kerbelp/metatron

View on GitHub ↗

Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewed markdown files in your repo; agents consult them before writing code and record what they learn. Files-first, no server required; MCP as an optional serving layer.

23 ★3 forksPythonUpdated 1mo ago

What you need to know

Metatron stores codebase conventions as versioned files in git that coding agents read before writing code, offering a files-first mode and an MCP serving-layer mode.

Install

pip install getmetatron

Key features

  • Versioned codebase conventions in git
  • Files-first mode
  • MCP serving-layer mode

Best for

Keeping coding agents aligned with project conventions across a team.

Platforms: Docker

Topics

agentic-aiagentic-workflowai-agentai-coding-assistantai-toolsclaude-codecursor-editordevtoolsllm-toolsmcpmcp-servermcp-toolsmodel-context-protocoltree-sitter
Stars
23★
Forks
3
Language
Python
License
MIT
Created
2026-06-03
Last push
2026-07-29