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.

AI that sees your screen, listens to your conversations and tells you what to do

BasedHardware/omi ↗

BasedHardware/omi AI coding statistics: 41.9%

of 19,768 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
41.9% agent · top contributor 31.6%73 contributors
org-wide

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

8,288
agent commits
11,480
other considered commits
73
agent contributors
31.6%
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

7873assisted
415autonomous

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
2026-01100%2
2026-0290.5%1084
2026-0356.5%2513
2026-0476.3%2222
2026-0544.4%1010
2026-0638%3880
2026-0720.4%5440
2026-0829.4%2654
2026-0938.8%963

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic626531.7%
Cursor AgentAnysphere16688.4%
Gemini CLIGoogle3801.9%
DevinCognition140.1%
GitHub CopilotGitHub60%
OpenAI CodexOpenAI10%

Inspect the matches

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

Matched commit samples

  • 252d8b4c on GitHubfix(notion): emit usable page, database and entry ids from the listing tooClaude Code
  • 19afe222 on GitHubfix(pre-push): stop the hook's GIT_DIR from reaching the gate's children (Claude Code
  • 3836a5f8 on GitHubfix(desktop): measure an on-device pause against the room's own noise (#13Claude Code
  • 2dd976b8 on GitHubfix: reject zero-byte data export downloads (#4678) (#13856)Cursor Agent
  • bfd9789c on GitHubfix: wire device timezone into AI chat for relative times (Fixes #4643) (#Cursor Agent
  • cdff25b5 on GitHubfix(desktop): preserve Claude Code sessions across re-auth (#13859)Cursor Agent
  • b8939f9c on GitHubUpdate desktop/Desktop/Sources/VADGateService.swiftGemini CLI
  • 79a1d88d on GitHubUpdate app/lib/providers/message_provider.dartGemini CLI
  • a3435b16 on GitHubUpdate CLAUDE.mdGemini CLI
  • 4fd15ad2 on GitHubfix(github-app): coerce inputs and propagate API errors (#13911) (#14080)Devin
  • c8558484 on GitHubfix(windows): append uid to external-app setup URLs without corrupting queDevin
  • 64db30c7 on GitHubfix(web): pin prettier and tighten pre-commit toolchain resolutionDevin
  • d6907c36 on GitHubfix(app): re-read device storage after clearing recordings (#12864)GitHub Copilot
  • 1f250097 on GitHubfix(backend): drop id-less records from the popular-apps listing too (#128GitHub Copilot
  • ab069b7d on GitHubfix(backend): drop marketplace records with no id before the shared cataloGitHub Copilot
  • 758cd3f1 on GitHubfix: keep bounded tool results successfulOpenAI Codex

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 window26,194
Merge commits removed−4,809
CI / dependency bots removed−1,617
Considered19,768

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 BasedHardware/omi

Scan another repository