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.

On-device AI across mobile, embedded and edge for PyTorch

01Result

pytorch/executorch ↗

pytorch/executorch AI coding statistics: 3.5%

of 3,169 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.5% agent · top contributor 31.8%32 contributors
org-wide

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

110
agent commits
3,059
other considered commits
32
agent contributors
31.8%
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

110assisted
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
2026-024.6%410
2026-034.8%433
2026-046.2%357
2026-052.4%416
2026-065.3%431
2026-073.3%331
2026-080.6%464
2026-090.3%327

Peak month: 6.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic722.3%
GitHub CopilotGitHub401.3%
Cursor AgentAnysphere20.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 99afd2cf on GitHubSkip ATen-mode out-of-range integer clamp/hardtanh death tests (#21933)Claude Code
  • 66967efa on GitHubCortex-M backend: supply a zero bias for grouped convolutions (#21825)Claude Code
  • 43f89fb2 on GitHubQualcomm AI Engine Direct - Add QNN HadamardTransform op support (#21729)Claude Code
  • 372aa3b9 on GitHubQualcomm: bounds-check the delegate (#22237)GitHub Copilot
  • 22778f75 on GitHub[executorch][vulkan] Add payload-bounded constant sharding (#21467)GitHub Copilot
  • dcc04efa on GitHubArm backend: Make pytest collection seeding deterministic (#20621)GitHub Copilot
  • fdb88c3d on GitHubbackends/mlx: runtime MoE expert-sort for decode (issue #20554) (#20685)Cursor Agent
  • c655dc61 on GitHubEnable int4 quantization for parakeet (#17061)Cursor Agent

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 window3,178
Merge commits removed−0
CI / dependency bots removed−9
Considered3,169

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Python AI coding statisticsCompare evidence across Python 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 pytorch/executorch

Scan another repository

Try