Back to directory

Awesome AI Agents

A curated collection of open-source AI agent frameworks, research papers and production deployment guides, organized by what a developer wants to build and by capability.

Awesome AI Agents

Awesome AI Agents catalogs open-source frameworks and research for building autonomous AI agents, organized around what someone wants to build, such as a multi-agent team, a coding assistant, a data-analysis agent or a desktop-automation agent, as well as by topic areas including multi-agent patterns, enterprise deployment, agent evaluation, MCP integration and computer-use agents.

It links out to specific frameworks such as CrewAI, AutoGen, LangChain, Open Interpreter and OpenDevin for particular use cases, and includes an interactive framework comparison and recommendation guide alongside worked use-case examples such as medical report analysis and recruitment-pipeline automation.

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.