Yogurt launches as an open-source, on-device meeting assistant
Developer Eric introduced Yogurt on Hacker News as a free, MIT-licensed desktop app and an open-source alternative to Granola. Yogurt runs in the background without joining calls, using on-device models for meeting transcription, summaries, and chat; it supports whisper.cpp, Apple’s on-device SpeechAnalyzer where available, and llama.cpp. The developer says transcripts, recordings, and summaries remain on the user’s computer, while a local MCP server can expose notes to external AI services.
Yogurt offers an open-source, locally processed alternative to cloud meeting assistants for privacy- and cost-conscious users, though its privacy and capability claims have not been independently verified.
Hey HN, I’m Eric and I want to share an OSS project that I’ve been building in my free time. Yogurt is a free, MIT licensed desktop app that uses on-device AI models to transcribe, summarize, and chat with your meetings.
Here's a quick demo video: https://www.youtube.com/watch?v=BFfbXAwRq98
Similar to Granola, Yogurt runs in the background and does not join your calls. But unlike Granola, Yogurt is open-source, free to use, and private. Your meeting transcripts, call recordings, and summaries never leave your computer.
As small OSS models have gotten faster and more powerful, Yogurt seemed like a pretty obvious win for privacy and cost conscious folks. You do not need a frontier model to summarize meeting notes or answer questions about them. And if you want to make your notes available to a frontier model, you can just share it with Anthropic, OpenAI, etc. directly via Yogurt’s local MCP server. There’s no need to use a paid cloud service as a middleman.
I tried some of the most popular OSS note taking tools, and most were missing features like calendar integration, MCP server, etc. or required you to connect or create an account. And more than that, they didn’t feel polished enough for it to be something I actually wanted to use daily, and so I built Yogurt to scratch that itch. I spent a lot of time fine-tuning every UI interaction/animation and optimizing the model calls to get the most out of your hardware + make it snappy.