# ggozad/oterm

the terminal client for LLMs

Repository: https://github.com/ggozad/oterm
Canonical: https://ross.abutalabs.com/products/oterm
Language: Python
License: MIT
License Family: permissive
Topics: llm, machine-learning, ollama, python, terminal, llms
Last push: 2026-08-06T08:12:07+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 96, longevity 75
- inputs: {"age_days": 1058, "days_push": 27, "days_rel": 27, "gap_med": 6.0, "n_releases_24m": 57}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2426, forks 139 (observed 2026-08-28T04:06:50.849274+00:00)

## What it is
oterm is a terminal-based chat client for LLMs, supporting Ollama, OpenAI, Anthropic, and any pydantic-ai-supported provider. It offers a rich TUI with markdown streaming, image attachments, thinking sections, token usage display, and MCP tool integration.

## Use cases
- chat with ollama models from the terminal
- use openai or anthropic in a terminal ui
- run a tui chat client for local llms
- connect mcp tools to llm chats
- attach images to llm conversations in the terminal
- compare responses from multiple llm providers
- chat with local models without leaving the shell

## When to choose
- you want a polished terminal UI for chatting with LLMs
- you use Ollama locally but also want cloud providers like OpenAI or Anthropic
- you need MCP tool support in a terminal chat client
- you prefer keyboard-driven, markdown-rendered chat over a browser

## When to avoid
- you need a graphical or web-based chat interface
- you want programmatic API access to LLMs rather than interactive chat
- you need team collaboration or shared chat history features

## Facets
- artifact type: application
- maturity: active
- function: chatbot, chat-interface, llm-inference, mcp, terminal-ui, cli
- domain: large-language-models, artificial-intelligence, developer-tools, chatbots
- platform: cli, cross-platform, python, windows
- tags: ollama, pydantic-ai, tui, textual, multi-provider, openai, anthropic, markdown-streaming, command-line, macos, linux

## Member repositories
- ggozad/oterm (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:50.849274+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:31:38.336761+00:00, confidence not recorded.
  - readme: https://github.com/ggozad/oterm (fetched 2026-08-28T04:06:50.849274+00:00, sha e7e952e6b3dc)
  - registry_pypi: https://pypi.org/pypi/oterm/json (fetched 2026-08-29T10:12:58.042627+00:00, sha 3f5f86829def)
- Data as of 2026-08-30T08:39:29.467469+00:00.