Dograh
The open source VAPI alternative
In plain words
Dograh is an open-source, self-hosted voice agent platform that lets developers build conversational AI without relying on closed services. It offers a visual flow builder, support for 30+ integrations, multiple AI model options including local models, telephony capabilities, and human transfer features. Users can deploy on their own servers or cloud infrastructure, keeping all data within their perimeter for compliance and security. The platform supports speech-to-speech pipelines and integrates with Claude via MCP for custom voice agent development.
written from the facts on this page · September 2026
From the sources
Closed voice platforms make you rent your own agents. Dograh is completely open source- nothing is gated. Visual flow builder, add your model key across 30+ integrations or use local models, telephony, human transfer, and advanced QA & monitoring - all free to self-host in one command. Also connect your claude code with MCP to build voice agents for a use case or call recordings.
Open-source, self-hostable voice agent platform. Bring your own models, drive it from MCP, deploy on your servers or our cloud. The open-source alternative to Vapi and Retell.
Click any node to see the providers you can plug in. Pick your inbound channel, STT, LLM, TTS, and telephony. Or skip the cascade entirely and switch the whole pipeline to speech-to-speech. Deploy Dograh on-prem or inside the VPC of your own cloud - even the AI models can be served within your perimeter or fully air-gapped, so no calls, recordings, transcripts, or model inference ever leave your boundary. Data security, data residency, and compliance, built in by default. Auditable open source, enterprise-ready for the most regulated industries and jurisdictions. Data stays in your perimeter, so your existing certifications and controls keep covering it — no third-party vendor to audit.…from dograh.com
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 28d ago · gtmcofounder.com
Lettertrace▲375Track your AI visibility for free (using your own API keys!)
Dev tools · 24d ago · lettertrace.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 9d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com