Back to directory

Awesome Agents

A curated list of open-source frameworks, products, and tools for building AI agents, spanning orchestration frameworks, testing, software development, and browser automation.

Awesome Agents

Awesome Agents is a curated list of open-source tools and products for building AI agents. Its frameworks section alone covers dozens of projects, from general orchestration frameworks to more specialized ones for multi-agent coordination, coding-specific agents, and lightweight agent-building libraries, each with a one-line description of what it does.

Beyond frameworks, the list is organized into sections for testing and evaluation, software development, research, conversational and general agents, game and simulation agents, memory and knowledge management, automation, and browser control. A companion list separately catalogs open-source environments for running coding agents in parallel, terminal and tmux harnesses, and desktop or container-isolated workspaces.

It is a Markdown list.

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.