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 Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

01Result

llvm/torch-mlir ↗

llvm/torch-mlir AI coding statistics: 7.9%

of 165 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
7.9% agent · top contributor 46.2%5 contributors
team

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

13
agent commits
152
other considered commits
5
agent contributors
46.2%
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

13assisted
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%15
2026-0311.1%18
2026-0428.6%21
2026-055.9%17
2026-060%16
2026-070%26
2026-085.1%39
2026-0915.4%13

Peak month: 28.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic137.9%

03Evidence

Inspect the matches

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

Matched commit samples

  • bd16df29 on GitHub[TorchConversion] Reject non-shaped function signatures in backend-co… (#4Claude Code
  • 1deff3a4 on GitHub[Torch] Fix aten.select.int folder for negative dim and index (#4738)Claude Code
  • 2226a1dd on GitHub[fx_importer] Support negated symbolic dims (#4723)Claude 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 window167
Merge commits removed−0
CI / dependency bots removed−2
Considered165

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 →C++ AI coding statisticsCompare evidence across C++ 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 llvm/torch-mlir

Scan another repository

Try