-safe handlers"],"useCases":["chat","agents"],"technologies":[],"relatedModelIds":[],"popularity":30},{"id":"braintrust-gateway","name":"Braintrust Gateway","vendor":"Braintrust","category":"ai-gateway","tags":["gateway","proxy","evals"],"tagline":"Hosted gateway to models from many providers, wired into Braintrust logging.","description":"Point an existing OpenAI, Anthropic or other SDK at Braintrust’s endpoint to call models from many providers with one key, and log the calls into Braintrust evals and traces. Replaces Braintrust’s older AI proxy; the hosted gateway is in public preview and free to use.","pricingModel":"freemium","openSource":false,"website":"https://www.braintrust.dev/docs/deploy/gateway","docs":"https://www.braintrust.dev/docs/deploy/gateway","platforms":["API"],"features":["Use existing SDKs","Multi-provider keys","Built-in logging"],"useCases":["enterprise"],"technologies":["llm-evals"],"relatedModelIds":[],"popularity":30},{"id":"mlflow-ai-gateway","name":"MLflow AI Gateway","vendor":"MLflow","category":"ai-gateway","tags":["gateway","self-hosted","mlops"],"tagline":"One governed endpoint for many LLM providers, inside MLflow.","description":"Part of the open-source MLflow platform: exposes several providers behind one endpoint, keeps provider keys in one place, splits traffic for A/B tests, chains failovers and logs requests for audit, with spend limits and budget alerts. Suits teams already using MLflow for evals and tracing.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://mlflow.org/docs/latest/genai/governance/ai-gateway/","github":"https://github.com/mlflow/mlflow","docs":"https://mlflow.org/docs/latest/genai/governance/ai-gateway/","platforms":["Python","Self-hosted"],"features":["Unified endpoint","Central key storage","Traffic splitting","Budgets"],"useCases":["enterprise"],"technologies":[],"relatedModelIds":[],"popularity":30},{"id":"requesty","name":"Requesty","vendor":"Requesty","category":"ai-gateway","tags":["gateway","router"],"tagline":"Managed LLM router with failover chains and spend governance.","description":"A hosted, OpenAI-compatible router across many providers: route by cost, latency or availability, set failover chains and weighted load balancing, and use prompt caching. Teams get PII masking, approved-model lists and access policies. Usage-based, with a percentage fee on model costs.","pricingModel":"paid","openSource":false,"website":"https://www.requesty.ai","platforms":["API"],"features":["Cost/latency routing","Failover chains","Prompt caching","PII masking"],"useCases":["high-volume","enterprise"],"technologies":[],"relatedModelIds":[],"popularity":30},{"id":"trulens","name":"TruLens","vendor":"Snowflake","category":"observability","tags":["evals","rag"],"tagline":"Open-source evaluation and tracing for LLM apps and agents.","description":"Instruments LLM apps with OpenTelemetry traces and scores them with feedback functions such as groundedness, context relevance and answer relevance; maintained by Snowflake.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://www.trulens.org","github":"https://github.com/truera/trulens","launchedYear":2020,"platforms":["Python"],"features":["Feedback functions","RAG triad metrics","OpenTelemetry tracing"],"useCases":["research","enterprise"],"technologies":["llm-evals","rag"],"relatedModelIds":[],"popularity":30},{"id":"llamafirewall","name":"LlamaFirewall","vendor":"Meta","category":"guardrails","tags":["guardrails","agent security"],"tagline":"Open-source guardrail system for AI agents.","description":"Part of Meta’s Purple Llama project: layered defences for agents including PromptGuard (jailbreak detection), agent alignment checks and CodeShield for insecure generated code.","pricingModel":"open-source","openSource":true,"website":"https://github.com/meta-llama/PurpleLlama","github":"https://github.com/meta-llama/PurpleLlama","launchedYear":2025,"platforms":["Python"],"features":["PromptGuard","Agent alignment checks","CodeShield"],"useCases":["agents","enterprise"],"technologies":["guardrails"],"relatedModelIds":["llama-guard-4"],"popularity":30},{"id":"nected","name":"Nected","vendor":"Nected","category":"decision-engine","tags":["rules engine","decision api","low code"],"tagline":"Low-code rules and workflow engine.","description":"Low-code decision engine for building rule sets, decision tables and workflows behind an API.","pricingModel":"freemium","openSource":false,"website":"https://www.nected.ai","launchedYear":2022,"platforms":["Cloud","Self-hosted"],"features":["Rule chains","Decision API","Workflow