# Cherry Studio

> One desktop chat app for cloud and local LLM providers

- Category: App UIs & Builders / Chat UIs
- Language: TypeScript
- Licence: AGPL-3.0
- Repository: https://github.com/CherryHQ/cherry-studio
- Website: https://cherry-ai.com
- Canonical page: https://ai-tldr.dev/tools/cherry-studio/

## In short

Cherry Studio is a desktop chat client that talks to many large language model providers from a single app. It runs on Windows, Mac, and Linux, and connects to cloud services like OpenAI, Gemini, and Anthropic, as well as local models served through Ollama or LM Studio. It sits in the Chat UIs category of the App UIs & Builders tools and is open-source, written in TypeScript and licensed AGPL-3.0.

## Overview

Cherry Studio is a desktop chat client that talks to many large language model providers from a single app. It runs on Windows, Mac, and Linux, and connects to cloud services like OpenAI, Gemini, and Anthropic, as well as local models served through Ollama or LM Studio.

It is aimed at people who use several models and want one place to manage them instead of juggling separate web tabs and tools. It ships ready to use with no environment setup, and includes 300+ preset assistants plus the ability to create your own.

As a chat UI, it focuses on day-to-day work: multi-model conversations, document and image input, Markdown and code rendering, global search, and Model Context Protocol (MCP) server support for connecting external tools.

## What it does

- Connects to cloud providers (OpenAI, Gemini, Anthropic) and local models via Ollama and LM Studio
- 300+ pre-configured AI assistants, custom assistant creation, and multi-model simultaneous conversations
- Handles text, images, Office files, and PDFs, with Mermaid charts and code syntax highlighting
- Model Context Protocol (MCP) server support for connecting external tools
- Global search, topic management, AI translation, and WebDAV backup
- Cross-platform desktop app with light/dark themes and full Markdown rendering

## Getting started

Most people install the prebuilt desktop app; developers can also build it from source. It is an Electron app written in TypeScript and React, and uses pnpm.

1. Install the app

   Download the build for your operating system (Windows, Mac, or Linux) from the project's releases page or homepage. No environment setup is required to use it.

2. Add a provider and start chatting

   Open the app, go to settings, add an API key for a cloud provider (such as OpenAI) or point it at a local Ollama or LM Studio endpoint, then pick a model and begin a conversation.

3. Build from source (optional)

   Clone the repo, install dependencies with pnpm, and run the dev build. Enable corepack first if needed.

```bash
pnpm install
pnpm dev
```

4. Package a release (optional)

   Build a distributable for your target platform.

```bash
pnpm build:win
pnpm build:mac
pnpm build:linux
```

## When to use it

- Compare answers from several models side by side in one window without switching between web apps
- Chat with local models through Ollama or LM Studio to keep data on your own machine
- Use preset or custom assistants for recurring tasks like translation, writing, or coding help
- Connect external tools to the chat through MCP servers for more capable workflows