taketwo/llm-ollama

LLM plugin providing access to models running on an Ollama server

What it solves

This project provides a plugin for the llm command-line tool, allowing users to easily access and interact with models running on an Ollama server—whether that server is hosted locally, on a remote machine, or via Ollama's hosted cloud service.

How it works

The plugin connects to an Ollama server (via OLLAMA_HOST) and automatically discovers all available models. It registers these models with the llm tool, enabling them to be used for prompting, chatting, and generating embeddings. It supports various connection methods, including Basic Authentication and custom headers for reverse proxies.

Who it’s for

Developers and AI enthusiasts who use the llm CLI tool and want to integrate local or remote Ollama-managed models into their workflow.

Highlights

  • Multi-modal support: Accepts image attachments for vision-capable models.
  • Tool use: Supports LLM tools, including built-in web search and fetch tools via the Ollama cloud API.
  • Reasoning traces: Surfaces reasoning steps from "thinking" models, with options to hide or disable them.
  • Structured outputs: Integrates with Ollama's structured output support via JSON schemas.
  • Async support: Provides async LLM models for use with Python's asyncio.
  • Flexible configuration: Supports Modelfile parameters as options and handles model aliases automatically.

Related

  • Project
    ollama/ollama-python

    A Python client for Ollama’s LLM server, offering simple sync/async chat, generation, streaming, embedding, model management, and cloud‑model access.

  • Dispatch
    Ollama Cloud Models Preview

    Ollama has introduced Cloud models in preview, enabling users to run large-scale models on datacenter-grade hardware while maintaining the same local toolset and API integration.

  • Project
    simonw/llm

    A CLI tool and Python library for interacting with various remote and local Large Language Models, featuring SQLite logging and plugin-based extensibility.

  • Dispatch
    Ollama Tool Support Release

    Ollama has introduced tool calling support for models like Llama 3.1, allowing local LLMs to interact with external APIs, functions, and code interpreters.

  • Project
    simonw/llm-openrouter

    A plugin for the LLM CLI utility that enables access to a wide variety of AI models hosted by OpenRouter, including support for vision, structured outputs, and hosted server tools.