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.

Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.

01Result

MCPJam/inspector ↗

MCPJam/inspector AI coding statistics: 63.7%

of 2,864 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

63.7% agent · top contributor 77.2%18 contributors

team

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

1,825

agent commits

1,039

other considered commits

agent contributors

77.2%

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

1771assisted

54autonomous

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: 87.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	1718	60%
Cursor Agent	Anysphere	91	3.2%
Devin	Cognition	58	2%

03Evidence

Inspect the matches

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

Matched commit samples

db191db0 on GitHubGenerate cases breadcrumb (#5125)Claude Code
dca4099f on GitHubRemove grading from User Testing (#5122)Claude Code
f202497c on GitHubRelease: wait for the registry to serve a first-published evaluators beforClaude Code
b38d0bfd on GitHubfix(servers): honor Auto-connect switch in the connect hook (#4925)Cursor Agent
31814d85 on GitHubTrim leftover Browser chrome ahead of the local launch (#4930)Cursor Agent
029976fc on GitHubLet Playground Tools list and run conversation page tools (#4919)Cursor Agent
fff704ee on GitHubdocs homepage: refresh title, subtitle, intro, hero, and getting-started cDevin
f202b377 on GitHubdocs: remove Chat from README (#4960)Devin
2c56c141 on GitHubShow the Invite team members CTA to hosted guests (#4828)Devin

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	3,239
Merge commits removed	−76
CI / dependency bots removed	−299
Considered	2,864

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 →Devin commitsBrowse repositories with detected Devin 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 MCPJam/inspector

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	12.7%	189
2026-03	15.6%	179
2026-04	19.9%	287
2026-05	58.7%	283
2026-06	80.4%	465
2026-07	81.1%	417
2026-08	87.4%	652
2026-09	68.4%	392