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.

Browse Mastodon, Bluesky, X, Misskey, Nostr, Pixiv, Fanbox and RSS all in one app. One timeline, all your accounts, cross-post everywhere.

01Result

DimensionDev/Flare ↗

DimensionDev/Flare AI coding statistics: 1%

of 1,030 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

1% agent · top contributor 70%2 contributors

individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

agent commits

1,020

other considered commits

agent contributors

70%

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

7assisted

3autonomous

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: 3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	6	0.6%
Claude Code	Anthropic	4	0.4%

03Evidence

Inspect the matches

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

Matched commit samples

d2a7cb87 on GitHubFix Android CI SDK packagesGitHub Copilot
9c39d495 on GitHubUpdate shared/src/commonMain/kotlin/dev/dimension/flare/data/network/nostrGitHub Copilot
425282d6 on GitHubApply suggestions from code reviewGitHub Copilot
9ce54859 on GitHubtest: use barrier in mock for concurrent bluesky refresh testClaude Code
63a1da62 on GitHubtest: stabilize concurrent bluesky refresh testClaude Code
2d3d57e7 on GitHubfix: stabilize flaky pre-translation and list handler testsClaude Code

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	1,778
Merge commits removed	−537
CI / dependency bots removed	−211
Considered	1,030

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 →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →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 DimensionDev/Flare

Scan another repository

Try

Month	Agent share	Considered commits
2026-01	0%	3
2026-02	0%	70
2026-03	2.2%	227
2026-04	0%	150
2026-05	3%	135
2026-06	0%	182
2026-07	0%	112
2026-08	0%	88
2026-09	1.6%	63