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.

High-performance automatic differentiation of LLVM and MLIR.

01Result

EnzymeAD/Enzyme ↗

EnzymeAD/Enzyme AI coding statistics: 27.2%

of 305 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
27.2% agent · top contributor 75.9%8 contributors
team

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

83
agent commits
222
other considered commits
8
agent contributors
75.9%
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

83assisted
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
2026-010%1
2026-020%17
2026-035%40
2026-0422.2%9
2026-0511.1%18
2026-064.3%47
2026-0710.5%76
2026-0876.3%80
2026-0935.3%17

Peak month: 76.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic7424.3%
GitHub CopilotGitHub93%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1e6fed00 on GitHubCompare the zeroing helper against its enzyme_math name (#3220)Claude Code
  • 83b9a361 on GitHubMark jl_world_counter as an inactive integral global (#3208)Claude Code
  • a0104f9d on GitHubRevert "Allow a cached value to be an argument, constant or global (#3201)Claude Code
  • fc6bb335 on GitHubEmit diagnostic instead of segfaulting when CreateReverseDiff/CreateForwarGitHub Copilot
  • 44156f33 on GitHubFix tanh derivative: use 1-tanh(x)^2 instead of 1/cosh(x)^2 for numerical GitHub Copilot
  • e4afe548 on GitHubSpeed up large constant ta (#3002)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 window305
Merge commits removed−0
CI / dependency bots removed−0
Considered305

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 EnzymeAD/Enzyme

Scan another repository

Try