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.

Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.

01Result

Vexa-ai/vexa ↗

Vexa-ai/vexa AI coding statistics: 26.9%

of 1,777 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
26.9% agent · top contributor 61.1%8 contributors
team

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

478
agent commits
1,299
other considered commits
8
agent contributors
61.1%
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

478assisted
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
2026-0232.7%220
2026-03100%34
2026-0470.6%360
2026-0560%85
2026-0616.8%387
2026-070.2%593
2026-080%78
2026-095%20

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic46826.3%
Cursor AgentAnysphere90.5%
OpenAI CodexOpenAI20.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • c7a6ca4c on GitHubfix(security): row-scope transcript access end to end — cross-tenant leak Claude Code
  • 592faa1d on GitHubfix(msteams): handle post-Join "Continue without audio or video" modalClaude Code
  • 176f1e1e on GitHubchore(clients): vendor the full dashboard, docs dropped — refactor pendingClaude Code
  • 371a0b66 on GitHubfeat(zoom): support bring-your-own OBF and ZAK tokens (#320)Cursor Agent
  • 8af5203e on GitHubIssue templates: use markdown files with standard frontmatterCursor Agent
  • 8f9ad75a on GitHubIssue templates: use markdown files with standard frontmatterCursor Agent
  • 3260bf29 on GitHub[DEV] Release train v0.12.27 — byte-identical to production (#1553) (#1559OpenAI Codex
  • 5a8b2c3d on GitHubrelease(0.10.6.3): 7-pack stitched release (#387)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 window1,936
Merge commits removed−159
CI / dependency bots removed−0
Considered1,777

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Python AI coding statisticsCompare evidence across Python 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 Vexa-ai/vexa

Scan another repository

Try