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.

Collaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, etc. Desktop app, self-hosted server, or Docker.

01Result

spacering-net/codeg ↗

spacering-net/codeg AI coding statistics: 9.6%

of 2,485 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

9.6% agent · top contributor 97.9%5 contributors

individual

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

238

agent commits

2,247

other considered commits

agent contributors

97.9%

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

238assisted

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: 34.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	236	9.5%
Cursor Agent	Anysphere	2	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

39506eb5 on GitHubfeat(acp): adapt claude-agent-acp to 0.77.0Claude Code
594024db on GitHubfix(acp): isolate per-launch agent temp dirs, relocate the binary cache, aClaude Code
b84e76c6 on GitHubfix(deepseek): read generation-addressed session logs and localise the ACPClaude Code
7ae6b2d0 on GitHubfix(cursor): restore ACP agent retry policyCursor Agent
c2d72d31 on GitHubfix(cursor-acp): enable parameterized model pickerCursor 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	2,806
Merge commits removed	−321
CI / dependency bots removed	−0
Considered	2,485

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 →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 spacering-net/codeg

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	0%	394
2026-04	34.8%	405
2026-05	8.2%	305
2026-06	7.6%	397
2026-07	0%	302
2026-08	3.8%	371
2026-09	9%	311