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.

The math library of Lean 4

01Result

leanprover-community/mathlib4 ↗

leanprover-community/mathlib4 AI coding statistics: 0.6%

of 6,432 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
0.6% agent · top contributor 22.2%11 contributors
org-wide

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

36
agent commits
6,396
other considered commits
11
agent contributors
22.2%
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

36assisted
0autonomous

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
2026-020.1%819
2026-030.3%1290
2026-040.2%930
2026-050.5%840
2026-060.5%840
2026-070.9%580
2026-081.4%702
2026-091.4%431

Peak month: 1.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic360.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • fd634dd2 on GitHubci: upload the master cache to R2 from the upload_cache job (#43648)Claude Code
  • d0831c7e on GitHubperf(LinearAlgebra/TensorProduct/Tower): remove unused P' instance bindersClaude Code
  • 04c9bc87 on GitHubchore: add missing `to_additive` docstrings in Topology, Geometry and AnalClaude 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 window6,695
Merge commits removed−0
CI / dependency bots removed−263
Considered6,432

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 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 leanprover-community/mathlib4

Scan another repository

Try