Skip to content
repository radar
Voice, Vision & Multimodal

🎙️dograh

ACTIVE BREAKOUT

dograh-hq/dograh · homepage ↗

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.

⭐ Popular: 5k stars, gaining about 136 a week

View on GitHub ↗

repo profile

vintage 2025 1 year old
delivery product
language Python
license BSD-2-Clause

momentum

total stars 5k
stars added last week +136
used by 6 repos & packages
commits / week 19 cooling · -29% vs prior mo
issues closed 96% ~8d to close, median
contributors 59 (+5 in 15d)
release cadence weekly
last activity 2d ago

durability

backing community / independent independent
openness permissive
bus factor 1 solo
top-author share 54% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

since we covered it

monthly average + 2k/mo (+54270%/mo) · + 5k total since PR#35

why it's a big deal

  • It gives teams a self-hosted alternative to Vapi and Retell, so voice agents can run without sending call data or logic through a proprietary vendor.
  • A drag-and-drop workflow builder plus in-dashboard web calls and a test mode lets non-specialists build and validate agents without wiring code by hand.
  • Bring-your-own LLM, STT, and TTS plus multiple telephony providers (Twilio, Vonage, Telnyx, Cloudonix) avoids lock-in to any single model or carrier.

under the hood

  • Built mostly in Python with a TypeScript frontend, and released under the BSD 2-Clause license.
  • Voice pipelines run on the Pipecat framework (vendored as a submodule), with COTURN handling the connectivity layer for real-time audio.
  • Ships Docker-first with a single-command self-hosted setup including HTTPS, auto-generated API keys, native MCP support, and Python and Node SDKs.

Radar summary, generated from the project's public sources

star history

PR#35 · 45k now Sep 2025Aug 2026
  1. PR#35 4 2026-06-03
  2. now 5k + 5k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Quietly building: more output than attention, for now.

+12 understory score output 84 · clout 72
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#35 2026-06-03 below the radar

    Open-source voice-agent platform, the Vapi alternative

similar projects

compare these →
  • ⚡ Unsloth

    13× the stars

    Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.

    72k ACTIVE
  • 🎬 OpenMontage

    9× the stars · AGPL-3.0 licensed

    World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.

    48k ACTIVE
  • 🤖 nanobot

    8.8× the stars

    Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

    47k ACTIVE

comments

Sign in with GitHub to add your blip on dograh.

loading comments…