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.

F# to JavaScript, TypeScript, Python, Rust, Erlang and Dart Compiler

01Result

fable-compiler/Fable ↗

fable-compiler/Fable AI coding statistics: 34.7%

of 418 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
34.7% agent · top contributor 73.1%7 contributors
team

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

145
agent commits
273
other considered commits
7
agent contributors
73.1%
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

115assisted
30autonomous

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
2026-0216.7%30
2026-0323.5%81
2026-0467.3%52
2026-0542.1%19
2026-0644.8%58
2026-0742.3%111
2026-0821.1%19
2026-092.1%48

Peak month: 67.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic13532.3%
GitHub CopilotGitHub215%

03Evidence

Inspect the matches

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

Matched commit samples

  • b3ec8b67 on GitHubfix(python): derive DateTime "O" format from the value, not the host timezClaude Code
  • bb3c86d7 on GitHubfix(beam): parse ISO-8601 numeric zone offsets and compare dates by instanClaude Code
  • 366919a7 on GitHubfix(beam): compile [<StringEnum>] cases to atoms instead of binaries (#486Claude Code
  • 9cf5bead on GitHubci: cache NuGet packages and npm downloads (#4525)GitHub Copilot
  • 09003de8 on GitHubfix(js/ts): reject JS-permissive date strings that .NET TryParse rejects (GitHub Copilot
  • 8e0fe91e on GitHubci: Add CI concurrency settings to cancel superseded PR runs (#4546)GitHub Copilot

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 window569
Merge commits removed−0
CI / dependency bots removed−151
Considered418

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 fable-compiler/Fable

Scan another repository

Try