Llama

GGML organization and Llama contributors · A macOS menu-bar controller for local GGUF models, llama.cpp inference, built-in web chat and compatible model APIs.

CaskAI ToolsAuto-updatesApple silicon

Homepage

From homebrew/cask

30-day installs280#404 in App

1-year installs1.2KLast 365 days

Latest version0.43.0Jan 1, 1 · Jan 1, 1

Download size1.2MBarm64 · dmg

Release cadenceWeekly1 release in 30 days

0.44.0
LatestJan 1, 1 · Mon
OpenNavo editorialAdded to Homebrew Oct 8 13:45
Adds decision models and DFlash draft heads, and reorganizes settings.
Models
Run decision models through /v1/systemone with option probabilities.Show a Decision chip and a guide link on compatible model pages.Download available DFlash draft heads; publisher claims up to 50% over MTP.
Engine
Update to b11429; switch immediately when no model is loaded.
Settings
Merge Downloads and Command into Advanced.Rename Web UI to Chat and the setting to custom web app.Open the quick prompt without bringing Settings to the front.
0.43.0
Oct 7 · Wed
OpenNavo editorialAdded to Homebrew Oct 2 10:14
Adds a replaceable Web UI and clearer server status and logs.
Web UI
Serve a chosen local web-app folder instead of the built-in chat.
Server
Show server state and an inline QR code in the menu.Keep localhost usable when bound to Tailscale or another address.Open server logs in Console from Settings.
Engine
Update engine to b11200 on the next start.
0.42.0
Jan 1, 1 · Mon
OpenNavo editorialAdded to Homebrew Sep 2 13:25
Adds controlled network access and QR-code connection details.
Network
Offer Off, Tailscale and This network access modes.Disable exposure when networks change or Tailscale signs out.Show the server address as a QR code.
Interface
Split Settings into General, Network, Downloads, Web UI and Command.Show an MTP chip for models supporting draft-ahead generation.
Engine
Update engine to b10679 on the next start.

Llama

0.44.0

0.43.0

0.42.0

0.41.0

0.40.0

0.39.0

0.38.0

0.37.0

0.36.0

0.35.0

0.34.0

0.33.1

0.33.0