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 straightforward method for training your LLM, from downloading data to generating text.

01Result

FareedKhan-dev/train-llm-from-scratch ↗

FareedKhan-dev/train-llm-from-scratch AI coding statistics: 57.9%

of 19 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

Too little recent activity to publish. Only 19 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.

57.9% agent · top contributor 36.4%5 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

agent commits

other considered commits

agent contributors

36.4%

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

11assisted

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: 73.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	10	52.6%
GitHub Copilot	GitHub	1	5.3%

03Evidence

Inspect the matches

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

Matched commit samples

d1b71e04 on GitHubdocs: rewrite README as a complete end-to-end tutorialClaude Code
040f478c on GitHubdocs: add hand-drawn diagrams and a reproducible generatorClaude Code
9476be56 on GitHubfix(ddp): make the reward model train on multiple GPUsClaude Code
efb92340 on GitHubHarden checkpoint writes and restore Python 3.9 typing compatibility in leGitHub Copilot

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	30
Merge commits removed	−11
CI / dependency bots removed	−0
Considered	19

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 →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot 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 FareedKhan-dev/train-llm-from-scratch

Scan another repository

Try

Agent-attributed commit share by month
Month	Agent share	Considered commits
2026-05	0%	2
2026-06	73.3%	15
2026-08	0%	2