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 voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.

01Result

dograh-hq/dograh ↗

dograh-hq/dograh AI coding statistics: 16.3%

of 607 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
16.3% agent · top contributor 42.4%31 contributors
org-wide

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

99
agent commits
508
other considered commits
31
agent contributors
42.4%
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

99assisted
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
2026-020%46
2026-030%78
2026-041.3%76
2026-057.4%108
2026-0625.3%95
2026-0728.4%109
2026-0831.7%63
2026-0946.9%32

Peak month: 46.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic9716%
Cursor AgentAnysphere10.2%
GitHub CopilotGitHub10.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • fc76383c on GitHubfeat: transfer call to a different agent (#776)Claude Code
  • 23d22b95 on GitHubfix(answer): run answer handling on inbound, and let patterns beat the cloClaude Code
  • 7d78e304 on GitHubfix(ui): derive session cookie Secure flag from the request, not NODE_ENV Claude Code
  • cfe1d370 on GitHubfeat: add ElevenLabs realtime STT provider support (#512) (#522)Cursor Agent
  • 8a58b099 on GitHubfeat: allow overriding base URL of OpenAI models (#368)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 window626
Merge commits removed−19
CI / dependency bots removed−0
Considered607

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 →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 dograh-hq/dograh

Scan another repository

Try