dograh-hq/dograh

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.

About the project

Dograh is an open-source, self-hostable platform for building voice AI agents that combine speech recognition, language models, and speech synthesis. Teams use its visual workflow builder and telephony integrations to create and operate voice agents while choosing their own providers and infrastructure.

Latest release dograh-v1.49.0 — dograh: v1.49.0 · 12 Oct 2026

7 files for Claude Code, Codex and OpenCode: merge-pipecat-upstream, review-agents-md, review-pr, dograh AGENTS.md and 3 more — 395 tokens loaded in every session.

Open on GitHub app.dograh.com

▶ How to Use MCP to Create & Edit Dograh Voice Agents with Claude Code & Codex Dograh AI · about dograh-hq/dograh · on YouTube →

Instructions

dograh AGENTS.md AGENTS.md A 390 tok
dograh CLAUDE.md CLAUDE.md A 5 tok

Skills

merge-pipecat-upstream .agents/skills/merge-pipecat-upstream/SKILL.md A 102 tok
review-agents-md .agents/skills/review-agents-md/SKILL.md A 82 tok
review-pr .agents/skills/review-pr/SKILL.md A 109 tok

Commands

event-banner-remove .claude/commands/event-banner-remove.md A 10 tok
event-banner .claude/commands/event-banner.md A 13 tok

These files are dograh-hq/dograh's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.