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.

GitHub Agentic Workflows

01Result

github/gh-aw ↗

github/gh-aw AI coding statistics: 25.6%

of 9,696 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
25.6% agent · top contributor 81.1%21 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

2,482
agent commits
7,214
other considered commits
21
agent contributors
81.1%
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

2225assisted
257autonomous

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
2026-0225.3%1556
2026-0332.3%1022
2026-0421.1%1235
2026-0519%1504
2026-0624.3%1385
2026-0728.8%1173
2026-0829.4%1516
2026-0930.2%305

Peak month: 32.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub235924.3%
Claude CodeAnthropic2252.3%
OpenAI CodexOpenAI150.2%
Cursor AgentAnysphere10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 0bb3e7df on GitHubAdd fixture and test coverage for body-footer safe output config (#61196)GitHub Copilot
  • 6eb5a958 on GitHubBump gh-aw-firewall (AWF) to v0.28.17 (#60945)GitHub Copilot
  • de4c8431 on GitHubMove release.md back to docker sandbox runtime (#60931)GitHub Copilot
  • 37f59040 on GitHubAdd daily grader audit workflow (#56359)Claude Code
  • 9807018f on GitHubInclude grader evaluator scripts in workflow packages (#56268)Claude Code
  • fcf78d2c on GitHubAlways configure OTLP from enterprise default variables and secrets (#5635Claude Code
  • 4e5e198d on GitHubDisplay secrecy and integrity fields in safe output step summary renderer OpenAI Codex
  • 567fee9f on GitHubFix safe-inputs `script:` runner always returning `{"stdout":"","stderr":"OpenAI Codex
  • 0d40e9cb on GitHubBeginnings of multi repo PR support (#18599)OpenAI Codex
  • f4b06916 on GitHubMigrate all generateFooter callers to generateFooterWithMessages (#15566)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 window11,723
Merge commits removed−80
CI / dependency bots removed−1,947
Considered9,696

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 →Go AI coding statisticsCompare evidence across Go 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 github/gh-aw

Scan another repository

Try