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.

Mirror of https://git.lede-project.org/?p=source.git Please send your PRs against this tree. They will be merged via staging trees and appear in this tree once the staging trees get merged back into source.git

lede-project/source ↗

lede-project/source AI coding statistics: 1%

of 3,421 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1% agent · top contributor 79.4%7 contributors
team

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

34
agent commits
3,387
other considered commits
7
agent contributors
79.4%
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

34assisted
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%357
2026-031.4%488
2026-041.4%506
2026-053.3%483
2026-060.4%455
2026-070%449
2026-080%372
2026-090.6%311

Peak month: 3.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic331%
Cursor AgentAnysphere10%

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 window3,421
Merge commits removed−0
CI / dependency bots removed−0
Considered3,421

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 lede-project/source

Scan another repository