oterm

MCP.Pizza Chef: ggozad

oterm is a versatile terminal client designed for Ollama that runs on Linux, MacOS, and Windows. It offers an intuitive, simple terminal UI without requiring servers or frontends—just type 'oterm' to start. It supports multiple persistent chat sessions with system prompt and parameter customizations stored in SQLite. oterm integrates fully with the Model Context Protocol (MCP), allowing seamless use of MCP tools and prompts. Users can interact with any Ollama-pulled or custom models, customize system prompts and parameters, and leverage external information through tool integrations. Recent updates include MCP Sampling and support for SSE and WebSocket transports, enhancing real-time model interaction and observability.

Use This MCP client To

Chat with LLMs directly from terminal Manage multiple persistent chat sessions Customize model system prompts and parameters Integrate MCP tools for external data access Use custom or Ollama-pulled models View logs within the terminal client Leverage SSE and WebSocket for real-time updates

README

oterm

the terminal client for Ollama.

Features

  • intuitive and simple terminal UI, no need to run servers, frontends, just type oterm in your terminal.
  • supports Linux, MacOS, and Windows and most terminal emulators.
  • multiple persistent chat sessions, stored together with system prompt & parameter customizations in sqlite.
  • support for Model Context Protocol (MCP) tools & prompts integration.
  • can use any of the models you have pulled in Ollama, or your own custom models.
  • allows for easy customization of the model's system prompt and parameters.
  • supports tools integration for providing external information to the model.

Quick install

uvx oterm

See Installation for more details.

Documentation

oterm Documentation

What's new

  • MCP Sampling is here! Also support for SSE & WebSocket transports for MCP servers.
  • In-app log viewer for debugging and troubleshooting.
  • Support sixel graphics for displaying images in the terminal.
  • Support for Model Context Protocol (MCP) tools & prompts!
  • Create custom commands that can be run from the terminal using oterm. Each of these commands is a chat, customized to your liking and connected to the tools of your choice.

Screenshots

Splash The splash screen animation that greets users when they start oterm.

Chat A view of the chat interface, showcasing the conversation between the user and the model.

Model selection The model selection screen, allowing users to choose and customize available models.

Tool support oterm using the git MCP server to access its own repo.

Image selection The image selection interface, demonstrating how users can include images in their conversations.

Theme oterm supports multiple themes, allowing users to customize the appearance of the interface.

License

This project is licensed under the MIT License.

oterm FAQ

How do I install oterm?
You can install oterm quickly using the command `uvx oterm`. For detailed instructions, visit the official installation guide at https://ggozad.github.io/oterm/installation.
Does oterm support multiple operating systems?
Yes, oterm supports Linux, MacOS, and Windows, and works with most terminal emulators.
Can I customize the model prompts and parameters in oterm?
Yes, oterm allows easy customization of the model's system prompt and parameters to tailor interactions.
How does oterm integrate with MCP tools?
oterm supports Model Context Protocol tools and prompts integration, enabling the model to access external information and functionality securely.
Do I need to run any servers or frontends to use oterm?
No, oterm provides a simple terminal UI that requires no additional servers or frontends—just run `oterm` in your terminal.
Can I use my own custom models with oterm?
Yes, oterm supports using any models you have pulled in Ollama or your own custom models.
What new features does the latest version of oterm include?
The latest version includes MCP Sampling, support for SSE and WebSocket transports for MCP servers, and an in-app log viewer.
Where can I find documentation for oterm?
Comprehensive documentation is available at https://ggozad.github.io/oterm/.