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.

Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.

01Result

callstack/agent-device ↗

callstack/agent-device AI coding statistics: 10.2%

of 1,951 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
10.2% agent · top contributor 78.9%7 contributors
team

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

199
agent commits
1,752
other considered commits
7
agent contributors
78.9%
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

163assisted
36autonomous

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
2026-024.2%165
2026-0321.9%160
2026-042.6%156
2026-050%117
2026-064.9%266
2026-0718.5%367
2026-0811.9%453
2026-096.7%267

Peak month: 21.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1547.9%
DevinCognition361.8%
Cursor AgentAnysphere90.5%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7f55c561 on GitHubrefactor(tests): share the router-open fixtures between its suites (#2585)Claude Code
  • 1e50f967 on GitHubfix(daemon): take a foreign device claim the device's own reboot invalidatClaude Code
  • 342e98cf on GitHubrefactor(daemon): separate open-target policy from platform mechanics (#24Claude Code
  • 885c1486 on GitHubtest(ci): single-retry policy for enumerated contention-flaky files (timeoDevin
  • 6544e9a0 on GitHubobs: repo-health snapshot command aggregating existing analyzers into one Devin
  • e0b8463e on GitHubfeat(scripts): blast-radius query — dependents, owning gates, live-coveragDevin
  • a5f1f362 on GitHubfeat(browserstack): add --provider-appium-version to pin the hosted AppiumCursor Agent
  • 8dd6b852 on GitHubfix(browserstack): send W3C-only capabilities so bstack:options labels areCursor Agent
  • b6fdbb1d on GitHubfix(android): install the snapshot and IME helpers as plain, non-test-onlyCursor Agent
  • 2876c983 on GitHubfeat: publish on ClawHub (#110)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 window1,951
Merge commits removed−0
CI / dependency bots removed−0
Considered1,951

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 →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 callstack/agent-device

Scan another repository

Try