Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Dograh

an OSS Vapi alternative to quickly build and test voice agents

Details

External ID
46189836
Source
HN
Company
—
Product
Dograh
Website domain
github.com
Launched
Dec. 8, 2025
Cohort
—
Upvotes
16
Upvotes percentile
0.6183206106870229
Tags
—
Fetched at
Sept. 7, 2026, 9:25 p.m.
Updated at
Sept. 7, 2026, 9:25 p.m.

Description

Hi HN, I have been building voice agents for sometime now. I was earlier automating parts of visa processing, and we needed real-time, multilingual voice calling.I assumed the hard work was just wiring LiveKit/Pipecat + STT/TTS + an LLM. It wasn’t.Even with solid OSS (Pipecat/LiveKit), we still had to do a lot of plumbing- variable extraction, tracing, testing etc and any workflow changes required constant redeploys.We eventually realized we’d spent more time building infrastructure than building the actual agents. Everything felt custom. We hit every possible pain with Pipecat and VAPI style systems.So we built Dograh - a fully open-source voice agent framework that includes all the boring, painful pieces by default.What’s different:- Pipecat-based engine, but forked - custom event model, and concurrency fixes- One-click start template generated by an LLM Agent for a quick get start template for any use case- Drag-and-drop visual agent builder for quick iteration (the thing we wished existed earlier)- Variable extraction layer (name/order/date/etc.) baked into the LLM loop- Built in Telephony integration (Twilio/ Vonage/ Vobiz/ Cloudonix)- Multilingual support end-to-end- Select any LLM TTS STT (add their credits, if any)- AI-to-AI call testing: automatically stress-test an agent before shipping (still a work in progress- so patchy as of now)- Fully Open SourceIt's built and maintained by YC alumni / exit founders who got tired of rebuilding the same plumbing.Why we open-sourced it: We kept feeling that the space was drifting toward closed SaaS abstractions (VAPI, Retell). Those are good for demos, but once you need data controls, privacy or self/offline deployment, you end up stuck. We wanted a stack where you can see every part, fork it, self-host it, and patch it as needed.Try it:- Repo: https://github.com/dograh-hq/dograhThis spins up a basic multilingual agent with everything pre-wired.Who this is for:- If you are looking for self hosting a Vapi like platform for Data Privacy etc.- Anyone trying to build production-grade voice agents without reinventing audio plumbing.- If you’ve tried to glue STT→LLM→TTS manually, you probably know the exact pain this is built forHappy to answer technical questions, show the architecture, or hear how we can improve the product.

Enrichment

Theme
voice AI agents and infrastructure
Vertical
Horizontal
Function
Agent / copilot
Audience
Developer
AI stance
AI-native
Project type
Hobby / open-source project
Normalized one-liner
voice agent development framework
Manually corrected
False

Could you build this?

Partial While standard WebRTC voice agents can be quickly scaffolded, building a reliable platform that handles telephony (SIP/PSTN), low-latency audio pipelines, barge-in, and agent evaluation requires non-trivial audio systems engineering.

What it would actually take: The system requires a distributed WebRTC/SIP telephony gateway (FreeSWITCH, Asterisk, or LiveKit SIP), orchestrating streaming pipelines between VAD (Silero), STT (Deepgram/Whisper), fast LLM inference, and streaming TTS (Cartesia/ElevenLabs). The hard engineering piece is sub-500ms voice turn-taking, acoustic echo cancellation, handling natural interruptions (barge-in), and packet-loss resilience over poor cellular connections.

Discussion

10 comments analyzed.

Competitors mentioned: Vapi, Retell, OpenAI Real Time API, Gemini Live, Qwen 3 Omni

Concerns raised: Latency vs reasoning tradeoff with larger models, High platform fees (60-70% of total spend), LLM inference lag from providers, Instruction following quality with smaller open-source models, Managing long-running conversations while keeping context tight and cost-effective

Feature requests: Different voice personas selector, Standardized way to extract variables from conversations, Faster workflow iteration without redeploying, AI-to-AI test loops

Competitors

Other products that read as similar to this one — 85 launches clear the similarity bar, closest 8 shown.

Attention rank: #32 of 86 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 32 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a agent / copilot tool for Agriculture yet.