# dograh-hq/dograh

Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across  Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.

Repository: https://github.com/dograh-hq/dograh
Canonical: https://ross.abutalabs.com/products/dograh
Homepage: https://app.dograh.com
Language: Python
License: BSD-2-Clause
License Family: permissive
Topics: conversational-ai, open-source, outbound-calls, pipecat, python, self-hosted, speech-to-text, telephony, text-to-speech, voice-agents, ai-calling, inbound-calls, local-llm, no-code, open-source-voice-ai, speech-to-speech, vapi-alternative, voice-ai-platform, on-prem-voice-agent-platform, asterisk-ari
Last push: 2026-08-25T05:07:41+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 25
- inputs: {"age_days": 358, "days_push": 8, "days_rel": 22, "gap_med": 4.0, "n_releases_24m": 53}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5505, forks 1337 (observed 2026-08-28T04:09:21.733764+00:00)

## What it is
Dograh is an open-source, self-hostable voice AI platform for building production voice agents, positioned as an alternative to Vapi and Retell. It provides a visual no-code workflow builder, flexible STT/TTS/LLM or speech-to-speech pipelines with BYOK, MCP-native AI assistant integration, and telephony support for inbound and outbound calls.

## Use cases
- build a self-hosted voice agent for inbound customer calls
- run outbound AI calling campaigns without vendor lock-in
- design conversational voice workflows with a visual builder
- connect my own STT, TTS, and LLM providers with BYOK
- replace Vapi or Retell with an on-prem voice AI platform
- let AI coding assistants edit voice agent workflows via MCP
- add telephony support to a speech-to-speech agent

## When to choose
- you want full control and transparency over your voice AI stack with self-hosting
- you need BYOK flexibility across STT/TTS/LLM or speech-to-speech providers
- you want telephony (inbound/outbound) support with a visual workflow builder
- you prefer an open-source alternative to Vapi or Retell with no vendor lock-in

## When to avoid
- you want a fully managed hosted voice AI service without operating infrastructure
- you need a simple text-only chatbot with no voice or telephony requirements
- you lack the resources to self-host and manage telephony integrations

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, tts, llm-inference, agent-framework, chatbot, mcp, workflow-automation, self-hosted
- domain: artificial-intelligence, speech-processing, self-hosted
- platform: self-hosted, python, cloud
- tags: voice-agents, voice-ai, telephony, speech-to-speech, vapi-alternative, retell-alternative, visual-workflow-builder, inbound-calls, outbound-calls, pipecat, asterisk-ari, no-code, byok, ai-agents, natural-language-processing, automation, docker, web-server

## Member repositories
- dograh-hq/dograh (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:21.733764+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:56:16.832071+00:00, confidence not recorded.
  - readme: https://github.com/dograh-hq/dograh (fetched 2026-08-28T04:09:21.733764+00:00, sha e3cd76bfebc6)
  - homepage: https://app.dograh.com (fetched 2026-08-29T08:51:20.584477+00:00, sha 5b887ee21601)
- Data as of 2026-08-30T08:39:29.467469+00:00.