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.

The Best Native Agents Workspace. Fully Rust & GPUI based. Mobile apps. 20+ agents. Native Ghostty.

01Result

maddada/Ghostex ↗

maddada/Ghostex AI coding statistics: 3.5%

of 3,313 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.5% agent · top contributor 59%8 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

117
agent commits
3,196
other considered commits
8
agent contributors
59%
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

117assisted
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
2026-040%64
2026-050%698
2026-061.6%567
2026-070.6%509
2026-0811.8%780
2026-091.9%695

Peak month: 11.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere692.1%
Claude CodeAnthropic481.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 15a10f5a on GitHubdocs: document the ghostex-bin AUR package on Linux.Cursor Agent
  • 2ef3829b on GitHubfeat(session-chat): show Codex Plan mode on the options pillCursor Agent
  • 28ca5f8c on GitHubstyle(session-chat): restyle reasoning wrap, context details, and the scroCursor Agent
  • 83182729 on GitHubfeat(chat): show slash commands sent from chat, with their output, after aClaude Code
  • 47377b87 on GitHubfix(desktop): render gpui-component's dialog layer so alert dialogs appearClaude Code
  • 57548fc4 on GitHubfix(board): start-work puts the worker in the named project, not the newesClaude 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 window3,419
Merge commits removed−60
CI / dependency bots removed−46
Considered3,313

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 →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 maddada/Ghostex

Scan another repository

Try