Happy slice of mcp pizzaMCP.pizza

Archon

MCP.Pizza Chef: coleam00

You write the steps down once — plan, build, run the tests, review, open the pull request — and every run follows them in the same order instead of depending on the model's mood. Each run happens in its own copy of the project, so five can go at once without tripping over each other. Start one from the terminal, a web dashboard, Slack, Telegram or GitHub, then come back to a finished branch. Free and open source; it drives Claude Code, so you bring your own model access.

Coding

Use This MCP client To

Kick off a fix and come back to a pull request Run the same review steps on every change Keep several jobs going at once without conflicts Make sure tests run before any code is proposed Reuse my process across every project I work on

README

Archon - AI Agent Builder

Archon Logo

🚀 **CURRENT VERSION** 🚀

[ V6 - Tool Library and MCP Integration ] Prebuilt tools, examples, and MCP server integration

🔄 IMPORTANT UPDATE (March 31st): Archon now includes a library of prebuilt tools, examples, and MCP server integrations. Archon can now incorporate these resources when building new agents, significantly enhancing capabilities and reducing hallucinations. Note that the examples/tool library for Archon is just starting out. Please feel free to contribute examples, MCP servers, and prebuilt tools!

Archon is the world's first "Agenteer", an AI agent designed to autonomously build, refine, and optimize other AI agents.

It serves both as a practical tool for developers and as an educational framework demonstrating the evolution of agentic systems. Archon will be developed in iterations, starting with just a simple Pydantic AI agent that can build other Pydantic AI agents, all the way to a full agentic workflow using LangGraph that can build other AI agents with any framework. Through its iterative development, Archon showcases the power of planning, feedback loops, and domain-specific knowledge in creating robust AI agents.

Important Links

  • The current version of Archon is V6 as mentioned above - see V6 Documentation for details.

  • I just created the Archon community forum over in the oTTomator Think Tank! Please post any questions you have there!

  • GitHub Kanban board for feature implementation and bug squashing.

Vision

Archon demonstrates three key principles in modern AI development:

  1. Agentic Reasoning: Planning, iterative feedback, and self-evaluation overcome the limitations of purely reactive systems
  2. Domain Knowledge Integration: Seamless embedding of frameworks like Pydantic AI and LangGraph within autonomous workflows
  3. Scalable Architecture: Modular design supporting maintainability, cost optimization, and ethical AI practices

Getting Started with V6 (current version)

Since V6 is the current version of Archon, all the code for V6 is in both the main directory and archon/iterations/v6-tool-library-integration directory.

Note that the examples/tool library for Archon is just starting out. Please feel free to contribute examples, MCP servers, and prebuilt tools!

Archon FAQ

Which coding assistant does it drive?
It is built around Claude Code, and runs can be started from the terminal, a web dashboard, Slack, Telegram or GitHub.
Do I need an account or key?
Archon itself is free and open source; you bring your own coding agent and model access.
Can I use this to get a finished pull request while I do something else?
Yes — start a workflow, walk away, and return to a branch with the pull request already opened.
How hard is setup?
Developer level: install Bun, the GitHub command line tool and Claude Code, clone the project, then run the guided wizard.
Can several runs happen at the same time?
Yes — each one gets its own copy of the project, so parallel work does not collide.
Is this the older Archon that stored documentation and tasks?
No. That Python version is kept on an archived branch; the current project is a workflow engine for coding agents.