Pulse
2026-09-18-v3.0
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 unified inference and post-training framework for accelerated video generation.

01Result

hao-ai-lab/FastVideo ↗

hao-ai-lab/FastVideo AI coding statistics: 5.1%

of 475 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.1% agent · top contributor 12.5%17 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

24
agent commits
451
other considered commits
17
agent contributors
12.5%
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

24assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-027.5%53
2026-032.4%42
2026-040%29
2026-054.2%96
2026-062.9%68
2026-077.2%83
2026-083.9%77
2026-0914.8%27

Peak month: 14.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic163.4%
Gemini CLIGoogle81.7%
Cursor AgentAnysphere20.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • aef4e9b3 on GitHub[kernel] VSA kernel: one sm_100a / sm_103a image per listed arch; un-gate Claude Code
  • 3d8ac9d1 on GitHub[feat]: collapse cookbook recipe pages into an accordion layout, add … (#1Claude Code
  • aaef49bf on GitHub[feat]: run FastH3 across two DGX Sparks with Ray sequence parallel (#1803Claude Code
  • 6e25d94e on GitHub[ci]: enable scheduled perf runs to update rolling baseline (#1599)Gemini CLI
  • e8597b74 on GitHub[Bugfix] FP4 FA4 installation fix (#1367)Gemini CLI
  • a55b1cdd on GitHub[feat] Dreamverse 08/14: Add frontend media and E2E coverage (#1331)Gemini CLI
  • a943220c on GitHub[bugfix]: drop dead h3_sequential_load from Spark FastH3 presets (#1831)Cursor Agent
  • 8e39ce38 on GitHub[Feat] Native dit implementation for SD3.5 (#1093)Cursor 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 window477
Merge commits removed−0
CI / dependency bots removed−2
Considered475

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 hao-ai-lab/FastVideo

Scan another repository

Try