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.

MCP server for GitLab: 277 tools for projects, MRs, issues, pipelines, wikis and more via the GitLab REST/GraphQL API

01Result

zereight/gitlab-mcp ↗

zereight/gitlab-mcp AI coding statistics: 26.3%

of 586 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

26.3% agent · top contributor 39.6%19 contributors

org-wide

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

154

agent commits

432

other considered commits

agent contributors

39.6%

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

140assisted

14autonomous

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: 56.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	100	17.1%
Claude Code	Anthropic	39	6.7%
GitHub Copilot	GitHub	15	2.6%

03Evidence

Inspect the matches

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

Matched commit samples

3c55452a on GitHubfix(snippets): honor ref for single-file get_snippet contentCursor Agent
09064f07 on GitHubdocs: update Star History chart (#646)Cursor Agent
233b217c on GitHubfix: harden path handling, redact approval secrets, and shorten OAuth proxCursor Agent
5efc8dca on GitHubrefactor: align snippet file ref handling with repository/files patternClaude Code
5231937b on GitHubfix: extract ref from raw_url to fetch multi-file snippet contentClaude Code
dec2e4bc on GitHubfeat: add snippet CRUD toolsClaude Code
af413242 on GitHubfix: use agent function in fetch to support HTTP/HTTPS protocol switchingGitHub Copilot
f95733f4 on GitHubInitial planGitHub Copilot
f1fe1b4d on GitHubfeat: add get_merge_request_conflicts toolGitHub 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	779
Merge commits removed	−150
CI / dependency bots removed	−43
Considered	586

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 zereight/gitlab-mcp

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	21.3%	47
2026-03	26.3%	57
2026-04	0%	47
2026-05	29.8%	84
2026-06	20.5%	73
2026-07	56.9%	123
2026-08	20.3%	64
2026-09	6.6%	91