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.

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

01Result

ag-ui-protocol/ag-ui ↗

ag-ui-protocol/ag-ui AI coding statistics: 25.1%

of 2,028 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

25.1% agent · top contributor 19.4%38 contributors

org-wide

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

509

agent commits

1,519

other considered commits

agent contributors

19.4%

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

509assisted

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

Agent-attributed commit share by month
Month	Agent share	Considered commits
2026-01	100%	1
2026-02	22.3%	94
2026-03	19.3%	197
2026-04	20.8%	303
2026-05	31.2%	234
2026-06	34%	353
2026-07	14.1%	191
2026-08	30.4%	497
2026-09	9.5%	158

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	480	23.7%
GitHub Copilot	GitHub	26	1.3%
Cursor Agent	Anysphere	3	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

008cb07e on GitHubfeat(spring): make the Spring integration publishable via publish-release.Claude Code
0f2aa210 on GitHubci: run the Spring integration test reactor on PRsClaude Code
5610c3eb on GitHubfeat(spring-ai): optional MESSAGES_SNAPSHOT of the run's produced conversaClaude Code
ffa836d0 on GitHubtest(dotnet): pass options in rebased testsGitHub Copilot
2874bd90 on GitHubrefactor(dotnet): merge metadata with JsonObjectGitHub Copilot
5797a2f3 on GitHubfix(dotnet): preserve serialized metadata keysGitHub Copilot
dea7fa5d on GitHubfix(langgraph): preserve runtime config in prepare_regenerate_stream (#174Cursor Agent
c30d1178 on GitHubfix(langgraph): detect same-id content edits in prepare_stream (#1748)Cursor Agent
02989fcb on GitHubfix(langgraph): handle non-string dict keys in dump_json_safeCursor 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	3,107
Merge commits removed	−954
CI / dependency bots removed	−125
Considered	2,028

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 ag-ui-protocol/ag-ui

Scan another repository

Try