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 Python framework for self-hosted LLM tool-calling and multi-step agentic workflows

01Result

antoinezambelli/forge ↗

antoinezambelli/forge AI coding statistics: 69%

of 87 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

Too little recent activity to publish. Only 87 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.

69% agent · top contributor 93.3%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

93.3%

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

60assisted

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	60	69%

03Evidence

Inspect the matches

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

Matched commit samples

77e87f59 on GitHubrelease: v0.8.2 — expanded model evals and dashboard refresh (#133)Claude Code
a02944a7 on GitHubfix(llamafile): harden the malformed-500 rescue gate and drop skeleton calClaude Code
f7749df8 on GitHubfix(llamafile): rescue tool calls from malformed tool-call 500s instead ofClaude 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 window	87
Merge commits removed	−0
CI / dependency bots removed	−0
Considered	87

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 →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 antoinezambelli/forge

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	100%	25
2026-04	100%	11
2026-05	56.3%	16
2026-06	83.3%	12
2026-07	71.4%	7
2026-08	0%	16