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.

Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins

vastsa/PI-Desktop ↗

vastsa/PI-Desktop AI coding statistics: 14.6%

of 2,239 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
14.6% agent · top contributor 97.2%3 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

326
agent commits
1,913
other considered commits
3
agent contributors
97.2%
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

326assisted
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
2026-0725.8%496
2026-0819.8%682
2026-095.9%1061

Peak month: 25.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic32614.6%

Inspect the matches

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

Matched commit samples

  • 4b6f35e6 on GitHubfeat(tray): share the session row budget across groupsClaude Code
  • ee16b1a2 on GitHubdocs: describe agent extensions in the plugin guide and READMEClaude Code
  • d163669a on GitHubfeat(plugins): agent extensions are a plugin contribution (D388, ADR 0215)Claude Code

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 window2,876
Merge commits removed−632
CI / dependency bots removed−5
Considered2,239

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 vastsa/PI-Desktop

Scan another repository