AI tools

Directory of AI tools — coding assistants, agent frameworks, vector databases, observability and more — with pricing model and open-source status.

Coding assistants

• Claude Code — Anthropic. Agentic coding in your terminal, IDE and browser.
• GitHub Copilot — GitHub (Microsoft). The most widely deployed AI pair programmer.
• Cursor — Anysphere. The AI-native code editor.
• Codex — OpenAI. OpenAI’s cloud and CLI coding agent.
• Windsurf — Cognition. Agentic IDE with the Cascade agent.
• Cline — Cline. Open-source autonomous coding agent for VS Code.
• Aider — Aider. AI pair programming in your terminal.
• Devin — Cognition. Autonomous AI software engineer.
• v0 — Vercel. Generate full-stack web apps from prompts.
• Lovable — Lovable. Build apps by chatting with AI.
• Replit Agent — Replit. Build and deploy apps from natural language.
• CodeRabbit — CodeRabbit. AI code reviews on every pull request.
• Gemini CLI — Google. Open-source terminal coding agent powered by Gemini.
• OpenCode — SST. Open-source, provider-agnostic coding agent for the terminal.
• Kiro — AWS. Spec-driven agentic IDE from AWS.
• Jules — Google. Asynchronous coding agent that works on your GitHub repos.

Agent frameworks

• Model Context Protocol — Anthropic (open standard). The open standard for connecting AI to tools and data.
• LangGraph — LangChain. Stateful, controllable agent orchestration.
• Claude Agent SDK — Anthropic. The agent harness behind Claude Code, as a library.
• OpenAI Agents SDK — OpenAI. Lightweight multi-agent workflows with handoffs.
• CrewAI — CrewAI. Role-based multi-agent crews.
• Agent Development Kit — Google. Google’s open-source framework for multi-agent systems.
• Pydantic AI — Pydantic. Type-safe agent framework for Python.
• Mastra — Mastra. The TypeScript agent framework.
• Microsoft Agent Framework — Microsoft. Successor to AutoGen and Semantic Kernel.
• smolagents — Hugging Face. Minimal agents that think in code.
• Strands Agents — AWS. Model-driven open-source agent SDK from AWS.

LLM & RAG frameworks

• LangChain — LangChain. The most widely used LLM application framework.
• LlamaIndex — LlamaIndex. Data framework for RAG and document agents.
• AI SDK — Vercel. The TypeScript toolkit for AI apps.
• DSPy — Stanford NLP. Program — don’t prompt — language models.
• Haystack — deepset. Production-ready RAG pipelines.
• Outlines — .txt (dottxt). Guaranteed structured generation with regex, JSON Schema and grammars.
• Instructor — Jason Liu & community. Pydantic-typed structured outputs from any LLM.
• BAML — Boundary. A typed language for defining and testing LLM functions.

Vector databases

• Pinecone — Pinecone. Fully managed serverless vector database.
• pgvector — Open source. Vector similarity search inside Postgres.
• Qdrant — Qdrant. High-performance vector search engine in Rust.
• Weaviate — Weaviate. AI-native open-source vector database.
• Chroma — Chroma. The open-source embedding database.
• Milvus — Zilliz. Vector database for billion-scale workloads.
• turbopuffer — turbopuffer. Serverless vector and full-text search on object storage.
• LanceDB — LanceDB. Embedded, multimodal vector database on the Lance columnar format.
• MongoDB Atlas Vector Search — MongoDB. Vector search inside your operational MongoDB database.
• Elasticsearch — Elastic. Search engine with dense, sparse and hybrid vector retrieval.

