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.

Web UI consciousness monitor for Hermes — the AI agent with persistent memory

01Result

joeynyc/hermes-hudui ↗

joeynyc/hermes-hudui AI coding statistics: 52%

of 150 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

52% agent · top contributor 73.1%3 contributors

individual

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

agent commits

other considered commits

agent contributors

73.1%

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

78assisted

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

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	75	50%
Cursor Agent	Anysphere	3	2%

03Evidence

Inspect the matches

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

Matched commit samples

6e7e610f on GitHubBump ai to 7.x and @ai-sdk/react to 4.x together (replaces #53 + #50) (#57Claude Code
43b4c62f on GitHubFix two high-severity npm audit findings blocking all frontend CI (#56)Claude Code
50368b52 on GitHubPrice Opus 5, legacy Opus, and guard against unpriced modelsClaude Code
3604013b on GitHubResync Costs pricing to August 2026 first-party rates. (#63)Cursor Agent
ad5ca1d3 on GitHubKeep HUD Cron, Sessions, and Projects in sync with Agent 0.20 (#61)Cursor Agent
59011eb3 on GitHubKeep blocking HUD reads off the event loop and isolate chat runs. (#60)Cursor Agent

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 window	157
Merge commits removed	−5
CI / dependency bots removed	−2
Considered	150

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 joeynyc/hermes-hudui

Scan another repository

Try

Month	Agent share	Considered commits
2026-04	56.7%	104
2026-05	0%	23
2026-06	100%	12
2026-07	33.3%	6
2026-08	100%	5