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.

Open-source Grok App — desktop workbench (GUI) for the local Grok Build CLI: sessions, projects, media, automations. Tauri 2.

01Result

RongleCat/grok-app ↗

RongleCat/grok-app AI coding statistics: 2.8%

of 1,606 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.8% agent · top contributor 22.2%11 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

45
agent commits
1,561
other considered commits
11
agent contributors
22.2%
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

45assisted
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
2026-070.2%587
2026-083.7%828
2026-096.8%191

Peak month: 6.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere251.6%
DevinCognition110.7%
Claude CodeAnthropic90.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 118ef237 on GitHubfix(sidebar): unify header into one titlebar row (#997)Cursor Agent
  • d5c4acce on GitHubfix(composer): localize top reasoning effort label in model menu (#995)Cursor Agent
  • 64b2d0ae on GitHubperf(chat): patch row offsets in place instead of rebuilding the prefix suCursor Agent
  • dea86673 on GitHubchore(rust): narrow file-level #![allow(dead_code)] to item-level (#1192)Devin
  • 4e514bee on GitHubrefactor(host): extract invoke_handler list into command_registry (#1183)Devin
  • 6f59cc54 on GitHubdocs(remote-bridge): mark package as deprecated reference-only (#1182)Devin
  • 53448a2a on GitHubfix(i18n): two translated strings dropped their {name} placeholder (#751)Claude Code
  • 3ca520e0 on GitHubstyle: cargo fmt so fmt --check is green on main (#725)Claude Code
  • 319a4d86 on GitHubfix(i18n): boot splash and follow-system use the chosen locale (#731)Claude 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 window1,998
Merge commits removed−388
CI / dependency bots removed−4
Considered1,606

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 →Devin commitsBrowse repositories with detected Devin 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 RongleCat/grok-app

Scan another repository

Try