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 open-source background agents coding system

01Result

ColeMurray/background-agents ↗

ColeMurray/background-agents AI coding statistics: 1.8%

of 1,242 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.8% agent · top contributor 22.7%13 contributors
org-wide

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

22
agent commits
1,220
other considered commits
13
agent contributors
22.7%
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

17assisted
5autonomous

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
2026-010%2
2026-020.5%195
2026-030%90
2026-041.2%84
2026-058.5%71
2026-067.3%96
2026-071.2%260
2026-081%311
2026-090.8%133

Peak month: 8.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic181.4%
GitHub CopilotGitHub30.2%
OpenAI CodexOpenAI10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7f23cf44 on GitHubfix(web): stop dispatching the model preferences lock key as a URL (#1876)Claude Code
  • 74de2741 on GitHubfix(slack): split long completions across sections instead of truncating aClaude Code
  • 93677d72 on GitHubfix(slack-bot): give each repo quick-pick button a unique action_id (#868)Claude Code
  • 7dd7fbbe on GitHubPrevent stale media and list state across UI updates (#1224)GitHub Copilot
  • 6e7b0297 on GitHubImprove settings rendering and session accessibility (#1154)GitHub Copilot
  • f6dcec67 on GitHubImprove web accessibility and client resilience (#1134)GitHub Copilot
  • 092888ae on GitHubfix(types): validate unsafe web boundary casts (#1563)OpenAI Codex

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 window1,415
Merge commits removed−0
CI / dependency bots removed−173
Considered1,242

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 ColeMurray/background-agents

Scan another repository

Try