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.

Agenta is a workspace where you and your team build agents and automations.

01Result

Agenta-AI/agenta ↗

Agenta-AI/agenta AI coding statistics: 6.2%

of 9,799 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

6.2% agent · top contributor 62.5%15 contributors

team

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

611

agent commits

9,188

other considered commits

agent contributors

62.5%

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

611assisted

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: 13.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	524	5.3%
GitHub Copilot	GitHub	51	0.5%
Devin	Cognition	34	0.3%
Cursor Agent	Anysphere	2	0%

03Evidence

Inspect the matches

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

Matched commit samples

3a1d6a55 on GitHubfeat(frontend): hide built-in skills and version numbers from the registryClaude Code
7d2342a7 on GitHub[5512] feat(api): meta-first skill provenance (Package 2, API) (#6619)Claude Code
c8d0ce0d on GitHubfix(frontend): the /m list toolbars follow desktop's axis and fit their roClaude Code
a24cfeb5 on GitHubPotential fix for pull request finding 'CodeQL / Clear-text logging of senGitHub Copilot
b6a21726 on GitHubPotential fix for pull request findingGitHub Copilot
f190eba5 on GitHubPotential fix for pull request findingGitHub Copilot
477ee62f on GitHubGuard _load_jinja2() call in except handler to avoid masking original erroDevin
8bfd2caa on GitHubUpdate docs/docs/prompt-engineering/playground/05-fallback-models-and-retrDevin
a216ce06 on GitHubUpdate api/pytest.iniDevin
8439d0d5 on GitHubdocs(demo): add UI flow screenshot for workspace reset passwordCursor Agent
509428ab on GitHubfeat(workspace): wire reset-password action into members menuCursor 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	13,683
Merge commits removed	−3,587
CI / dependency bots removed	−297
Considered	9,799

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 →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 Agenta-AI/agenta

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	3.2%	1035
2026-03	4.7%	1042
2026-04	0.6%	467
2026-05	8%	908
2026-06	13.2%	999
2026-07	9.9%	1343
2026-08	7.2%	2490
2026-09	0.5%	1515