OSS Tanbou
View on GitHub

Dograh — self-host voice agents with visual workflows, pluggable LLM/STT/TTS, telephony, and MCP

OSS scale score Not calculatedOSS health 93Update pace 49 commits/30d
About these scores

OSS scale score is an unbounded metric that log-compresses and weights Stars, Watchers, Forks, and Contributors. Discovery score is the current OSS scale score minus the score at discovery. Update pace is commits in the last 30 days, growth momentum is the OSS scale score difference within the recent observation window, and OSS health is a 0–100 rating based on available recency, Community Health, and release data.

Stars
5,691
Primary language
Python
License
BSD-2-Clause
Repository last updated
Sep 18, 2026

Overview

Dograh is a self-hostable voice AI platform for visually designing agent workflows and swapping LLM, speech-to-text, text-to-speech, and telephony providers. It supports Twilio, Vonage, Telnyx, Plivo, Asterisk ARI and more, plus MCP and Python/Node SDKs. The latest release checked is dograh-v1.47.0.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Design voice workflows visually and test by audio or chat

Start/agent/tool/transition/end nodes can be combined with knowledge bases, webhooks, and tool calling, then tested through browser audio/chat.

Sources: [2]

Bring your own LLM, STT, TTS, and telephony providers

Dograh supports its bundled stack or external model/speech/telephony providers and human handoff on supported integrations.

Sources: [2]

For teams that want voice AI under their own infrastructure/provider choices

It fits support, booking, qualification, and outbound workflows where SaaS lock-in or data residency matters.

Sources: [2]

Review call-data privacy, telemetry, and external-provider flows

Anonymous telemetry is enabled by default according to the README and can be disabled with ENABLE_TELEMETRY=false. External LLM/STT/TTS/telephony services may receive voice/text data, so recording consent, retention, and privacy controls remain essential. Dograh is BSD-2-Clause.

Sources: [2][3][4]

Official sources

  1. [1]dograh-hq/dograh repository(2026-09-18)
  2. [2]Dograh README(2026-09-18)
  3. [3]Dograh LICENSE(2026-09-18)
  4. [4]Dograh v1.47.0 release(2026-09-18)
Supplemental curator note

Dograh brings Vapi/Retell-style voice agents on-premises. The README states anonymous telemetry is enabled by default and can be disabled with `ENABLE_TELEMETRY=false`; call audio/transcripts/recordings require deliberate privacy controls.

Try it in 3 steps

  1. 1

    Get the source

    git clone --depth 1 https://github.com/dograh-hq/dograh.git
  2. 2

    Enter the repository

    cd dograh
  3. 3

    Check the official steps

    Continue with the commands in the README Installation, Quick Start, or Getting Started section.

    find . -maxdepth 1 -iname 'README*' -exec sed -n '1,220p' {} \; -quit
Check the official README

Growth

Growth trends · Last 30 days

5,691 Stars

Trend data is still being collected.

Development activity

Last 90 days · weekly

Commits (last 30 days)
49
Open PRs
34

Development activity is still being collected.

Built with

Categories and tags

Categories

Tags

GitHub data

GitHub dataView detailed GitHub data
View on GitHub

GitHub Topics

  • conversational-ai
  • open-source
  • outbound-calls
  • pipecat
  • python
  • self-hosted
  • speech-to-text
  • telephony
  • text-to-speech
  • voice-agents
  • ai-calling
  • inbound-calls
Stars
5,691
Forks
1,419
Watchers
44
Open issues
50
Primary language
Python
Repository last updated
Sep 18, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.