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.

For EHRs, payer portals, and any app your team clicks through. A person or an agent shows the task; OpenAdapt turns it into a local program that repeats the steps with no model calls, checks each save, and stops when something doesn't match.

01Result

OpenAdaptAI/OpenAdapt ↗

OpenAdaptAI/OpenAdapt AI coding statistics: 30.5%

of 855 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
30.5% agent · top contributor 82%4 contributors
individual

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

261
agent commits
594
other considered commits
4
agent contributors
82%
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

260assisted
1autonomous

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
2026-0278.6%14
2026-0351.5%33
2026-0655.6%9
2026-0728%443
2026-0833%297
2026-0910.2%59

Peak month: 78.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic26130.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • c9cf7b6b on GitHubci: don't let a push cancel a release-qualification dispatch (#466)Claude Code
  • 0346b430 on GitHubfix(reward): derive what the receipt asserts instead of believing the bundClaude Code
  • d8c970a8 on GitHubfix(reward)!: refuse the certificate claims this version cannot check (#40Claude Code

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 window993
Merge commits removed−35
CI / dependency bots removed−103
Considered855

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 →Python AI coding statisticsCompare evidence across Python 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 OpenAdaptAI/OpenAdapt

Scan another repository

Try