Back to directory

BeeAI Framework

A toolkit, available in Python and TypeScript, for building production-ready autonomous agents and multi-agent systems that can reason, act and collaborate.

BeeAI Framework

BeeAI Framework is a toolkit for building intelligent, autonomous agents and multi-agent systems in either Python or TypeScript. It provides a Requirement Agent for creating predictable, rule-constrained behavior across different language models, a general agent abstraction for reasoning and acting, a backend module for connecting to any LLM provider through a unified interface, built-in and custom tools such as web search and code execution, and retrieval-augmented generation support.

Recent updates added a Workflows concept for composing multi-agent systems, support for the Model Context Protocol and the Agent Communication Protocol (now part of the Agent2Agent protocol under the Linux Foundation), and support for newer models such as DeepSeek R1 and LLaMA 3.3. Starter templates are available for both the Python and TypeScript libraries.

It is released under the Apache 2.0 license.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.