wedge is a
CLI tool that makes it easy to download and use
Large
Language
Models (LLMs). All models run via
wedge expose
a simple, standardized local HTTP interface, making it easy to build
model-agnostic tools that rely on LLMs.
wedge also
includes a CLI chat UX for interacting directly with installed models.
It currently supports OS X and Linux, and includes both local and remote
models in its package repository. The ability to add new packages/models
to the Wedge repository is coming soon. Meanwhile, if you're interested
in contributing,
shoot me an email.