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.

The coding intelligence and skills for Hermes Agent ⚚ just install once. then type 'dag-ulw' to be graph engineering master.

01Result

rlaope/oh-my-hermes ↗

rlaope/oh-my-hermes AI coding statistics: 22%

of 2,171 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
22% agent · top contributor 74.1%3 contributors
individual

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

478
agent commits
1,693
other considered commits
3
agent contributors
74.1%
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

478assisted
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
2026-060.2%616
2026-0720.6%350
2026-0827.1%642
2026-0941%563

Peak month: 41%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic47722%
OpenAI CodexOpenAI10%

03Evidence

Inspect the matches

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

Matched commit samples

  • fd257b16 on GitHubtest(loop): stop the parity card racing the clock on age_secondsClaude Code
  • e85c400e on GitHubfeat(hud): attest the model that answered against the model requestedClaude Code
  • 3b21a11e on GitHubfeat(plugin-audit): classify declared hook semantics before enabling a pluClaude Code
  • f1616112 on GitHubHarden OMH awareness evaluation routing (#278)OpenAI Codex

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 window3,490
Merge commits removed−1,298
CI / dependency bots removed−21
Considered2,171

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 rlaope/oh-my-hermes

Scan another repository

Try