automation"],"useCases":["enterprise"],"technologies":["decision-modeling"],"relatedModelIds":[],"popularity":30},{"id":"synthflow","name":"Synthflow","vendor":"Synthflow","category":"voice-audio","tags":["voice agents","no code","phone"],"tagline":"No-code AI phone agents for businesses.","description":"Build and deploy inbound and outbound AI voice agents with a visual builder, telephony and CRM integrations, aimed at teams without engineers.","pricingModel":"paid","openSource":false,"website":"https://synthflow.ai","platforms":["Web","API"],"features":["Visual agent builder","Telephony","CRM integrations"],"useCases":["realtime","enterprise"],"technologies":["realtime-voice"],"relatedModelIds":[],"popularity":30},{"id":"genesis","name":"Genesis","vendor":"Genesis Embodied AI","category":"physical-ai","tags":["simulation","physics engine"],"tagline":"Generative physics platform for robotics and embodied AI.","description":"A Python-native universal physics engine and simulation platform designed for very fast, parallel robot-learning simulation.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://genesis-embodied-ai.github.io","github":"https://github.com/Genesis-Embodied-AI/genesis-world","launchedYear":2024,"platforms":["Python"],"features":["Multi-physics solvers","Parallel simulation","Photo-realistic rendering"],"useCases":["research"],"technologies":[],"relatedModelIds":[],"popularity":30},{"id":"eden-ai","name":"Eden AI","vendor":"Eden AI","category":"ai-gateway","tags":["gateway","unified api"],"tagline":"One API and one invoice for LLMs and other AI services.","description":"A unified API across many providers that covers LLMs plus speech, OCR, translation and image services, with routing between providers and per-request cost reporting on a single bill. Pay as you go, with enterprise plans for dedicated deployments.","pricingModel":"freemium","openSource":false,"website":"https://www.edenai.co","docs":"https://www.edenai.co/docs/v3/overview/ai-gateway","platforms":["API"],"features":["LLM + speech/OCR/vision APIs","Provider routing","Single invoice"],"useCases":["high-volume"],"technologies":[],"relatedModelIds":[],"popularity":28},{"id":"aera-technology","name":"Aera Technology","vendor":"Aera Technology","category":"decision-engine","tags":["decision intelligence"],"tagline":"Decision intelligence for the enterprise.","description":"Decision intelligence platform that automates supply-chain and operational decisions with agentic AI.","pricingModel":"enterprise","openSource":false,"website":"https://www.aeratechnology.com","launchedYear":2017,"platforms":["Cloud"],"features":["Decision automation","Supply chain","Agentic AI"],"useCases":["enterprise","agents"],"technologies":["decision-modeling"],"relatedModelIds":[],"popularity":28},{"id":"linkup","name":"Linkup","vendor":"Linkup","category":"search-api","tags":["web search","grounding"],"tagline":"Web search API for grounding AI answers.","description":"A search API that returns sourced web content and answers for LLM grounding, with standard and deep search modes and a monthly free credit allowance.","pricingModel":"freemium","openSource":false,"website":"https://www.linkup.so","platforms":["API","Python","TypeScript","MCP"],"features":["Standard & deep search","Sourced answers","MCP server"],"useCases":["research","agents"],"technologies":["rag","mcp"],"relatedModelIds":[],"popularity":28},{"id":"browseros","name":"BrowserOS","vendor":"BrowserOS","category":"ai-browser","tags":["ai browser","open source","chromium"],"tagline":"Open-source, privacy-first agentic browser.","description":"A Chromium-based browser with a built-in agent that can use your own API keys or local models, so browsing data can stay on your machine.","pricingModel":"open-source","openSource":true,"license":"AGPL-3.0","website":"https://www.browseros.com","github":"https://github.com/browseros-ai/BrowserOS","launchedYear":2025,"platforms":["macOS","Windows","Linux"],"features":["Built-in agent","Bring your own keys","Local models"],"useCases":["agents","on-device"],"technologies":["computer-use"],"relatedModelIds":[],"popularity":28},{"id":"rime","name":"Rime","vendor":"Rime","category":"voice-audio","tags":["tts","voice agents"],"tagline":"Low-latency text-to-speech for conversational voice agents.","description":"Speech synthesis models tuned for real-time phone and voice-agent use, with natural conversational delivery and on-prem deployment options for enterprises.","pricingModel":"freemium","openSource":false,"website":"https://rime.ai","platforms":["API"],"features":["Low-latency TTS","Conversational voices","On-prem