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.

Deploy headless browsers in Docker. Run on our cloud or bring your own. Free for non-commercial uses.

01Result

browserless/browserless ↗

browserless/browserless AI coding statistics: 65.9%

of 135 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
65.9% agent · top contributor 38.2%11 contributors
org-wide

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

89
agent commits
46
other considered commits
11
agent contributors
38.2%
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

75assisted
14autonomous

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
2026-020%11
2026-0352.6%19
2026-0472.2%18
2026-0577.3%22
2026-0692.1%38
2026-0777.8%9
2026-0842.9%7
2026-0936.4%11

Peak month: 92.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic8160%
DevinCognition107.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • e81e99c4 on GitHubfix: block IPv4 prefixes without a trailing dot (#5577)Claude Code
  • c1f3509a on GitHubfix: block URLs with Network.setBlockedURLs, not Fetch (PLT-1596) (#5574)Claude Code
  • ba7b5046 on GitHubfix: serve the images the API docs page references (#5568)Claude Code
  • d2388de9 on GitHubfix: retry page.content() on navigation teardown in content API (SCRAP-604Devin
  • 5c128435 on GitHubfeat: support per-route error codes in Swagger build pipeline (#5480)Devin
  • a1212578 on GitHubfix: reset billing clock at job execution start, not queue time (SCRAP-410Devin

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 window514
Merge commits removed−154
CI / dependency bots removed−225
Considered135

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 →Devin commitsBrowse repositories with detected Devin 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 browserless/browserless

Scan another repository

Try