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.

bump

Release version bumps, opened automatically once a merge lands.

clean

The disk janitor: finished runs get their worktrees folded, worktrees whose run record is already gone get reclaimed too, and the shared build cache is pruned to its cap.

conduct

The conductor: a single agent seat that arranges the queue.

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.

disk

Disk accounting: how much magi’s own directories occupy, how much space is left on the volume they live on, and how the shared build cache is pruned.

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.

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: magi repos and GET /api/repos.

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.

talk

The standing conversation: a place to think out loud with an agent between tasks, reachable from a phone.

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.