Dograh AI

The open-source, self-hostable alternative to Vapi & Retell — build production voice agents with a visual workflow builder, test them in minutes, and let AI coding assistants help design and edit them through MCP.

• 100% open source, self-hostable — no vendor lock-in, unlike Vapi or Retell
• Full control & transparency — every line of code is open, with flexible LLM / TTS / STT integration
• Maintained by YC alumni and exit founders, committed to keeping voice AI open

🎥 Featured

⚖️ Dograh vs Vapi vs Retell

An honest comparison on the axes that matter most to teams evaluating voice AI platforms.

	Dograh	Vapi	Retell
License	BSD 2-Clause (open source)	Proprietary	Proprietary
Self-hostable	✅ Yes — one Docker command	❌ SaaS only	❌ SaaS only
Pricing	Free (self-host) · usage-based (cloud)	Per-minute SaaS	Per-minute SaaS
Bring your own LLM / STT / TTS	✅ Any provider, or use Dograh's stack	Configurable within their integrations	Configurable within their integrations
Source-level customization	✅ Every line is yours to modify	❌ Closed source	❌ Closed source
Data residency	Your infra, your rules	Their cloud	Their cloud
Vendor lock-in	None	Full	Full

🚀 Get Started

Download and setup Dograh on your Local Machine

Note We collect anonymous usage data to improve the product. You can opt out by setting ENABLE_TELEMETRY=false before running the startup script.

Note If you wish to run the platform on a remote server instead, checkout our Documentation

curl -o docker-compose.yaml https://raw.githubusercontent.com/dograh-hq/dograh/main/docker-compose.yaml && curl -o start_docker.sh https://raw.githubusercontent.com/dograh-hq/dograh/main/scripts/start_docker.sh && chmod +x start_docker.sh && ./start_docker.sh

Note By default the quickstart starts a public *.trycloudflare.com quick tunnel to the API (for inbound telephony webhooks), and signup is enabled. After creating your first account, you can close signup by setting ENABLE_SIGNUP=false in .env and re-running ./start_docker.sh (docker compose restart does not apply .env changes).

⚡ Prefer an AI agent to set it up for you? If you use Claude Code or Codex, install the official Dograh setup skill and let your agent handle installation, configuration, and troubleshooting — it detects your OS, picks the right deploy path, runs Dograh's own setup scripts, and verifies the result.

# In Claude Code
/plugin marketplace add dograh-hq/dograh-plugins
/plugin install dograh@dograh

Then start a new session and ask it to "set up Dograh" (or run /dograh-setup). Codex is supported too — see the plugin repo.

Note First startup may take 2-3 minutes to download all images. Once running, open http://localhost:3010 to create your first AI voice assistant! For common issues and solutions, see 🔧 Troubleshooting.

🎙️ Your First Voice Bot

1. Open http://localhost:3010 in your browser.
2. Pick Inbound or Outbound, name your bot (e.g. Lead Qualification), and describe the use case in 5–10 words (e.g. Screen insurance form submissions for purchase intent).
3. Click Test Agent.
4. Use Test Audio to talk to your agent in the browser, or Test Chat to iterate faster in text. In Test Chat, you can edit or replay user turns and Dograh will regenerate the agent's replies and node transitions from that point.

🔑 No API keys needed. Dograh ships with auto-generated keys and its own LLM / TTS / STT stack. Connect your own keys for LLM, TTS, STT, or Telephony (e.g. Twilio, Vonage, Telnyx) anytime.

Featured On & Community Validation: Dograh was named #1 Product of the Day on Product Hunt.

Build Agents with MCP

Dograh ships with an MCP server, so coding agents can work directly inside your Dograh workspace.

Connect Codex, Claude Code, Cursor, or any MCP client to inspect existing agents, search Dograh docs, fetch node schemas, create new workflows, and save draft edits from natural language.

When asking your coding agent to build a voice agent, share a short script for the use case instead of only a one-line prompt. Include the agent persona, call flow, rules, objection handling, success criteria, and a sample conversation if you have one.

See the MCP guide to connect your assistant.

Features

Voice Agent Builder

• Visual workflow builder with start nodes, agent nodes, global instructions, tools, transitions, and end-call outcomes
• Test Agent panel with Test Audio for browser voice testing and Test Chat for fast prompt iteration
• QA node, knowledge bases, webhooks, embeds, and tool calling for production workflows

Voice & Telephony

• Built-in telephony integrations including Twilio, Vonage, Telnyx, Plivo, Vobiz, Cloudonix, and Asterisk ARI
• Human handoff with call transfer on supported telephony providers
• Bring your own LLM, TTS, STT, and telephony providers; store artifacts in bundled MinIO or AWS/S3-compatible storage

Developer Experience

• One-command Docker setup for self-hosting
• Python backend and modular provider architecture for customization
• Python and Node SDKs for programmatic agent creation and outbound calls

Deployment Options

Local Development

Refer Local Setup

This is the beginning of the README. Read the rest at the original. Read the full README ↗