Crate magi 

magi — a blind multi-agent implementation competition.

One task, several agents, and a graph that decides which implementation survives without a human reading the diff:

1. implement — N agents solve the same task in isolated git worktrees, unaware of each other.
2. judge — M judges rank the candidates blind: labels A/B/C, a per-judge presentation order, attribution trailers stripped at write time by a commit-msg hook and again at presentation time.
3. deliberate — if the first choices disagree, the judges argue, with magi as the facilitator. A facilitator made of code cannot leak an author.
4. vote — final votes are collected one-to-one and privately, so nobody can drift toward a visible majority.
5. review — the winner enters a bounded review + real-machine verification loop with a fixer that may reject a finding with an argument.
6. gate — configured commands must pass before anything merges.

Everything is recorded, so the by-products are real numbers: per-agent win rates, per-reviewer precision, and how often execution caught what static review missed. See stats.

Modules

agent

Driving agent CLIs.

ask

Questions: what an agent does when the next decision is the owner’s.

blind

Blindness: label assignment, attribution stripping, and leak detection.

chat

The browser interview: magi plan for somebody holding a phone.

config

Run configuration: the agent roster, the shape of the graph, and the blindness / verification policy.

daemon

The unattended loop: take the next task, run the graph, record what happened, take the next one.

git

Git plumbing.

graph

The competition graph.

land

Landing the winner: watch the pull request, fix what it complains about, and merge it.

md

GFM markdown, parsed into a serializable node tree instead of HTML.

plan

magi plan: the interview that turns an idea into a task file worth competing.

proc

Spawning child processes without putting a window on the operator’s screen.

prompt

Prompt construction.

queue

The task queue: what magi should do next, and who asked for it.

report

Terminal rendering.

repos

Local repository discovery for the plan surface’s repository picker.

rng

A seeded PRNG, so that label assignment and session ids are reproducible from a run id.

run

Run state: what happened, where it is stored, and how a run is resumed.

stats

Aggregate statistics over every recorded run.

tui

The observation deck.

updater

Self-update, via kaishin.

verdict

Structured answers extracted from free-form agent output.

web

The web UI: magi’s queue and run history, readable from a phone.