Dograh
Dograh is an open-source, self-hostable voice AI platform for building phone agents with a visual workflow builder, positioned against Vapi and Retell.
- GitHub stars
- 5.8k
- Last commit
- yesterday
- Latest release
- dograh-v1.47.0
- Licence
- BSD-2-Clause
- Self-hosted
- Yes
- Hosted version
- Available
Dograh is an open-source platform for building voice AI agents that can make and receive phone calls. It describes itself as a self-hostable alternative to Vapi and Retell, and promises full code transparency with no vendor lock-in. Agents are designed in a visual workflow builder and can be tested quickly before going live.
The platform supports bring-your-own-key setups across speech-to-speech models or a pipeline of language model, speech-to-text and text-to-speech providers, including local models. It is MCP-native, so AI coding assistants can help design and edit agents, and it includes telephony support for inbound and outbound calling, with Asterisk ARI among its topics. It is written in Python and builds on the Pipecat framework.
Dograh is released under the BSD 2-Clause license and can run on premises or in a hosted cloud, with the vendor operating an app site. It suits support, sales and operations teams that want to automate calls while controlling data and provider choice.
Key features
- Visual workflow builder for voice agents
- Bring-your-own-key model and provider choice
- Speech-to-speech or LLM, STT and TTS pipelines
- MCP-native agent editing
- Inbound and outbound telephony support
- Self-hosted or on-premises deployment
Pricing: Open source under BSD 2-Clause; you bring your own AI provider keys, and a hosted version is available.
