Dataset: 2026-10-27-catalog-ai-v2
Ruleset: b2e8889c66f7
Scanned: 2026-10-27
Window: February–September 15, 2026

Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Run any process, on your machine or in an AI agent's environment, as if it were a pod in your Kubernetes cluster: real env vars, DNS, network, traffic.

01Result

metalbear-co/mirrord ↗

metalbear-co/mirrord AI coding statistics: 12.8%

of 830 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

12.8% agent · top contributor 35.8%13 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

106

agent commits

724

other considered commits

agent contributors

35.8%

largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

106assisted

0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Peak month: 24.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	105	12.7%
Cursor Agent	Anysphere	1	0.1%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

809cd1df on GitHubPoint AI agents at the agent-started trial from operator-required errorsClaude Code
216ff8c5 on GitHubSay the trial is Enterprise tier, and what that unlocksClaude Code
f5a506a2 on GitHubSurface agent-started trials on the install pathsClaude Code
c8d5d717 on GitHubRemove unstable marking from feature.network.dns.filter (#4341)Cursor Agent

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window	1,170
Merge commits removed	−267
CI / dependency bots removed	−73
Considered	830

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Rust AI coding statisticsCompare evidence across Rust repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →

Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli metalbear-co/mirrord

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	1.6%	64
2026-03	7.7%	78
2026-04	7.5%	80
2026-05	15.6%	45
2026-06	9.6%	73
2026-07	17.6%	165
2026-08	9.5%	199
2026-09	24.6%	126