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.

A Proof-oriented Programming Language

01Result

FStarLang/FStar ↗

FStarLang/FStar AI coding statistics: 60.4%

of 1,235 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
60.4% agent · top contributor 50.4%19 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

746
agent commits
489
other considered commits
19
agent contributors
50.4%
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

745assisted
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
2026-0224.2%124
2026-0350.6%176
2026-0425%148
2026-0519.7%71
2026-0616.7%48
2026-0752.7%91
2026-0888.6%411
2026-0994%166

Peak month: 94%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub74360.2%
Claude CodeAnthropic30.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 0b13ae35 on GitHubRestore ShortCircuit.out.expected and refresh the Pulse expected outputsGitHub Copilot
  • 463cf510 on GitHubCustard section 116: ten more findings from a validation reportGitHub Copilot
  • 4c83276a on GitHubCustard section 115: fourteen findings from a validation reportGitHub Copilot
  • c4e60fc5 on GitHuboverload: collect candidates through `include`Claude Code
  • 71e6627f on GitHuboverload: classify erased by its argument, not as compatible with everythiClaude Code
  • 028c7051 on GitHubOverloading: respect the direction of coercionsClaude 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 window1,651
Merge commits removed−413
CI / dependency bots removed−3
Considered1,235

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 →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 FStarLang/FStar

Scan another repository

Try