A Python library and CLI that lets any supported LLM (OpenAI, Anthropic, Ollama, LMStudio) call tools on one or more MCP servers via natural language.
ggozad/oterm
A terminal chat client for Ollama, OpenAI, Anthropic and other pydantic-ai-supported LLM providers.
- Stars
- 2,447
- Forks
- 140
- Open issues
- 3
- Last commit
- 23 hours ago
What is it?
oterm is a text-based user interface for chatting with large language models directly from the terminal. It connects to local models served by Ollama as well as hosted providers such as OpenAI and Anthropic, and can use any provider supported by pydantic-ai.
The client is built with Textual and runs in any terminal, so developers can keep model conversations next to their shell, editor and code without switching to a browser. The project is installable with uvx oterm and is configured through its documentation site.
The topics on the repository point to MCP (Model Context Protocol) support, so the client can be used alongside tool servers that expose external capabilities to the model.
Key features
- 01Chat with local Ollama models from the terminal.
- 02Connect to OpenAI and Anthropic models.
- 03Supports any provider available through pydantic-ai.
- 04Runs as a Textual-based terminal user interface.
- 05Install and launch with uvx oterm.
Use cases
- Chatting with a locally hosted model without leaving the terminal.
- Comparing or switching between OpenAI, Anthropic and Ollama models from one client.
- Using LLM assistance during server or SSH sessions where a browser is unavailable.
Quick start
- 1
Run oterm with uvx
uvx oterm
Things to know
- Full install and configuration details are only in the external documentation site.
Topics
FAQ
- What is oterm?
- A terminal chat client for Ollama, OpenAI, Anthropic and other pydantic-ai-supported LLM providers. oterm is a text-based user interface for chatting with large language models directly from the terminal. It connects to local models served by Ollama as well as hosted providers such as OpenAI and Anthropic, and can use any provider supported by pydantic-ai.
- Is oterm free to use? What license does it have?
- oterm is open source under the MIT license. Check the license terms before using it in commercial products.
- Is oterm still maintained?
- Actively maintained. The last commit to oterm was on Oct 21, 2026.
- What can I use oterm for?
- Chatting with a locally hosted model without leaving the terminal. Comparing or switching between OpenAI, Anthropic and Ollama models from one client. Using LLM assistance during server or SSH sessions where a browser is unavailable.
- How do I install oterm?
- Run oterm with uvx: uvx oterm
- Where can I get oterm?
- The source code and installation instructions are on GitHub: https://github.com/ggozad/oterm
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Self-hosted ChatGPT-style chat platform that unifies many AI providers, with Agents, MCP support, Artifacts, and multi-user auth.
A command-line tool and Python library for running prompts and chats against remote and locally installed large language models.
Desktop client for ChatGPT, Claude and other LLMs, running on Windows, macOS and Linux with local data storage.
Open-source AI agent that automatically reviews pull requests and offers /describe, /review, /improve and /ask commands on GitHub, GitLab, Bitbucket and Azure DevOps.
A Python terminal chat client for OpenAI-compatible LLMs, Ollama and Telegram, with MCP server support.