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.

Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.

01Result

inkeep/agents ↗

inkeep/agents AI coding statistics: 47%

of 996 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

47% agent · top contributor 34.2%19 contributors

org-wide

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

468

agent commits

528

other considered commits

agent contributors

34.2%

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

427assisted

41autonomous

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	395	39.7%
Cursor Agent	Anysphere	81	8.1%
GitHub Copilot	GitHub	3	0.3%

03Evidence

Inspect the matches

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

Matched commit samples

83340a2f on GitHubFix chat-to-edit turn erroring after a successful tool call (#2073) (#3417Claude Code
56894a20 on GitHubDisable self-service organization creation (#2058) (#3414)Claude Code
166133c1 on GitHubfeat(agents-api): allowlist sub-agent read/update tools for builder promptClaude Code
bd27fcc6 on GitHubtrace conversation widget view (#2109) (#3422)Cursor Agent
6fe221c7 on GitHubfix(sentinel): propagate Sentinel 429s instead of masking as 502 (#1504) (Cursor Agent
456f7649 on GitHubFeat/fix cursor skills rule dupe (#1508) (#3331)Cursor Agent
895eb328 on GitHubchore: sync from agents-private (#3219)GitHub Copilot
08ba7c27 on GitHubPrd 5972 2 (#2290)GitHub Copilot
9c293ff3 on GitHubprd-5972 (#1744)GitHub 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	1,408
Merge commits removed	−0
CI / dependency bots removed	−412
Considered	996

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 →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 inkeep/agents

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	43%	551
2026-03	51.7%	288
2026-04	43.2%	125
2026-05	100%	11
2026-06	100%	17
2026-07	0%	4