Happy slice of mcp pizzaMCP.pizza

tome

MCP.Pizza Chef: runebookai

Tome is a free desktop app for Mac and Windows that puts a chat window in front of whichever model you like: Ollama or LM Studio running on your own machine, or Gemini and OpenAI in the cloud. Adding tools is a button rather than a config file, and it draws on the Smithery directory of thousands of ready-made ones. You can also schedule a prompt to run hourly or at a set time each day. It is still labelled a technical preview, with the most recent release in October 2025.

Other
Web/Research

Use This MCP client To

Chat with a model that runs entirely on my own computer Add new abilities to my assistant without editing config files Schedule a daily prompt that runs while I am away Ask my assistant to fetch and summarize a web page Try several different models side by side in one app

README

Tome - Magical AI Spellbook

Tome

a magical desktop app that lets you chat with local or remote LLMs, schedule hourly or daily tasks, all superpowered by MCP

Join Us on Discord License: Apache 2.0 GitHub Release

🔮 Download the Tome Desktop App: Windows | MacOS

Tome

Tome is a desktop app that lets anyone harness the magic of LLMs and MCP. Download Tome, connect any local or remote LLM and hook it up to thousands of MCP servers to create your own magical AI-powered spellbook.

What is MCP? MCP stands for Model Context Protocol and lets your LLM access tools - like search engines, your filesystem, or APIs like Scryfall or Atlassian

🫥 Want it to be 100% local, 100% private? Use Ollama and Qwen3 with only local MCP servers to cast spells in your own pocket universe. ⚡ Want state of the art cloud models with the latest remote MCP servers? You can have that too. It's all up to you!

🏗️ This is a Technical Preview so bear in mind things will be rough around the edges. Join us on Discord to share tips, tricks, and issues you run into. Star this repo to stay on top of updates and feature releases!

🪄 Features

  • 🧙 Streamlined Beginner Friendly Experience
    • Simply download and install Tome and hook up the LLM of your choice
    • No fiddling with JSON, Docker, python or node
    • Chat with MCP-powered models within minutes
  • 🗓 Scheduled Tasks
    • Schedule prompts to run hourly or at a specific time every day
    • Support for any model or MCP servers
  • 🤖 AI Model Support
    • Remote: Google Gemini, OpenAI, any OpenAI API-compatible endpoint
    • Local: Ollama, LM Studio, Cortex, any OpenAI API-compatible endpoint
  • 🔮 Enhanced MCP support
    • UI to install, remove, turn on/off MCP servers
    • npm, uvx, node, python MCP servers all supported out of box
  • 🏪 Integration into Smithery.ai registry
    • Thousands of MCP servers available via one-click installation
  • ✏️ Customization of context windows and temperature
  • 🧰 Native support for tool calls and reasoning models
    • UI enhancements that clearly delineate tool calls and thinking messages
  • 🧪 NEW! Labs Feature: Telegram Relay (must enable Labs in settings)
    • Chat with Tome via our Telegram Relay, use LLMs and MCPs from anywhere you can send a Telegram message!

tome FAQ

Do I need to pay for anything?
The app is free. You bring your own model, and Ollama runs free on your machine if you would rather not pay for a cloud one.
Which computers does it run on?
Mac and Windows. Linux was still listed as coming soon at the most recent release.
Can I use this to keep everything private?
Yes. Pair it with Ollama and tools that run locally and nothing leaves your computer.
Do I have to edit config files or install Docker?
No. Tools are installed from a menu inside the app, including one-click installs from the Smithery directory.
Is it finished software?
No. The developers call it a technical preview, and the latest release was version 0.13.0 in October 2025.
Can it do things while I am away from the computer?
Yes. You can schedule a prompt to run every hour or once a day at a set time.
Which models can I connect?
Gemini, OpenAI and anything OpenAI-compatible in the cloud, or Ollama, LM Studio and Cortex locally.