Cherry Studio
by Cherry Studio · Open-source desktop AI client for 300+ models across 50+ providers
37.9 — BenchRank score out of 100
Screenshots of Cherry Studio
Homepage Pricing page
Overview
Cherry Studio is a cross-platform desktop client for AI chat, image generation, translation and agents, connecting to 300+ models from 50+ providers including OpenAI, Anthropic, Google and DeepSeek, plus local models via Ollama and LM Studio. It adds a knowledge base built from imported documents and web pages, pre-configured assistants, and MCP server support. Data is stored locally.
- Best for
- Heavy AI users wanting one desktop client for many model providers, with data kept on their machine.
- Pricing
- No prices are published; the Community Edition is free and open source under AGPL-3.0, with an enterprise licence available on request.
Strengths and trade-offs
Strengths
- Free, open-source Community Edition under AGPL-3.0
- 300+ models from 50+ providers, plus local Ollama and LM Studio
- Chat history, settings and knowledge base files stored on device
- Extensible through MCP servers and mini-programs
Trade-offs
- Desktop only: Windows, macOS and Linux; no web or mobile client listed
- Commercial use needs AGPL compliance or a separate enterprise licence
- Enterprise licence terms and prices are not published
- Multi-device sync depends on WebDAV or manual local/cloud backups
How this score is made up
Each dimension is scored out of 100 and combined into the headline score using fixed weights.
- MCP support
- 60 out of 100
- API quality
- 0 out of 100
- Documentation
- 15 out of 100
- Agent friendliness
- 41 out of 100
- Changelog
- 100 out of 100
- Marketing site structure
- 50 out of 100
- Operational trust
- 25 out of 100
Measured, but not part of the score
Useful to know, but not a mark for or against the product — so these do not affect the ranking.
- Openness
- 40 out of 100
- Maintenance
- 100 out of 100
This doesn’t look right — report a problem with Cherry Studio’s score
Alternatives in Chat Assistants
Ranked 1
77.1 — BenchRank score out of 100Browser Use
Browser Use · Open-source browser automation with hosted stealth browsers and agents
Best for: Teams building web automation that need hosted stealth browsers and agent APIs, plus an open-source library
Ranked 2
76.6 — BenchRank score out of 100LobeHub
LobeHub · Hosted multi-agent platform with a skills and MCP marketplace
Best for: Individuals and small teams wanting to run several AI agents on a hosted, credit-metered platform
Ranked 3
68.8 — BenchRank score out of 100Open WebUI
Open WebUI · Self-hosted interface for running local and cloud AI models
Best for: Teams that want to self-host one interface over local and cloud models on their own infrastructure.
