AnythingLLM lets you chat with your own documents, do research, build agent workflows and transcribe and summarise meetings. It can run models on your computer or connect to cloud model providers.
There are Mac builds for Apple silicon and Intel. For a basic experience it asks for 16 GB of memory; any M-series chip can run local models without extra hardware.
The desktop app is free and open source (MIT). By default your models, documents and chats stay on your Mac; prompts go to a cloud provider only if you choose one.
How to Get It
brew install --cask anythingllmOfficial downloads only. MLX never re-hosts an app, and never runs a command for you.
MLX Score
Ranked against the run models locally listings, from real public data only. How the score works.
Information
- Developer
- Mintplex Labs
- Category
- Run models locally
- Price
- Free (The desktop app is free.)
- Your data
- On your Mac or in the cloud
- Licence
- MIT
- Mac
- Runs on a Mac (no minimum stated)
- iPhone and iPad
- —
- Needs
- 16 GB memory
- Facts checked
- 2026-11-01
Sources
You Might Also Like
OllamaRun locally
llama.cppRun locally
LM StudioRun locally
Open WebUIRun locally
exoRun locally
LlamaRun locally
vMLX (MLX Studio)Run locallyAnythingLLM is a product of Mintplex Labs; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.