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.

Unofficial ChatGPT desktop app for Linux (formerly the Codex app), built locally from OpenAI’s official macOS app. Includes Chat, Work, and Codex. Packages for Debian/Ubuntu (.deb), Fedora/openSUSE (.rpm), Arch (pacman), Nix/NixOS, and AppImage, with Wayland and X11 support.

ilysenko/codex-desktop-linux ↗

ilysenko/codex-desktop-linux AI coding statistics: 7%

of 1,547 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
7% agent · top contributor 40.7%19 contributors
org-wide

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

108
agent commits
1,439
other considered commits
19
agent contributors
40.7%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

60assisted
48autonomous

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
2026-020%3
2026-0311.8%34
2026-0414.8%122
2026-052.4%418
2026-0610%230
2026-076%482
2026-089.9%203
2026-097.3%55

Peak month: 14.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic573.7%
OpenAI CodexOpenAI463%
GitHub CopilotGitHub40.3%
Cursor AgentAnysphere10.1%

Inspect the matches

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

Matched commit samples

  • f06f077d on GitHubfix(plugins): re-target the Chrome skill guard instead of dropping itClaude Code
  • e43b64e3 on GitHubtest(plugins): drop the removed Chrome skill guard assertionsClaude Code
  • 2393e65d on GitHubchore(plugins): drop Chrome plugin patches upstream now shipsClaude Code
  • baf2f034 on GitHubfix(nix): refresh official Linux package pins for 26.908.70816 (#1482)OpenAI Codex
  • 135ec960 on GitHubfix(nix): refresh official Linux package pins for 26.901.51231 (#1439)OpenAI Codex
  • 9845401c on GitHubfix(nix): refresh official Linux package pins for 26.901.41600 (#1431)OpenAI Codex
  • 31d6b209 on GitHubAdd Rust/cargo installation to install-deps.sh and improve cargo error mesGitHub Copilot
  • 4fb9501c on GitHubAdd scripts/install-deps.sh and fix Fedora/dnf5 package names in hints andGitHub Copilot
  • 21829ed9 on GitHubRename BuildArtifacts.deb_path to package_path; add --app-id for Wayland tGitHub Copilot
  • 901ca642 on GitHubfix(launcher): fall back to full webview verify before startup failureCursor Agent

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 window2,122
Merge commits removed−575
CI / dependency bots removed−0
Considered1,547

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 ilysenko/codex-desktop-linux

Scan another repository