Find your next open-source project

Search by name, purpose, or keyword — or paste a GitHub repository URL

CherryHQ/cherry-studio

Productivity & Utilities

A cross-platform AI desktop workspace for chatting with multiple models, running agents, building knowledge bases, and creating images.

53,509
5,222
TypeScript
AGPL-3.0
2 years old

What it is

Cherry Studio is a desktop AI workstation for Windows, macOS, and Linux. It puts multi-model chat, agents, local knowledge bases, image generation, translation, and workspace tools in one application, targeting users who want to work across several LLM providers without switching between many separate clients.

Within one workspace, users can configure cloud providers such as OpenAI, Anthropic, and Gemini or custom OpenAI-compatible services, and also run local models through Ollama and LM Studio. Agents can be given their own instructions, workspace, model, and tool permissions, and can be extended with Skills and MCP servers. Knowledge bases accept files, folders, and web pages, and are usable in both conversations and agent workflows. Speech input/output, local and WebDAV backup, and a light/dark theme system round out the desktop experience.

Getting started

  1. Download the desktop build for your platform from the download page.
  2. Follow the quick-start guide to complete initial setup.
  3. Open the provider settings and add a cloud provider API key, or point the app at a local Ollama or LM Studio endpoint.
  4. Create a conversation and select the configured model; optionally compare responses from more than one model in the same conversation.
  5. For RAG-style work, create a knowledge base, add files or folders, then reference it from a conversation or an agent.

The official documentation is the authoritative reference for provider configuration, model setup, and feature-specific requirements.

Constraints

  • Feature availability depends on the operating system, configured provider, and downloaded models; some capabilities require API credentials or system permissions.
  • Agent capabilities such as file operations, command execution, and browser/computer automation depend on the permissions granted to each agent.
  • Themes written for v1 must be adapted before they work with the v2 interface.
  • The community edition is licensed under AGPL-3.0; commercial use is permitted under the license terms, and a separate commercial license is available for organizations needing an exemption.

HotRepo's take

On 2026-11-14 Cherry Studio recorded 31 new stars in the TypeScript daily list and placed 9th in that day's ranking. That single snapshot shows continued visibility in the TypeScript ecosystem, but it is not enough to establish a longer-term trend on its own. No best overall daily rank is available in the station's records, and there are no discussion threads to draw on.

Written by AI from the project's README, updated . The project's own docs are the source of truth.

Hacker News

LLM desktop client – Cherry Studio
▲ 3 · 0 comments · January 23, 2025

You might also like

  1. sigoden/aichatA terminal LLM client that unifies 20+ providers with shell command generation, chat REPL, RAG, tools and agents.Rust10,548
  2. modelcontextprotocol/java-sdkLets JVM applications expose tools to, or call tools from, AI models over the Model Context Protocol.Java3,743