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.

Production-grade C++ edge AI engine for video analytics and on-device VLM across Sophon, Rockchip RKNN, and x86, with visual orchestration, real-time OSD, events, and reproducible benchmarks.

cosmo-wander-ai/cosmo-edge ↗

cosmo-wander-ai/cosmo-edge AI coding statistics: 0.6%

of 539 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
0.6% agent · top contributor 66.7%2 contributors
individual

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

3
agent commits
536
other considered commits
2
agent contributors
66.7%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

3assisted
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
2026-060%56
2026-071%199
2026-080.5%210
2026-090%74

Peak month: 1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic30.6%

Inspect the matches

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

Matched commit samples

  • a41fd1c0 on GitHubdocs(bench): qualify VLM protocol asymmetry and defer re-measurementClaude Code
  • bb69e522 on GitHubfix(alarm): reset TaskAlarm suppression state on task restartClaude Code
  • 8d4fb8cf on GitHubfix(alarm): reset AreaAlarm tracking state on task restartClaude Code

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 window698
Merge commits removed−156
CI / dependency bots removed−3
Considered539

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 cosmo-wander-ai/cosmo-edge

Scan another repository