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.

Workflow SDK: Build durable, reliable, and observable apps and AI Agents in TypeScript

01Result

vercel/workflow ↗

vercel/workflow AI coding statistics: 19.9%

of 1,211 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
19.9% agent · top contributor 44.4%21 contributors
org-wide

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

241
agent commits
970
other considered commits
21
agent contributors
44.4%
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

241assisted
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
2026-0215.3%150
2026-0320.2%168
2026-048.6%152
2026-0516.4%128
2026-0633.2%184
2026-0725.4%181
2026-0818.1%171
2026-0915.6%77

Peak month: 33.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic18815.5%
Cursor AgentAnysphere453.7%
GitHub CopilotGitHub110.9%

03Evidence

Inspect the matches

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

Matched commit samples

  • fb9e2758 on GitHubperf(core): commit pre-claimed inline pairs in their own batch chunk (#409Claude Code
  • 788d4fbc on GitHubperf(core): don't re-publish step messages this invocation already publishClaude Code
  • 6cc851c3 on GitHub[core] Stop sending a slot snapshot on step executor writes (#4096)Claude Code
  • 695a1b76 on GitHubfix(web-shared): describe map-like iterables via entries() (#3806)Cursor Agent
  • 4d5852b9 on GitHubAlt-click focus behavior (#3872)Cursor Agent
  • a06afeef on GitHubPrefix marker context cards with Hook received / Attribute set (#3692)Cursor Agent
  • 14b52ac0 on GitHub[1/4] Replace shared observability component styles with Tailwind (#3295)GitHub Copilot
  • ac41e7d1 on GitHubfix(world): parse timezone-naive analytics timestamps as UTC (#2899)GitHub Copilot
  • aa93cc5e on GitHubMigrate docs to package-backed geistdocs (#2222)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 window1,294
Merge commits removed−0
CI / dependency bots removed−83
Considered1,211

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 →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 vercel/workflow

Scan another repository

Try