paulrobello/parllama

TUI for Ollama and other LLM providers

What it solves

PAR LLAMA is a terminal-based interface (TUI) that simplifies the management and interaction with local and cloud-based Large Language Models. It removes the need for complex command-line interactions or browser-based interfaces by providing a unified, keyboard-driven environment for chatting, model management, and session organization.

How it works

Built with the Textual and Rich Python libraries, the application provides a responsive, asynchronous interface that connects to local Ollama instances or various cloud providers (OpenAI, Anthropic, Groq, etc.). It manages chat sessions, handles document attachments (with text extraction for models lacking native support), and provides a secure, encrypted vault for storing API keys. Users can navigate through different tabs to manage local models, pull new models from registries, configure system prompts, and execute templates.

Who it’s for

This tool is designed for developers and power users who prefer working within a terminal environment and want a centralized, efficient way to manage multiple LLM providers and local models without leaving their command line.

Highlights

  • Multi-Provider Support: Works with Ollama, OpenAI, Anthropic, Groq, XAI, OpenRouter, Deepseek, and LiteLLM.
  • Cross-Platform TUI: Runs natively on Windows, macOS, and Linux with a responsive, keyboard-centric interface.
  • Advanced Session Management: Supports saving, exporting, and auto-naming chat sessions, plus persistent memory across conversations.
  • Document & Vision Support: Allows attaching PDFs, text, and Markdown files, as well as interacting with vision-capable models like LLaVA and GPT-4 Vision.

Related

  • Project
    ggozad/oterm

    oterm is a terminal client that provides a TUI for interacting with LLM providers like Ollama, OpenAI, and Anthropic.

  • Project
    fmaclen/hollama

    A minimal, browser-based LLM chat application that connects to Ollama and OpenAI servers while storing all data locally.

  • Project
    sammcj/gollama

    Gollama is a Go‑based terminal UI for listing, inspecting, editing, running, unloading, copying, deleting and pushing Ollama models, with command‑line shortcuts and a vRAM estimator to help decide if a model fits on your hardware.

  • 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.

  • Project
    taketwo/llm-ollama

    A Python plug‑in for the LLM CLI that discovers and talks to Ollama models (local, remote, or cloud). It adds commands for listing models, prompting, chatting, image attachments, tool use, embeddings, reasoning traces, JSON schemas, and async calls, all configurable via environment variables.