CherryHQ/cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

Cherry Studio – A Cross‑Platform Desktop Client for LLMs

What it is – Cherry Studio is an open‑source desktop application (Windows, macOS, Linux) that lets you chat with a wide range of large language models (LLMs). It bundles cloud services (OpenAI, Gemini, Anthropic, etc.), web‑based AI services (Claude, Perplexity, Poe) and locally‑run models (Ollama, LM Studio) into a single UI, so you don’t need to configure each provider separately.

Key capabilities

  • Multi‑model support – Switch between dozens of providers or run several models side‑by‑side in one conversation.
  • 300+ ready‑made assistants – Pre‑configured AI personalities for common tasks; you can also create your own.
  • Rich content handling – Paste or upload text, images, Office files, PDFs; the app extracts and displays them, even rendering Mermaid diagrams and syntax‑highlighted code.
  • Productivity tools – Global search, topic management, AI‑powered translation, drag‑and‑drop sorting, mini‑program extensions, and a “Model Context Protocol” (MCP) server for custom back‑ends.
  • User experience – Light/dark themes, transparent windows, full markdown rendering, easy sharing, and no extra environment setup.

Roadmap highlights (still in development)

  • Selection‑assistant, deep‑research, better document preprocessing, and an MCP marketplace.
  • Knowledge‑management features such as notes, collections, OCR, TTS, and a dynamic canvas.
  • Expanded platform support (HarmonyOS, Android/iOS, multi‑window, Intel AI PC).
  • Plugin system, automatic speech recognition, and UI refactoring.

Community & licensing

  • The community edition is released under AGPL‑3.0; a commercial/enterprise edition is available for private deployment with admin controls, shared knowledge bases, and role‑based permissions.
  • Contributions are welcomed via pull requests, issues, and discussions. The project also runs a contributor‑rewards program (credits for Cursor, unlimited DeepSeek/Qwen API calls, etc.).

Where to start

  • Download the latest release from the GitHub releases page or build from source (no extra setup required).
  • Check the online documentation for usage tips and the developer guide if you want to add features.

Related projects – The README links to other LLM gateway tools such as new‑api and one‑api, as well as the Poe platform for accessing many models in one place.

All information above is taken directly from the repository’s README.

Related

  • Project
    CherryHQ/cherry-studio-app

    A mobile AI workspace for iOS and Android that lets users chat with multiple AI models, build custom agents with tools, and generate images.

  • Project
    pmbstyle/Alice

    A desktop AI companion with voice interaction, system-level tool access, and long-term memory that can be run locally or via cloud APIs.

  • Project
    chatboxai/chatbox

    A cross-platform desktop and mobile client for ChatGPT, Claude, and other LLMs that provides a unified interface and local data storage for enhanced privacy.

  • Project
    netease-youdao/LobsterAI

    A desktop AI agent that operates within your local environment, automating tasks across files, terminals, browsers, and office software.

  • Project
    MindWorkAI/AI-Studio

    MindWork AI Studio is a free cross‑platform desktop app that lets users chat with many LLM providers (cloud or local), use pre‑built assistants, run tool‑enabled RAG, and manage settings centrally for enterprises. It runs on low‑cost hardware, supports voice transcription, and is released under a functional source license that becomes MIT after two years.