Pulse
2026-09-18-v3.0
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.

A self-hosted open source photo management service.

01Result

LibrePhotos/librephotos ↗

LibrePhotos/librephotos AI coding statistics: 87.9%

of 372 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
87.9% agent · top contributor 56%8 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

327
agent commits
45
other considered commits
8
agent contributors
56%
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

144assisted
183autonomous

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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0290%120
2026-03100%8
2026-0492.4%119
2026-0566.7%18
2026-0692.6%27
2026-0788.6%44
2026-0852.4%21
2026-0993.3%15

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

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub18349.2%
Claude CodeAnthropic13736.8%
Cursor AgentAnysphere71.9%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7f74905b on GitHubFix IndexError in face encoding generation and ValueError in face trainingGitHub Copilot
  • 15f377e9 on GitHubAdd migration to clear 128-dim face encodings and stale clustersGitHub Copilot
  • 6c63885c on GitHubfix: filter inhomogeneous face encodings in create_all_clustersGitHub Copilot
  • 45ac2568 on GitHubfix(captioning): start the model download when a caption is asked for too Claude Code
  • 5bd4d48f on GitHubfix(captioning): caption with the q4 LFM2.5-VL export, not q4f16 (#2014)Claude Code
  • 06130a89 on GitHubfix(captioning): surface the sidecar's error instead of KeyError: 'captionClaude Code
  • f5ece3de on GitHubfix: restore Event album loading, lightbox, and add-to-album (#1978)Cursor Agent
  • d7312a77 on GitHubImprove README with tech stack, dev setup, and contributing guidelinesCursor Agent
  • dbeae94c on GitHubImprove README with tech stack, system requirements, and related projectsCursor 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 window595
Merge commits removed−131
CI / dependency bots removed−92
Considered372

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Python AI coding statisticsCompare evidence across Python 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 LibrePhotos/librephotos

Scan another repository

Try