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.

Fastest way to build, submit, and update iOS and Android apps

01Result

expo/eas-cli ↗

expo/eas-cli AI coding statistics: 7.2%

of 753 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
7.2% agent · top contributor 33.3%13 contributors
org-wide

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

54
agent commits
699
other considered commits
13
agent contributors
33.3%
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

54assisted
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
2026-025.4%56
2026-0312.9%70
2026-0410%60
2026-052.9%137
2026-069.4%64
2026-076.6%151
2026-085.3%132
2026-0910.8%83

Peak month: 12.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic445.8%
OpenAI CodexOpenAI91.2%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • d1938606 on GitHub[eas-cli] Add observe:event command to fetch a single event by ID (#4252)Claude Code
  • 08b43466 on GitHub[eas-cli] Add observe:errors command (#4339)Claude Code
  • 99cbcae2 on GitHub[eas-cli] Align Observe code with new server schema (#4338)Claude Code
  • 1da0be85 on GitHub[build-tools] Use `bun x` to start Argent remote sessions (#4366)OpenAI Codex
  • 4d6d9b1f on GitHub[build-tools] Allow configuring Android emulator display (#4349)OpenAI Codex
  • 1cb06a6c on GitHub[build-tools] Install FFmpeg before Android device hub (#4332)OpenAI Codex
  • d660e360 on GitHub[worker] Preserve `UserFacingError` instead of `UNKNOWN_ERROR` (#3445)GitHub 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 window756
Merge commits removed−0
CI / dependency bots removed−3
Considered753

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 expo/eas-cli

Scan another repository

Try