Directory / Local AI

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).

Local AIOpen sourceFree option
Visit site
CategoryLocal AI
PricingFree, open source (MIT); no paid tier found(summary; confirm on vendor site)
Free pathFree download for Mac (Apple silicon, macOS 14.4+), Windows 10 (2004+) x64 and Linux x64; 8 GB memory minimum; runs offline
Official sitehttps://www.yogurt.soLink last checked 2026-11-17

Research notes

How we research

Listed because it fits the Local AI category. Listings are free; sponsored placements, if any, are labeled and never change rankings.

Alternatives

Ollama

Local AI

Run open models locally with one command and a local API.

Free locally; cloud Pro $20/mo ($200/yr), Max $100/mo; Team $500/mo (early access)Free option

LM Studio

Local AI

Desktop app to download and chat with local models (GGUF/MLX).

Free $0 for local models; Bionic+ $20/mo and Pro $100/mo (US-hosted cloud, billed monthly). Organization plans have no public dollar price.Free option

llama.cpp

Local AI

C/C++ LLM inference engine behind many local AI apps.

Free, open sourceOpen sourceFree option

MLX

Local AI

Apple's array framework for fast ML on Apple silicon.

Free, open source (MIT)Open sourceFree option

Open WebUI

Local AI

Self-hosted ChatGPT-style web UI for Ollama and other backends.

Free self-host; enterprise optionsFree option

vLLM

Local AI

High-throughput LLM serving engine for NVIDIA GPU servers.

Free, open sourceOpen sourceFree option

Apple desktop with large unified memory, popular for local LLMs.

Hardware; from $2,499 (M5 Max); M5 Ultra from $5,499

Desktop Grace Blackwell AI system in 64GB or 128GB unified memory configurations; the 64GB version is sold only through OEM partners.

Hardware purchase; 64GB partner systems from $4,999 (NVIDIA)

See all 35 Local AI tools

Visit Yogurt (by Frigade)