Cherry Studio
Cherry Studio is an open-source desktop client under AGPL-3.0 for Windows, macOS and Linux that connects many model providers in one window: OpenAI, Gemini, Anthropic, web services such as Claude and Perplexity, and local models through Ollama and LM Studio. It ships over 300 preset assistants, runs several models in one conversation, reads text, images, Office files and PDFs, and supports MCP servers. A paid enterprise edition adds private deployment and team features.
What does Cherry Studio do?
Cherry Studio is "a desktop client that supports multiple LLM providers, available on Windows, Mac and Linux." It connects cloud providers "OpenAI, Gemini, Anthropic, and more", web services including Claude, Perplexity and Poe, and local models through Ollama and LM Studio. It ships over 300 pre-configured assistants, lets you make your own, and runs "multi-model simultaneous conversations" so you can compare answers side by side.
It reads text, images, Office documents and PDFs, backs up files over WebDAV, renders Mermaid charts and code, and supports MCP servers. Global search, topic management, translation and mini programs round it out, and the README says it is ready to use with no environment setup. The roadmap lists deep research, an MCP marketplace, OCR, speech, a plugin system and mobile apps as work in progress. An Enterprise Edition, sold by subscription or buyout, adds an admin backend, employee management, a shared knowledge base and private deployment.
Key facts
- Licence: AGPL-3.0, unmodified. The README permits commercial use of the Community Edition under the AGPL and offers a separate commercial licence, by contacting the company, for anyone who needs an exemption from the AGPL's terms.
- Providers: OpenAI, Gemini, Anthropic and more; web services Claude, Perplexity and Poe; local models through Ollama and LM Studio.
- 300+ pre-configured assistants and custom assistants; several models in one conversation.
- Files: text, images, Office documents and PDF; WebDAV backup; Mermaid and code rendering.
- MCP server support; global search, topic management, translation and mini programs.
- Roadmap, not shipped when read: deep research, MCP marketplace, OCR, text to speech, speech recognition, a plugin system, and Android and iOS apps.
- Enterprise Edition: private deployment with admin backend, employee management, shared knowledge base and access control, for a subscription or buyout fee.
- Latest tagged release when read: v2.0.14 on 2026-09-09; 51,935 stars on 2026-09-17.
What does it replace, and where does it fall short?
Cherry Studio replaces the ChatGPT and Claude desktop apps for someone who wants every provider, local models and 300 ready-made assistants in one native window, and who likes comparing models side by side. It is the pick for many providers in one desktop app on the open-source alternatives to Claude page.
Where it falls short: speech, OCR and mobile apps are still on the roadmap. The README does not describe web search, image generation or a knowledge base in the Community Edition; the shared knowledge base is an Enterprise feature. For document chat on the desktop, AnythingLLM.
How does Cherry Studio run?
Download the installer for Windows, macOS or Linux from GitHub Releases; the README says no environment setup is required. Add keys for hosted providers or point it at Ollama or LM Studio. The Enterprise Edition is a separate, privately deployed product sold by subscription or buyout; the Community Edition is free.
Who is Cherry Studio for?
Someone who wants a polished desktop app for many providers and local models with ready-made assistants. A team that needs a shared server should look at Open WebUI or LibreChat, or buy Cherry's Enterprise Edition.
What limits does the README state?
The README's roadmap names OCR, text to speech, speech recognition, a plugin system, multi-window support and mobile apps as work in progress, so they are not in the current release.
Questions people ask
Is Cherry Studio open source?
Yes. The Community Edition is AGPL-3.0, unmodified, and the README says commercial use is permitted in full compliance with the AGPL. A separate commercial licence exempting you from the AGPL's terms is available from the company, and a paid Enterprise Edition exists.
Can Cherry Studio use local models?
Yes. The README lists local model support through Ollama and LM Studio, alongside cloud providers OpenAI, Gemini and Anthropic and web services such as Claude, Perplexity and Poe. Local and hosted models sit side by side in the same window, and one conversation can run several of them at once.
Does Cherry Studio have a mobile app?
Not yet. Android and iOS apps are on the README's roadmap as phase one work in progress, alongside OCR, speech and a plugin system. The current release runs on Windows, macOS and Linux, installed from GitHub Releases with no environment setup.
How does Cherry Studio compare with the Claude app?
Cherry Studio puts Claude beside OpenAI, Gemini and local models in one desktop app, with 300 preset assistants, side-by-side model comparison and MCP. The Claude app is Anthropic's own with its features built in. The open-source alternatives to Claude page compares the options.
What does the Cherry Studio Enterprise Edition add?
A privately deployed platform with an admin backend, employee management, a shared knowledge base, access control and data backup, sold by subscription or buyout. The README says its source is partly released to customers.
Sources
- Cherry Studio README and AGPL-3.0 LICENSE: github.com/CherryHQ/cherry-studio, read 2026-09-17.
Compared with the others
On the open-source alternatives to ChatGPT page, Cherry Studio is the pick for many providers and 300+ assistants in one desktop app. AGPL-3.0 client with OpenAI, Gemini, Anthropic, Ollama and LM Studio, 300+ preset assistants, side-by-side model chats, file support and MCP.
Also on that page: Open WebUI for a private chatgpt for a whole team, LibreChat for every provider in one mit platform, AnythingLLM for chatting with your documents.
On the open-source alternatives to Claude page, Cherry Studio is the pick for many providers and 300+ assistants in one desktop app. AGPL-3.0 client with OpenAI, Gemini, Anthropic, Ollama and LM Studio, 300+ preset assistants, side-by-side model chats, file support and MCP.
Also on that page: LibreChat for claude plus agents, artifacts and a code sandbox, Chatbox for one app across desktop and phone, AnythingLLM for chatting with your documents.
More chat interfaces
A self-hosted chat platform for Ollama and OpenAI-compatible models with document search over 9 vector databases, web search, image generation, roles and single sign-on, under a BSD-3 licence with an added branding clause.
LobeHub, formerly LobeChat, is an agent workspace with an agent builder, agent groups, scheduled runs, editable memory and a library of over 10,000 tools and MCP plugins, under a community licence that needs a paid licence to distribute a modified version.
An MIT all-in-one AI app from Mintplex Labs for chatting with your documents with citations, running agents with MCP, and using any of 39 model providers including local llama.cpp and Ollama, as a desktop app or a multi-user Docker server.
An AGPL-3.0 desktop app for local models, formerly text-generation-webui, with five engines including llama.cpp and ExLlamaV3, an OpenAI and Anthropic-compatible API, tool calling, file chat, image generation and LoRA training, fully offline.
An Apache-2.0 desktop app from Menlo Research that downloads and runs open models from Hugging Face on your own computer, connects to OpenAI, Anthropic and others when you want, serves a local OpenAI-compatible API, and supports MCP.
Added September 17, 2026. Every claim above comes from the project's README, LICENSE or model card, read on September 17, 2026, or from the GitHub API on the date shown in the panel. Found an error? Write to reveneau@licheo.com and it is fixed in the next weekly pass. Repository: github.com/CherryHQ/cherry-studio.
Running one of these inside your own environment, with your own data and your own security rules, is the kind of work Reveneau does. Read how a forward deployed engagement works.