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.

自部署的摄影作品网站，支持多种功能特性。PicImpact，分享你和世界！

01Result

besscroft/PicImpact ↗

besscroft/PicImpact AI coding statistics: 80.9%

of 194 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

80.9% agent · top contributor 100%1 contributor

individual

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

157

agent commits

other considered commits

agent contributors

100%

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

157assisted

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	157	80.9%

03Evidence

Inspect the matches

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

Matched commit samples

36db1593 on GitHubdocs: correct multi-replica task-cancellation section (§5)Claude Code
ce43d5e1 on GitHubdocs: address review notes on cache handler connection count + tag sweepClaude Code
156024d6 on GitHubfeat: PostgreSQL-backed cross-replica Data Cache handler (P2)Claude 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	313
Merge commits removed	−119
CI / dependency bots removed	−0
Considered	194

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 besscroft/PicImpact

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	77.4%	93
2026-04	0%	3
2026-05	100%	61
2026-06	75%	32
2026-07	0%	5