Cherry Studio

What Cherry Studio does

Cherry Studio runs as a desktop application on Windows, Mac and Linux and needs no environment setup. It connects to cloud services such as OpenAI, Gemini and Anthropic, to AI web services including Claude and Perplexity, and to local models through Ollama and LM Studio. Users can hold multi-model conversations, create custom assistants or pick from more than 300 pre-configured ones.

Document handling covers text, images, Office files and PDF, with WebDAV file management and backup, Mermaid chart rendering and code syntax highlighting. Other tools include global search, a topic management system, AI-powered translation, mini programs and MCP server support. The README roadmap lists a plugin system, deep research, a selection assistant, notes and mobile apps as planned work, so those should not be assumed to exist yet. The code is published under AGPL-3.0.

Key features

• Connects to cloud LLM providers, AI web services and local models via Ollama and LM Studio
• 300+ pre-configured assistants and custom assistant creation
• Multi-model simultaneous conversations
• Handles text, images, Office files and PDF, with WebDAV backup
• MCP server support
• Mermaid charts, code highlighting, AI translation and light and dark themes

When to use it

• Comparing answers from several models in one conversation
• Running local Ollama or LM Studio models from a desktop chat window
• Chatting about PDF and Office documents and backing up data over WebDAV

Who it is for: Desktop users who want one app for many LLM providers and local models, including people who also run Hermes Agent.

How it fits with Hermes Agent

The repository carries the hermes-agent topic, but the opening part of the README does not describe a Hermes-specific integration. It is a general LLM client with MCP server support, also tagged claude-code, codex and skills.

FAQ