Pulse
2026-09-18-v3.0
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.

An idiomatic, lean, fast & safe pure Rust implementation of Git

01Result

GitoxideLabs/gitoxide ↗

GitoxideLabs/gitoxide AI coding statistics: 6.6%

of 1,219 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
6.6% agent · top contributor 29.6%15 contributors
org-wide

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

81
agent commits
1,138
other considered commits
15
agent contributors
29.6%
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

70assisted
11autonomous

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
MonthAgent shareConsidered commits
2026-0220.3%64
2026-038.2%49
2026-041.6%127
2026-0510.9%92
2026-0630.2%86
2026-075.7%227
2026-082.4%493
2026-091.2%81

Peak month: 30.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic685.6%
OpenAI CodexOpenAI60.5%
GitHub CopilotGitHub50.4%
Cursor AgentAnysphere20.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 13d784dc on GitHubfix: keep fixture scripts isolated when they set GIT_CONFIG_COUNT themselvClaude Code
  • 45e6d93f on GitHubfix: peel revspecs to a commit in `gix merge-base`Claude Code
  • 232dd1c6 on GitHubfix: peel annotated tags before navigating a rev-spec, like in Git.Claude Code
  • abe8bbfb on GitHubAdd a test for mergiraf-style merge drivers specificallyOpenAI Codex
  • f15911c7 on GitHubfeat: add `Repository::reopen()` as quick way to reload all configuration OpenAI Codex
  • 33dc7d71 on GitHubfeat: `ein t hours -p` now respects `co-authored-by` message trailers.OpenAI Codex
  • 72134f56 on GitHubfix: ignore assume-unchanged submodule path replaced by symlink in statusGitHub Copilot
  • 32885f36 on GitHubfix: re-encode HTTP(S) paths in URL serialization (#2430)GitHub Copilot
  • 6648e05a on GitHubfix: Add Windows-specific retry logic for persist operations (#2417)GitHub Copilot
  • 67467157 on GitHubfix: resolve the empty pattern in `<rev>^{/}` like Git, instead of skippinCursor Agent
  • 08de71ad on GitHubfix: relative dates roll over month ends like Git, instead of clamping. (#Cursor 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 window1,576
Merge commits removed−333
CI / dependency bots removed−24
Considered1,219

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Rust AI coding statisticsCompare evidence across Rust 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 GitoxideLabs/gitoxide

Scan another repository

Try