BAML
A typed language for defining and testing LLM functions.
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.
- Vendor
- Boundary
- Category
- LLM & RAG frameworks
- Pricing
- Open source
- Open source
- Yes
- License
- Apache 2.0
- Platforms
- Python, TypeScript, Ruby, Go, VS Code
- Website
- boundaryml.com
Features
- Typed prompt functions
- Schema-aligned parsing
- Prompt playground
Best for
- Extraction & classification
- Agents
More llm & rag frameworks
- LangChain — LangChain. The most widely used LLM application framework.
- AI SDK — Vercel. The TypeScript toolkit for AI apps.
- LlamaIndex — LlamaIndex. Data framework for RAG and document agents.
- DSPy — Stanford NLP. Program — don’t prompt — language models.
- Haystack — deepset. Production-ready RAG pipelines.
- Instructor — Jason Liu & community. Pydantic-typed structured outputs from any LLM.
- Outlines — .txt (dottxt). Guaranteed structured generation with regex, JSON Schema and grammars.