Magi Council — AI skill for Claude Code

MAGI Council — three AI heads that deliberate, vote and execute

A **MAGI council of three heads** (Melchior / Balthasar / Casper — the persona lives in the seat, the provider is swappable: kimi, codex, claude, Ollama, any CLI or OpenAI-compatible API) that deliberate on your questions and vote on decisions, with a ruling, minority report, mind changes between rounds and human arbitration. With **memory**: a local knowledge graph that ingests your agent sessions and decisions and injects them into every deliberation. And in **production mode**: the council approves a plan, an executor implements it on a dedicated branch, the council reviews the diff and — on unanimous approval — it merges itself.

The UI is a MAGI-style web app (design based on TomaszRewak/MAGI) with a single text box, like a CLI. Runs on Windows, macOS and Linux.



What you need to get started (from scratch, on any machine)

1. Python 3.14+.
2. A reachable Postgres (any standard install; the system default is dbname=debate host=localhost, port 5432, user = your OS user). If you have none, on Windows the repo ships a portable postmaster in experiments/pg and bin\start-magi.bat starts it.
3. At least one head (with no heads the system runs "degraded" and only you can close decisions):
   • kimi (or another MCP-capable agent CLI: claude, …) — investigates the repo with tools and votes via MCP;
   • codex or another plain-text CLI — votes with the journal inlined in the prompt (journal: "inline" mode);
   • Ollama / LM Studio / any OpenAI-compatible endpoint — local API head at no cost. All configured in debate-mcp/heads.json; you don't need all three.
4. Optional: an OpenAI account (codex) and/or Moonshot (kimi) if you use those cloud heads.

Install and first run

git clone https://github.com/Adrian-Sandwic