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.

Use Claude Agent SDK from any ACP client

01Result

agentclientprotocol/claude-agent-acp ↗

agentclientprotocol/claude-agent-acp AI coding statistics: 12.3%

of 301 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
12.3% agent · top contributor 24.3%20 contributors
org-wide

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

37
agent commits
264
other considered commits
20
agent contributors
24.3%
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

35assisted
2autonomous

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
2026-024.3%47
2026-035.1%59
2026-0410%40
2026-0512%25
2026-0620.5%39
2026-0723.5%34
2026-086.1%33
2026-0929.2%24

Peak month: 29.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic3712.3%
Cursor AgentAnysphere10.3%
OpenAI CodexOpenAI10.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8823ea6f on GitHubfix: keep the picked option when AskUserQuestion custom text is also supplClaude Code
  • 3d99cafe on GitHubfix: honor host opt-out for allowDangerouslySkipPermissions (#1129)Claude Code
  • 1a4512c7 on GitHubfix: keep multi-select answers when a custom answer is typed (#1031)Claude Code
  • 3d99cafe on GitHubfix: honor host opt-out for allowDangerouslySkipPermissions (#1129)Cursor Agent
  • 6253b161 on GitHubRespect user settings for permission mode and model selection (#340)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 window452
Merge commits removed−0
CI / dependency bots removed−151
Considered301

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 agentclientprotocol/claude-agent-acp

Scan another repository

Try