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.

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

StarTrail-org/LEANN ↗

StarTrail-org/LEANN AI coding statistics: 26.8%

of 112 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
26.8% agent · top contributor 26.7%6 contributors
team

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

30
agent commits
82
other considered commits
6
agent contributors
26.7%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

30assisted
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
2026-0243.5%23
2026-0341.7%12
2026-040%14
2026-0544.4%18
2026-0610.5%19
2026-0728.6%7
2026-080%8
2026-0927.3%11

Peak month: 44.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic2118.8%
Cursor AgentAnysphere98%

Inspect the matches

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

Matched commit samples

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 window121
Merge commits removed−9
CI / dependency bots removed−0
Considered112

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 StarTrail-org/LEANN

Scan another repository