option"],"useCases":["realtime","enterprise"],"technologies":["realtime-voice"],"relatedModelIds":[],"popularity":28},{"id":"fellou","name":"Fellou","vendor":"Fellou","category":"ai-browser","tags":["ai browser","browser agent"],"tagline":"An agentic browser that carries out web tasks for you.","description":"A desktop browser built around an agent that plans and runs multi-step web tasks, deep research and cross-site workflows.","pricingModel":"freemium","openSource":false,"website":"https://fellou.ai","launchedYear":2025,"platforms":["Desktop"],"features":["Agentic tasks","Deep research","Cross-site workflows"],"useCases":["agents","research"],"technologies":["computer-use"],"relatedModelIds":[],"popularity":26},{"id":"opera-neon","name":"Opera Neon","vendor":"Opera","category":"ai-browser","tags":["ai browser","browser agent"],"tagline":"Subscription agentic browser from Opera.","description":"Opera’s subscription agentic browser that can browse and act on web pages on your behalf.","pricingModel":"paid","openSource":false,"website":"https://www.operaneon.com","launchedYear":2025,"platforms":["macOS","Windows"],"features":["Browser agent"],"useCases":["agents"],"technologies":["computer-use"],"relatedModelIds":[],"popularity":22},{"id":"chatgpt-atlas","name":"ChatGPT Atlas","vendor":"OpenAI","category":"ai-browser","tags":["ai browser","browser agent","discontinued"],"tagline":"Discontinued: OpenAI’s browser with ChatGPT and agent mode built in.","description":"A macOS web browser with ChatGPT in a sidebar on every page, browser memories, and an agent mode that could complete tasks in your tabs. OpenAI retired it on 9 August 2026 and folded its browsing into the redesigned ChatGPT desktop app, with browser automation moving to Codex.","pricingModel":"freemium","openSource":false,"website":"https://chatgpt.com/atlas","launchedYear":2025,"platforms":["macOS"],"features":["ChatGPT sidebar","Agent mode","Browser memories"],"useCases":["agents","research","chat"],"technologies":["computer-use"],"relatedModelIds":[],"popularity":20},{"id":"llm-guard","name":"LLM Guard","vendor":"Protect AI (Palo Alto Networks)","category":"guardrails","tags":["ai security","pii","archived"],"tagline":"Archived: open-source scanners for LLM prompts and outputs.","description":"A library of input and output scanners — prompt injection, secrets, PII anonymisation, toxicity, code — to sanitise LLM traffic. The GitHub repository was archived in July 2026, so the code no longer receives fixes.","pricingModel":"open-source","openSource":true,"license":"MIT","website":"https://protectai.com/llm-guard","github":"https://github.com/protectai/llm-guard","launchedYear":2023,"platforms":["Python","API"],"features":["Input & output scanners","PII anonymisation","Self-hosted API"],"useCases":["enterprise"],"technologies":["guardrails"],"relatedModelIds":[],"popularity":18},{"id":"flowise","name":"Flowise","vendor":"FlowiseAI (Workday)","category":"automation","tags":["low code","visual builder","discontinued"],"tagline":"Discontinued: open-source low-code builder for AI agents and chatflows.","description":"Built chatbots, RAG and multi-agent systems by connecting nodes in a visual canvas. After Workday acquired it, the team sunset the project: the repository was archived in August 2026 and Flowise reached end of life on 31 August 2026. The Apache 2.0 code stays available to fork.","pricingModel":"open-source","openSource":true,"license":"Apache 2.0","website":"https://flowiseai.com","github":"https://github.com/FlowiseAI/Flowise","launchedYear":2023,"platforms":["Self-host","Cloud"],"features":["Agentflows","RAG chatflows","Embeddable chat widget"],"useCases":["agents","chat"],"technologies":["agent-orchestration","rag"],"relatedModelIds":[],"popularity":18},{"id":"system-one-adapter","name":"System One adapter","vendor":"TypeSafe AI","category":"decision-engine","tags":["decision model","structured output","system one"],"tagline":"Turn LLM calls into typed, System One-style decisions.","description":"Open-source Python wrapper from TypeSafe AI that constrains LLMs to System One-shaped questions — choices, scores and true/false judgments with typed outputs — so the same code can later run on Jev, TypeSafe’s dedicated decision model.","pricingModel":"open-source","openSource":true,"website":"https://typesafe.ai","github":"https://github.com/typesafe-ai/system-one-adapter-python","docs":"https://docs.typesafe.ai/introduction","launchedYear":2026,"platforms":["Python"],"features":["Choice / Score / Noul questions","Typed outputs","Swap LLM ↔ Jev"],"useCases":["extraction","agents","enterprise"],"technologies":["system-one","constrained-decoding"],"relatedModelIds":["jev"],"popularity":14}],"total":264}