Plain-AyI
← All projects
Speech & audio

Dograh

Build AI voice agents that answer and make phone calls, using a visual drag-and-drop workflow builder.

New this week

What it does

Dograh is a platform for building voice AI agents, bots that speak with people on phone calls. You design the conversation in a visual builder, then test it by talking to it in your browser or chatting in text.

It connects to phone services such as Twilio and Vonage and can hand calls to a human. You can bring your own AI, speech-to-text and text-to-speech providers, or use its built-in stack. Its makers present it as a self-hostable, open-source alternative to paid services like Vapi and Retell.

The README notes it collects anonymous usage data by default, which you can switch off.

Who it's for

Businesses and developers who want phone-calling AI agents they can host and control themselves.

Can I use it without coding?

With some setup. Setup is a single Docker command; after that you build agents in a web page. New to this? Start here.

Can I run it?

Cost
Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
Runs on
Server
API key
Not needed

Try it

  1. Install Docker, then run the one-line setup command from the README.
  2. Open the local web page it gives you and create your first voice bot.
  3. Use Test Audio to talk to your agent in the browser.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (BSD-2-Clause): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it