# llm-ollama

A plugin for Simon Willison's LLM command-line tool that adds access to models running on a local or remote Ollama server, including chat, image attachments, tool calling, and embeddings.

llm-ollama is a plugin for the LLM command-line tool that connects it to models served by Ollama, either a local server or a remote or managed Ollama Cloud instance. It automatically discovers every model available on the configured server and registers it with LLM, along with each model's capabilities, so models can be used for prompting, chatting, or embedding through LLM's usual interface, with shorter aliases generated for models tagged as the latest version.

Multi-modal Ollama models can receive image attachments through LLM's attachment option, and models with tool support can call tools passed to them by LLM, including two bundled tools that wrap Ollama's own web search API to reduce hallucinations when an API key is configured. Both regular and specialized embedding models are supported.

It installs as an LLM plugin and is written in Python under the Apache-2.0 license.

Website: https://github.com/taketwo/llm-ollama