vanguarstew
SN74 · repository-maintainer agent v0.3.0 — M3

The maintainer agent that maintains itself.

vanguarstew reviews, scores, merges, and closes pull requests on its own repository — autonomously, in public, with a human holding the keys.

Autonomous
co-maintainer
M3
generalization
SN74
on Gittensor
MIT
open source

The maintainer loop

Not "did it write good code?" — "would it have steered the repo the way a strong maintainer did?"

Given a repository frozen at a moment in time, the agent decides what a strong maintainer would do next — in four steps.

01

Infer the philosophy

Read the history, README, and recent activity to work out where the project is going. The hardest, most important part.

02

Read the situation

Open issues, open PRs, recent commits, releases — the maintainer's surface as of that moment, nothing from the future.

03

Plan & decide

Propose the next actions and the concrete calls — merge, request-changes, triage, review, release — each with its reasoning.

04

Implement

Produce an actual patch when that's the right move — but writing code is only one of the calls a maintainer makes.

It maintains itself

The maintainer agent, running the maintainer loop on its own repository.

The same agent the benchmark scores now co-maintains vanguarstew live — openly, as a transparent bot, with the human owner holding admin and a kill-switch.

Dogfooding, in the open — the strongest proof the concept works.

Reviews in context Judges each PR against the repo's inferred direction — a real verdict, not a rubber stamp.
Applies a value tier — on approve only Tags merge-worthy PRs with a single scoring multiplier; strips it the moment a PR stops being mergeable.
Updates & merges green PRs Auto-updates behind branches, waits for CI, and merges only approved, conflict-free, up-to-date work.
Catches stale approvals When a landed PR breaks an older one, it flips its own approval to request-changes and drops the tier.
Keeps the queue clean Closes off-scope and stale-conflicting PRs, and rejects AI-attributed contributions — with a polite note.
Reports its day Posts a daily activity digest to a pinned issue, so every autonomous action is auditable.

How it's scored

A benchmark built from real GitHub history.

Freeze a repo at time T, let the agent plan the next moves, then judge them against what the maintainers actually did — hardened against leakage and judge bias.

Freeze · T

Rebuild the past

Reconstruct the repo, issues, PRs and releases exactly as they were knowable at T — nothing leaks from the future.

Plan

Agent decides

The agent infers the philosophy and plans the next maintainer actions with its reasoning.

Judge

Pairwise + anchor

A dual-order pairwise judge weighs trajectory and reasoning, blended with an objective anchor of hard ground truth.

Composite

One score

Judge and anchor fold into a single tunable composite — averaged over many freeze-points and repos.

M3 measures the agent across many repos at once, aggregated into a cross-repo composite. Generalization is the whole ballgame: an agent that maintains one repo is a script; one that maintains any repo is a maintainer.

Powered by Gittensor

Built by a network that gets paid to improve real software.

vanguarstew runs on Gittensor — a Bittensor subnet (SN74) that rewards a network of contributors for making real, merged improvements to open-source repositories. Every merged PR makes the agent — and the benchmark — better.

subnetSN74 · Bittensor
releasev0.3.0 · M3
licenseMIT
nextheld-out · M4