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.

Blazing-fast, Neuro-symbolic Data-Wrangling toolkit

01Result

dathere/qsv ↗

dathere/qsv AI coding statistics: 50.9%

of 2,175 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

50.9% agent · top contributor 98.9%4 contributors

individual

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

1,106

agent commits

1,069

other considered commits

agent contributors

98.9%

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

1099assisted

7autonomous

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

Agent-attributed commit share by month
Month	Agent share	Considered commits
2026-01	100%	9
2026-02	47.4%	548
2026-03	39.3%	290
2026-04	44.4%	223
2026-05	50.6%	241
2026-06	57.8%	282
2026-07	52.6%	253
2026-08	60.2%	201
2026-09	66.4%	128

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	1075	49.4%
GitHub Copilot	GitHub	51	2.3%

03Evidence

Inspect the matches

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

Matched commit samples

e931ba32 on GitHubdeps: pin reqwest's charset/system-proxy features, add fetch/fetchpost --dClaude Code
6d33fb41 on GitHubdeps: bump polars to d84c1d4 (2.0 prep), and fix the join-order fallout (#Claude Code
a6e0e3d4 on GitHubdocs: update test counts (5,863 total)Claude Code
b5d4479c on GitHubfeat(excel): expose has_1904_epoch in workbook metadata (#3905)GitHub Copilot
688aba8d on GitHubfeat(describegpt): date/datetime content-type tokens with LLM-inferred chrGitHub Copilot
08127c1d on GitHubfeat(sample): add VarOpt + mergeable-reservoir sampling with sketch I/O (#GitHub 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	2,594
Merge commits removed	−144
CI / dependency bots removed	−275
Considered	2,175

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 →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 dathere/qsv

Scan another repository

Try