Inference & model hosting

• OpenRouter — OpenRouter. One API for hundreds of models.
• Ollama — Ollama. Run open models locally with one command.
• vLLM — vLLM project. High-throughput LLM serving engine.
• llama.cpp — ggml. LLM inference in C/C++ on any hardware.
• LM Studio — Element Labs. Desktop app to discover and run local LLMs.
• Together AI — Together AI. Fast inference and fine-tuning for open models.
• Fireworks AI — Fireworks AI. Production inference for open models.
• Groq — Groq. Ultra-fast inference on custom LPUs.
• Cerebras Inference — Cerebras. Wafer-scale speed for open models.
• Amazon Bedrock — AWS. Foundation models on AWS.
• Vertex AI — Google Cloud. Google Cloud’s AI platform.
• Azure AI Foundry — Microsoft. Build and run AI apps on Azure.
• Replicate — Replicate. Run open-source models with an API.
• Modal — Modal Labs. Serverless GPUs for AI workloads.
• SGLang — LMSYS / SGLang community. High-throughput serving engine for LLMs and VLMs.
• NVIDIA NIM — NVIDIA. Prebuilt, optimised inference microservices for NVIDIA GPUs.
• SambaNova Cloud — SambaNova. Fast inference on SambaNova’s RDU chips.
• Baseten — Baseten. Production inference platform for custom and open models.

Observability & evals

• LangSmith — LangChain. Tracing, evals and monitoring for LLM apps.
• Langfuse — Langfuse. Open-source LLM engineering platform.
• Braintrust — Braintrust. The evals platform for AI products.
• Arize Phoenix — Arize AI. Open-source AI observability and evaluation.
• promptfoo — promptfoo. Test and red-team your LLM apps.
• Helicone — Helicone. LLM observability via a one-line proxy.
• W&B Weave — Weights & Biases. Track and evaluate LLM applications.
• Opik — Comet. Open-source LLM tracing, evaluation and optimisation.
• Ragas — Exploding Gradients. Evaluation metrics for RAG pipelines and agents.
• DeepEval — Confident AI. Pytest-style unit testing for LLM outputs.

Decision & rules engines

• GoRules — GoRules. Open-source business rules engine (ZEN) with a visual editor.
• DecisionRules — DecisionRules. No-code business rules engine with a decision API.
• Camunda — Camunda. Process orchestration with BPMN & DMN decisions.
• Drools — Apache KIE. The classic Java business rules management system.
• Nected — Nected. Low-code rules and workflow engine.
• Taktile — Taktile. Decision platform for risk and credit teams.
• Aera Technology — Aera Technology. Decision intelligence for the enterprise.
• FICO Platform — FICO. Enterprise decision management and optimization.
• System One adapter — TypeSafe AI. Turn LLM calls into typed, System One-style decisions.

Agent infrastructure

• E2B — E2B. Secure cloud sandboxes for running AI-generated code.
• Daytona — Daytona. Elastic sandboxes for AI code execution.
• Browserbase — Browserbase. Headless browsers in the cloud for AI agents.
• Browser Use — Browser Use. Open-source library that lets LLMs operate a web browser.
• Mem0 — Mem0. Memory layer for AI agents and assistants.
• Zep — Zep. Temporal knowledge-graph memory for agents.
• Letta — Letta. Stateful agents with self-editing memory (formerly MemGPT).
• Composio — Composio. Hundreds of authenticated tool integrations for agents.
• Smithery — Smithery. Registry and hosting for MCP servers.

AI browsers

• ChatGPT Atlas — OpenAI. OpenAI’s browser with ChatGPT and agent mode built in.
• Comet — Perplexity. Perplexity’s agentic browser.
• Dia — The Browser Company (Atlassian). AI-first browser from the makers of Arc.
• Opera Neon — Opera. Subscription agentic browser from Opera.

AI security & guardrails

• NeMo Guardrails — NVIDIA. Open-source toolkit for programmable LLM guardrails.
• Guardrails AI — Guardrails AI. Validators that check and correct LLM inputs and outputs.
• Lakera Guard — Lakera (Check Point). Real-time prompt-injection and data-leak protection API.
• LLM Guard — Protect AI (Palo Alto Networks). Open-source scanners for LLM prompts and outputs.
• garak — NVIDIA. LLM vulnerability scanner for red-teaming.
• LlamaFirewall — Meta. Open-source guardrail system for AI agents.

