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.

DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks

01Result

MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark ↗

MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark AI coding statistics: 14.9%

of 316 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
14.9% agent · top contributor 91.5%3 contributors
individual

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

47
agent commits
269
other considered commits
3
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

47assisted
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%22
2026-070%39
2026-0815.3%163
2026-0923.9%92

Peak month: 23.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere3611.4%
Claude CodeAnthropic113.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • e8c13d0b on GitHubAdd gated runtime ablation on official Vision-Exp weights.Cursor Agent
  • 141760c1 on GitHubAdd optional three-node TP=3 launcher without changing the default 2-node Cursor Agent
  • 22bdac78 on GitHubfix(build): do not pass a digest-pinned image to docker build -t (issue #1Cursor Agent
  • bbf6acfd on GitHubfix(vision-exp): the drafter's routing-kind fallback is expected, not a waClaude Code
  • 5b0bf8cf on GitHubharden(vision-exp): no silent degradation in the per-forward routing kindClaude Code
  • 2fa35497 on GitHubperf(vision-exp): classify routing kind once per forward, not once per MoEClaude 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 window469
Merge commits removed−153
CI / dependency bots removed−0
Considered316

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 →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 MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark

Scan another repository

Try