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.

Control panel for VLLM, Sglang, llama.cpp, exllamav3

01Result

sybil-solutions/local-studio ↗

sybil-solutions/local-studio AI coding statistics: 25.5%

of 1,736 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
25.5% agent · top contributor 98.2%2 contributors
individual

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

443
agent commits
1,293
other considered commits
2
agent contributors
98.2%
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

443assisted
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
2026-025.3%94
2026-034.5%22
2026-043.6%112
2026-051.8%450
2026-0643.8%377
2026-0742.5%593
2026-085.9%85
2026-09100%3

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic44225.5%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • d1abdef9 on GitHubfix(google): working Gmail/Calendar sign-in on desktop and server installsClaude Code
  • 9bf7b342 on GitHubfeat(app): cursor-wave 4 — sidebar redesign, composer dedupe, title generaClaude Code
  • 0b916f57 on GitHubfeat(controller): context soft-limit guard and scaled local compaction (#4Claude Code
  • a00d8a8c on GitHubfix: respect explicit null parser overrides in vLLM launch flagsGitHub Copilot

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 window1,784
Merge commits removed−48
CI / dependency bots removed−0
Considered1,736

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 →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 sybil-solutions/local-studio

Scan another repository

Try