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.

Media over QUIC: Real-time latency at massive scale

01Result

moq-dev/moq ↗

moq-dev/moq AI coding statistics: 76.4%

of 2,003 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
76.4% agent · top contributor 94.4%32 contributors
individual

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

1,531
agent commits
472
other considered commits
32
agent contributors
94.4%
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

1525assisted
6autonomous

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
2026-0242.2%90
2026-0382.8%116
2026-0488.7%151
2026-0591.7%156
2026-0694.5%307
2026-0773.1%387
2026-0872.5%415
2026-0964.6%381

Peak month: 94.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic149374.5%
OpenAI CodexOpenAI512.5%
Cursor AgentAnysphere70.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • b65e28a2 on GitHubdocs(cluster): revise the cluster draft to -01 and plan its implementationClaude Code
  • 877a561d on GitHubchore(quest): joining FETCH for pre-draft-20 peers (#3701)Claude Code
  • 324cb3a1 on GitHubfeat(relay): admit every session through a moq-auth lease (#3688)Claude Code
  • d95c706a on GitHubdocs(quest): scope parallel M2 work and pre-release API groundworkOpenAI Codex
  • f7f1ad3f on GitHubfix(moq-video): stop a dead codec session and a failed flush from spinningOpenAI Codex
  • 3dff6dcf on GitHubci: cut the Release RS job from ~55 minutes (#3547)OpenAI Codex
  • d88c2ee9 on GitHubfeat(obs): add connection stats and encoding controls to the MoQ dock (#34Cursor Agent
  • 8b1eeec3 on GitHubtest(ts): reach the sparse EIT schedule and pending-version cases (#2920)Cursor Agent
  • 7b73c433 on GitHubtest(ts): synthesise an EIT so the import path's SI routing is testable (#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 window2,281
Merge commits removed−116
CI / dependency bots removed−162
Considered2,003

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 moq-dev/moq

Scan another repository

Try