
Yogurt (by Frigade)
New and early (v0.3.x, first created Nov 10, 2026): free, open-source desktop app for AI meeting notes that run on your own computer. It records your mic and call audio with no bot joining the meeting, makes a live transcript (whisper.cpp), then writes a summary and next steps with a local open-weight model through llama.cpp. You can ask questions across past meetings, export to Markdown, and optionally connect a local MCP server. Works offline after the model download and needs no account. Caveats: the Windows installer is unsigned, model downloads are large (about 5 GB to start), speed and quality claims are the maker's own, and it records call audio, so tell people you're recording (California requires all-party consent).
Research notes
How we research- Official site loadsChecked Nov 17, 2026: yogurt.so
- Pricing checked on the vendor siteSource: https://github.com/FrigadeHQ/yogurt
- Free / DIY pathFree download for Mac (Apple silicon, macOS 14.4+), Windows 10 (2004+) x64 and Linux x64; 8 GB memory minimum; runs offline
Listed because it fits the Local AI category. Listings are free; sponsored placements, if any, are labeled and never change rankings.
Alternatives
Ollama
Local AIRun open models locally with one command and a local API.
LM Studio
Local AIDesktop app to download and chat with local models (GGUF/MLX).
llama.cpp
Local AIC/C++ LLM inference engine behind many local AI apps.
MLX
Local AIApple's array framework for fast ML on Apple silicon.
Open WebUI
Local AISelf-hosted ChatGPT-style web UI for Ollama and other backends.
vLLM
Local AIHigh-throughput LLM serving engine for NVIDIA GPU servers.
Mac Studio (hardware)
Local AIApple desktop with large unified memory, popular for local LLMs.
NVIDIA DGX Spark (hardware)
Local AIDesktop Grace Blackwell AI system in 64GB or 128GB unified memory configurations; the 64GB version is sold only through OEM partners.