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.

Install our local first extensions for your favorite AI IDE or Terminal Agent. Process your histories into reusable skills with Lore. Sync your conversations to the cloud. File issues and requests.

01Result

specstoryai/getspecstory ↗

specstoryai/getspecstory AI coding statistics: 23.9%

of 557 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

23.9% agent · top contributor 40.6%10 contributors

org-wide

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

133

agent commits

424

other considered commits

agent contributors

40.6%

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

132assisted

1autonomous

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: 50%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	124	22.3%
GitHub Copilot	GitHub	9	1.6%

03Evidence

Inspect the matches

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

Matched commit samples

0c0ebeff on GitHubPi watcher: sweep the session directory after the watch is added and againClaude Code
cd3f4597 on GitHubfix(piagent): check the header cwd in the default layout so a colliding enClaude Code
17c9db79 on GitHubfix(piagent): return pi's exit status so run stops the watcher before exitClaude Code
60fecef8 on GitHubfix(piagent): harden check probe and session parsing limitsGitHub Copilot
bcdf857b on GitHubCheck repo too.GitHub Copilot
e16a59a0 on GitHubComment fixGitHub Copilot

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	779
Merge commits removed	−188
CI / dependency bots removed	−34
Considered	557

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 →Go AI coding statisticsCompare evidence across Go 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 specstoryai/getspecstory

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0.6%	156
2026-03	7.4%	27
2026-04	50%	6
2026-05	22.7%	22
2026-06	32.5%	80
2026-07	44.2%	138
2026-08	25.9%	85
2026-09	30.2%	43