Pal-AI-Lab/Coopanion

Your tiny AI desktopet companion, built with Cortico 0 0)

What it solves

Coopanion provides an interactive, AI-powered desktop companion that lives on your screen to assist with tasks, chat, and provide a more engaging interface for interacting with various large language models.

How it works

It runs as a lightweight desktop application that integrates with numerous AI model providers (such as OpenAI, Anthropic, DeepSeek, and Gemini). It uses local speech-to-text engines (FunASR or Whisper) to process voice input and can be granted permission to perform basic computer tasks like clicking buttons or typing. The application maintains a persistent memory of your interactions, which is stored locally and used to inform the AI's responses.

Who it’s for

This project is for users who want a personalized, animated AI assistant that resides directly on their desktop, supports voice interaction, and offers the flexibility to switch between different AI model providers.

Highlights

  • Supports a wide range of model services including OpenAI, Anthropic, DeepSeek, Gemini, and more.
  • Includes "computer use" capabilities, allowing the AI to interact with your desktop environment with your permission.
  • Features a customizable "pet" persona with dress-up options, different character figures, and adjustable behavior settings.
  • Offers local voice recognition using FunASR or Whisper.
  • Cross-platform support for Windows, macOS, and Linux.

Related

  • Project
    nanaism/yomiyasu

    A specialized skill for AI coding agents that refines AI-generated Japanese text for better readability and structural clarity in technical and business contexts, while providing tools to verify that the meaning remains unchanged.

  • Project
    papersgpt/papersgpt-for-zotero

    PapersGPT is a native C++ Zotero plug‑in that indexes thousands of PDFs locally and lets you query them with offline LLMs. It offers millisecond‑fast retrieval, cross‑paper synthesis with clickable citations, and an AutoPilot mode for batch processing, all without sending data to the cloud.

  • Project
    ZHZisZZ/dllm

    A library that unifies the training, inference, and evaluation of diffusion language models, providing scalable pipelines and recipes for converting AR models into diffusion models.

  • Project
    Zero6992/chatGPT-discord-bot

    A self-hosted Discord bot that integrates multiple AI providers and local models into one interface, supporting persistent chat history and media generation.