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.

Persistent memory for Claude Code, Codex and 6 other AI agents, stored as plain markdown in your Obsidian vault. New: Crew, one shared logbook so Claude Code, Codex, Cursor and Grok Bot know what each other did. 48 commands: semantic search, self-rewriting notes, key-less research, scheduled agents.

01Result

eugeniughelbur/obsidian-second-brain ↗

eugeniughelbur/obsidian-second-brain AI coding statistics: 84.9%

of 443 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

84.9% agent · top contributor 89.1%22 contributors

individual

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

376

agent commits

other considered commits

agent contributors

89.1%

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

376assisted

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: 91.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	373	84.2%
Cursor Agent	Anysphere	3	0.7%

03Evidence

Inspect the matches

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

Matched commit samples

e29ffc5d on GitHubStop counting AppleDouble files as notes, and stop matching links by filenClaude Code
2ef82f80 on GitHubFix SessionStart hook silently skipping the vault manual (env-only OBSIDIAClaude Code
d1e88950 on GitHubResolve the config in one place instead of sevenClaude Code
c93ce3f2 on GitHubSEO: name Grok Bot in title, description, and topics (#225)Cursor Agent
df7080db on GitHubAdd grok-bot adapterCursor Agent
ecc5609c on GitHubFix validate-ai-first for VS Code create_file writes (#202)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	483
Merge commits removed	−33
CI / dependency bots removed	−7
Considered	443

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 eugeniughelbur/obsidian-second-brain

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	90%	10
2026-04	85.9%	64
2026-05	83.3%	60
2026-06	91.7%	60
2026-07	90.1%	162
2026-08	81.1%	37
2026-09	62%	50