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.

The coding agent that answers to you, your model, your machine, your rules.

01Result

Twigpine/zero ↗

Twigpine/zero AI coding statistics: 10.9%

of 718 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
10.9% agent · top contributor 34.6%10 contributors
org-wide

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

78
agent commits
640
other considered commits
10
agent contributors
34.6%
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

78assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0533.3%3
2026-065.8%379
2026-0715.5%238
2026-0829.1%55
2026-094.7%43

Peak month: 33.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic7310.2%
Cursor AgentAnysphere71%
GitHub CopilotGitHub40.6%
DevinCognition10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • b04fe96e on GitHubfix(config): lock config read-modify-write across processes (#960)Claude Code
  • 79fa1422 on GitHubfix(providers): register Atomic Chat as local OpenAI-compatible runtime (#Claude Code
  • 27b319ca on GitHubtest(execution): fail loudly when ps cannot answer instead of skipping (#9Claude Code
  • 79fa1422 on GitHubfix(providers): register Atomic Chat as local OpenAI-compatible runtime (#Cursor Agent
  • 9c292092 on GitHubfix(daemon): clean up child after startup timeout (#774)Cursor Agent
  • 936aa4e7 on GitHubfix(lsp): dispatch notifications off read loop (#759)Cursor Agent
  • 1057d745 on GitHubdocs(readme,cli): document /new & zero upgrade, add Discord link, and syncGitHub Copilot
  • 062328b6 on GitHubfix: warn about untracked scratch files left behind after a run (#571)GitHub Copilot
  • 008bc9b3 on GitHubfix: address bugs found in a multi-agent codebase audit (#481)GitHub Copilot
  • 88fb7b61 on GitHubfix(sandbox): add platform-specific write lock around grant state file (#7Devin

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 window728
Merge commits removed−0
CI / dependency bots removed−10
Considered718

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 →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 Twigpine/zero

Scan another repository

Try