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.

Home Assistant integration framework for (garbage collection) schedules

01Result

mampfes/hacs_waste_collection_schedule ↗

mampfes/hacs_waste_collection_schedule AI coding statistics: 60%

of 1,287 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

60% agent · top contributor 44.6%186 contributors

org-wide

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

772

agent commits

515

other considered commits

186

agent contributors

44.6%

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

736assisted

36autonomous

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: 86.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	690	53.6%
GitHub Copilot	GitHub	91	7.1%
Cursor Agent	Anysphere	3	0.2%
OpenAI Codex	OpenAI	2	0.2%

03Evidence

Inspect the matches

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

Matched commit samples

5e5b09ce on GitHubMap kiedysmieci_info bulky wasteClaude Code
c61c91e2 on GitHubMap kiedysmieci_info electronics, textiles and non-pickup entriesClaude Code
37067104 on GitHubtest(abfall_io): cover comma separated f_abfallartenClaude Code
fbfa8883 on GitHubAdd source: SMOLO a.s. Trinec, Czech Republic (smolo_cz) (#7367)GitHub Copilot
1b4dce44 on GitHubadd(maur_ch): Add waste collection for Gemeinde Maur, Zurich, Switzerland GitHub Copilot
5724f877 on GitHubAdd source for Gmina Bochnia (Poland) - bochnia_gmina_pl (#7214)GitHub Copilot
4efbc55e on GitHubfix(mohu_bp_hu): accept old and new OctoberCMS partial keys (#7242)Cursor Agent
e5377ce4 on GitHubfix(eastdevon_gov_uk): migrate to shared Cloud9 API (#7151)Cursor Agent
ca022ba1 on GitHubfeat: add Bathurst Regional Council (NSW) waste collection source (#6792)Cursor Agent
4dae9ee5 on GitHubfix Enfield address matching (#6149)OpenAI Codex
42b0422a on GitHubAdd Enfield Council source (#4917) (#6013)OpenAI Codex

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	1,796
Merge commits removed	−130
CI / dependency bots removed	−379
Considered	1,287

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 mampfes/hacs_waste_collection_schedule

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	6.8%	73
2026-03	24.7%	97
2026-04	77.9%	380
2026-05	73.3%	195
2026-06	86.9%	153
2026-07	34.4%	209
2026-08	44.3%	88
2026-09	65.2%	92