Robotics & physical AI

• Isaac Lab — NVIDIA. GPU-accelerated robot learning framework on Isaac Sim.
• LeRobot — Hugging Face. Open-source models, datasets and tools for real-world robotics.
• MuJoCo — Google DeepMind. Fast, accurate physics engine for robotics research.
• Genesis — Genesis Embodied AI. Generative physics platform for robotics and embodied AI.
• openpi — Physical Intelligence. Open-source π0 / π0.5 robot foundation models and training code.

Workflow automation

• n8n — n8n. Fair-code workflow automation with AI agents.
• Zapier — Zapier. Automate across 8,000+ apps with AI.
• Make — Make (Celonis). Visual automation platform.
• Dify — LangGenius. Open-source platform for building LLM apps and agent workflows.
• Langflow — DataStax (IBM). Visual builder for agents and RAG flows.
• Flowise — FlowiseAI (Workday). Open-source low-code builder for AI agents and chatflows.

Search & web data APIs

• Exa — Exa. Web search API built for AI.
• Tavily — Tavily. Real-time search API for agents.
• Firecrawl — Firecrawl. Turn websites into LLM-ready data.
• Perplexity Sonar API — Perplexity. Search-grounded answers via API.
• Brave Search API — Brave. Independent web index via API.
• Jina Reader — Jina AI (Elastic). Turn any URL into LLM-ready markdown by prefixing r.jina.ai.

Chat assistants

• ChatGPT — OpenAI. The most widely used AI assistant.
• Claude — Anthropic. Anthropic’s AI assistant for thinking and making.
• Gemini — Google. Google’s AI assistant across Search, Android and Workspace.
• Perplexity — Perplexity. Answer engine with citations.
• Microsoft Copilot — Microsoft. AI across Windows and Microsoft 365.
• Le Chat — Mistral AI. Mistral’s fast, European AI assistant.
• Grok — SpaceXAI. SpaceXAI’s assistant with real-time X data.
• Meta AI — Meta. Meta’s assistant across WhatsApp, Instagram, Facebook and glasses.

Image & video generation

• Midjourney — Midjourney. Distinctive, high-aesthetic image generation.
• Runway — Runway. AI video generation and editing for creators.
• Flow (Veo) — Google. AI filmmaking with Veo.
• Sora — OpenAI. OpenAI’s video generation app.
• ComfyUI — Comfy Org. Node-based open-source diffusion workflows.
• FLUX — Black Forest Labs. State-of-the-art image models, open and pro.
• Ideogram — Ideogram. Image generation with excellent typography.
• Krea — Krea AI. Real-time AI image and video creation suite.

Voice & audio

• ElevenLabs — ElevenLabs. Lifelike AI voice, dubbing and voice agents.
• Deepgram — Deepgram. Speech-to-text and voice AI APIs.
• AssemblyAI — AssemblyAI. Speech AI models for transcription and understanding.
• Whisper — OpenAI. Open-source multilingual speech recognition.
• LiveKit Agents — LiveKit. Framework for real-time voice AI agents.
• Vapi — Vapi. Voice AI agents for developers.
• Suno — Suno. Make any song you can imagine.
• Pipecat — Daily. Open-source framework for real-time voice and multimodal agents.
• Cartesia — Cartesia. Ultra-low-latency voice API for real-time agents.

Data & ML platforms

• Hugging Face — Hugging Face. The home of open models and datasets.
• Unsloth — Unsloth AI. Fine-tune LLMs faster with less memory.
• Scale AI — Scale AI. Data labeling and evaluation for frontier AI.
• Weights & Biases — Weights & Biases. The AI developer platform.
• Axolotl — Axolotl AI. Config-driven fine-tuning for open LLMs.
• TRL — Hugging Face. Post-training library: SFT, DPO, GRPO and RL for LLMs.
• Label Studio — HumanSignal. Open-source data labelling for text, images, audio and LLM outputs.

Productivity & knowledge

• NotebookLM — Google. AI research notebook grounded in your sources.
• Notion AI — Notion. AI agents inside your workspace.
• Glean — Glean. Work AI and enterprise search.
• Granola — Granola. AI notepad for meetings — no bot required.
• Gamma — Gamma. Generate presentations, documents and sites from a prompt.
• Fireflies.ai — Fireflies.ai. AI meeting notetaker, transcription and search.