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.

An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.

01Result

vellum-ai/vellum-assistant ↗

vellum-ai/vellum-assistant AI coding statistics: 76.3%

of 28,662 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
76.3% agent · top contributor 31.5%45 contributors
org-wide

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

21,860
agent commits
6,802
other considered commits
45
agent contributors
31.5%
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

19269assisted
2591autonomous

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
2026-0294.4%8048
2026-0383%9400
2026-0431.5%3779
2026-0549.8%1873
2026-0676.1%2242
2026-0778.6%1638
2026-0879.1%1172
2026-0981.4%510

Peak month: 94.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1886765.8%
DevinCognition286810%
Cursor AgentAnysphere2040.7%
OpenAI CodexOpenAI10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 4cba45df on GitHubfix(computer-use): give macOS app scripting one story across prompt, skillClaude Code
  • 03e77eb7 on GitHubfix(computer-use): stop reporting an unchanged accessibility tree as a faiClaude Code
  • 1d2df4e9 on GitHubfeat(live-voice): start desktop voice turns with computer use active (#427Claude Code
  • 9ff042ee on GitHub[ATL-1180] fix(providers): retry with flattened content and classify chat-Devin
  • 14dda4e3 on GitHubfix(web): disable local-only providers in pickers instead of hiding them (Devin
  • a259ed06 on GitHub[ATL-1204] fix(assistant): refresh providers when a connection-backed credDevin
  • e48da4d6 on GitHubfix(web): make the Connect Claude Code card dismissable (#42747)Cursor Agent
  • 94809fdc on GitHubfeat(monitoring): log assistant-container mount diffs in the resource moniCursor Agent
  • 6ed4976d on GitHubfix(telegram): surface private-chat-only limitation during setup (#42749)Cursor Agent
  • 34427442 on GitHubFix Anthropic normalization fidelity in inspector (#19370)OpenAI Codex

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 window30,244
Merge commits removed−0
CI / dependency bots removed−1,582
Considered28,662

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Devin commitsBrowse repositories with detected Devin 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 vellum-ai/vellum-assistant

Scan another repository

Try