Back to directory

Ollama App

A cross-platform client app for Ollama that connects to an existing Ollama server over its API, without hosting a model server on the device itself.

Ollama App

Ollama App is a client for Ollama, aimed at being modern and easy to use while keeping conversations private and on the local network. It does not run an Ollama server on the device; instead it connects to an existing Ollama server through its API endpoint, so a host running Ollama must already be set up and reachable.

It installs on Android from the releases page or app stores, and has experimental desktop support for Windows and Linux; the Windows build is an unsigned installer, and the Linux build is a portable executable that may need a GTK package installed first on some distributions. After installation, the most involved step is pointing the app at the host's address, which normally only needs to be entered once. A newer, experimental voice mode is also available.

Application data is stored per platform, for example under the user's AppData folder on Windows or a local share directory on Linux.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.