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.

A coding agent that evolves its own source, in public — 200 lines of Rust on day one, every commit since agent-written and tests-gated.

01Result

yologdev/yoyo-evolve ↗

yologdev/yoyo-evolve AI coding statistics: 93.6%

of 330 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
93.6% agent · top contributor 100%1 contributor
individual

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

309
agent commits
21
other considered commits
1
agent contributors
100%
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

309assisted
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
2026-0391.4%163
2026-0496.4%55
2026-0550%4
2026-0690.9%22
2026-07100%29
2026-08100%42
2026-0993.3%15

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic30993.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7d282d67 on GitHubRevert "social.sh: decide the milestone trigger in the shell and state it Claude Code
  • 4bb4d5ba on GitHubsocial.sh: decide the milestone trigger in the shell and state it in the pClaude Code
  • 3c0ebbcc on GitHubharness_logic.sh: tolerate the one-second race in the budget checkClaude 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 window5,923
Merge commits removed−3
CI / dependency bots removed−5,590
Considered330

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 →Rust AI coding statisticsCompare evidence across Rust 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 yologdev/yoyo-evolve

Scan another repository

Try