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.

Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.

01Result

sqliteai/warp ↗

sqliteai/warp AI coding statistics: 82.2%

of 287 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

82.2% agent · top contributor 91.5%4 contributors

individual

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

236

agent commits

other considered commits

agent contributors

91.5%

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

236assisted

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: 97.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	236	82.2%

03Evidence

Inspect the matches

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

Matched commit samples

ceea3fac on GitHubmodel: fewer places a Qwen step lets the pool fall asleepClaude Code
2c8b51b0 on GitHubfetch_weights.sh: a shard that finished on the last attempt had finishedClaude Code
b4a53346 on GitHubds41_preflight.py: every shape the engine will demand, before a byte is wrClaude 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	323
Merge commits removed	−36
CI / dependency bots removed	−0
Considered	287

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 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 sqliteai/warp

Scan another repository

Try

Month	Agent share	Considered commits
2026-07	97.6%	123
2026-08	74%	123
2026-09	61%	41