#42 · Primary category： LLM Application Frameworks
baml
The programming language for agents
Project last updated：08/29/26
GitHub Stars
9.1K
Forks
489
Contributors
105
License
Apache-2.0
Why we included this project
BAML treats an LLM prompt as a typed function: you declare the inputs, the output schema, and which model to call, and a Rust compiler generates a client you can invoke from Python, TypeScript, Go, Ruby, Java, or C#. Teams that have outgrown freeform prompt strings get structured, validated outputs they can build against without hand-rolling JSON parsing. The IDE playground and VS Code tooling keep prompt iteration fast, and the built-in retry, fallback, and round-robin policies plus schema-aligned parsing handle multi-model agent and extraction pipelines, even when the model lacks native tool-calling support. Since you can adopt BAML for just the prompts you want.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform