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.

Simulate Before Reality.

01Result

MatrAIx-ai/MatrAIx-Persona-8B ↗

MatrAIx-ai/MatrAIx-Persona-8B AI coding statistics: 77.1%

of 144 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
77.1% agent · top contributor 83.8%5 contributors
individual

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

111
agent commits
33
other considered commits
5
agent contributors
83.8%
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

111assisted
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
2026-0881.2%133
2026-0927.3%11

Peak month: 81.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere10572.9%
Claude CodeAnthropic64.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 4cfb189b on GitHubfix(playground): close batch workspace reset and job-page empty statesCursor Agent
  • def4337e on GitHubfix(playground): read task strategy portions from harbor repo_rootCursor Agent
  • 50b70156 on GitHubKeep Playground batch cells attached and add a Run Status job view.Cursor Agent
  • ef2d6ac7 on GitHubstyle: fix ruff F401/E741 in microdata_to_jsonlClaude Code
  • 18eb9f63 on GitHubfix(philippines): correct WVS/DHS variable mappings against the real releaClaude Code
  • 9d2d3421 on GitHubfix(crosswalk): match integer codes that pandas widened to floatClaude 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 window210
Merge commits removed−66
CI / dependency bots removed−0
Considered144

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 MatrAIx-ai/MatrAIx-Persona-8B

Scan another repository

Try