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.

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

01Result

Kiln-AI/Kiln ↗

Kiln-AI/Kiln AI coding statistics: 49.3%

of 2,222 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

49.3% agent · top contributor 29%10 contributors

org-wide

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

1,096

agent commits

1,126

other considered commits

agent contributors

29%

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

1096assisted

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: 93.5%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	1086	48.9%
Gemini CLI	Google	7	0.3%
Cursor Agent	Anysphere	5	0.2%

03Evidence

Inspect the matches

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

Matched commit samples

943179b8 on GitHubRetry a model reply that came back empty instead of failing the caseClaude Code
808c4af2 on GitHubfix(web): stop indexedDBStore from hanging, and from clobbering unread staClaude Code
5611259d on GitHubTake the Full Trace link out of Output, and three fixes to the lookClaude Code
04dbbaaa on GitHubUpdate app/desktop/git_sync/middleware.pyGemini CLI
ad1251d2 on GitHubUpdate libs/server/kiln_server/utils/agent_checks/policy_lookup.pyGemini CLI
b96dce24 on GitHubUpdate libs/core/kiln_ai/utils/config.pyGemini CLI
97cf7007 on GitHubrefactor: tighten up jobs empty-state copyCursor Agent
8b9199f2 on GitHubfeat: rename sidebar "In progress" to "Jobs" with active-state stylingCursor Agent
23046241 on GitHubAdd Gemini 3.5 Flash to model list (#1422)Cursor 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 window	2,987
Merge commits removed	−719
CI / dependency bots removed	−46
Considered	2,222

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 Kiln-AI/Kiln

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	272
2026-03	8.3%	242
2026-04	36.4%	536
2026-05	32.6%	233
2026-06	76.9%	277
2026-07	81.4%	172
2026-08	93.5%	367
2026-09	88.6%	123