Cherry Studio
Cross-platform AI desktop client with multiple LLM providers, local model support, 300+ assistants, document and image handling, WebDAV backup, MCP server support, mini programs, and enterprise deployment options.
Open the source and read safety notes before installing.
Safety notes
- Cherry Studio is a desktop AI client that can connect to multiple cloud providers, local model servers, MCP servers, mini programs, document parsers, backup services, and enterprise backends; review each integration before adding sensitive data.
- MCP server support can expose model-callable tools. Only connect servers you trust, and scope file, shell, browser, SaaS, and write-capable tools carefully.
- Document and image processing can read local files and generate derived text, charts, summaries, or code blocks that may persist in app state or backups.
- WebDAV backup and sync can move local conversation or document state to a remote storage provider; verify endpoint, encryption, retention, and restore behavior.
- The README describes Enterprise Edition and private deployment options; confirm licensing, access control, data backup, and team management requirements before rollout.
Privacy notes
- Prompts, model responses, local documents, images, Office files, PDFs, assistant settings, topic history, MCP tool arguments, WebDAV backups, provider keys, and logs may contain sensitive data.
- Cloud model providers, AI web services, local model servers, MCP servers, WebDAV endpoints, mini programs, and enterprise services may receive data depending on configuration.
- Keep provider API keys, WebDAV credentials, enterprise endpoints, local model URLs, MCP config, document contents, and exported chats out of public prompts, screenshots, issues, and examples.
- For team use, define which models, assistants, MCP servers, backups, knowledge bases, and enterprise admin controls are approved.
Prerequisites
- Windows, macOS, or Linux desktop environment.
- Model provider credentials for cloud services, or local Ollama / LM Studio setup for local model use.
- A review of AGPL-3.0 community edition terms and any Enterprise Edition terms before organization-wide use.
- WebDAV credentials only if file backup and sync are needed.
- A reviewed MCP server list before connecting tools that can read files, call APIs, or mutate external systems.
Schema details
- Install type
- cli
- Troubleshooting
- No
- Scope
- Source repo
- Estimated setup
- 15 minutes
- Difficulty
- beginner
- Website
- https://cherryai.com
- Pricing
- freemium
- Disclosure
- editorial
- Application category
- DeveloperApplication
- Operating system
- Cross-platform
Full copyable content
Open https://github.com/CherryHQ/cherry-studio/releases
Download the release asset for Windows, macOS, or Linux.About this resource
Overview
Cherry Studio is a cross-platform AI desktop client for Windows, macOS, and Linux. It supports multiple LLM providers, local models through Ollama and LM Studio, more than 300 preconfigured assistants, custom assistants, multi-model conversations, document and image handling, Mermaid rendering, WebDAV file management and backup, mini programs, and MCP server support.
It is relevant for searches around Cherry Studio, Cherry Studio MCP, AI desktop client, local model desktop client, Ollama LM Studio client, AI assistants desktop app, MCP desktop client, Cherry Studio OpenClaw, and Cherry Studio Codex.
Install
Cherry Studio distributes desktop builds through GitHub Releases. Choose the
release asset for your operating system and verify it matches the official
CherryHQ/cherry-studio repository before installing.
Open https://github.com/CherryHQ/cherry-studio/releases
Download the release asset for Windows, macOS, or Linux.
For development builds, the repository is an Electron/Vite application with
Node.js 24.11.1 or newer declared in package.json, plus pnpm workspace tooling.
End users should normally start from release builds instead of local source
builds.
Core Capabilities
| Area | Cherry Studio Coverage |
|---|---|
| Desktop Client | Windows, macOS, and Linux AI productivity client |
| Providers | OpenAI, Gemini, Anthropic, Claude web service, Perplexity, Poe, and others documented in the README |
| Local Models | Ollama and LM Studio support |
| Assistants | 300+ preconfigured assistants and custom assistant creation |
| Conversations | Multi-model simultaneous conversations and topic management |
| Documents | Text, image, Office, PDF, Markdown, Mermaid, and code rendering features |
| Backup | WebDAV file management and backup support |
| MCP | MCP server support for connecting external tools |
| Extensions | Mini program support, roadmap plugin system, and theme ecosystem |
| Enterprise | Enterprise Edition with centralized model access, employees, shared knowledge base, access control, data backup, and private deployment positioning |
MCP and Agent Fit
Cherry Studio belongs in MCP and agent discovery because it is a desktop client where users can combine model providers, local models, assistants, documents, and MCP servers. The repository topics also align with Claude Code, Codex, OpenClaw, skills, Hermes Agent, and agent skills searches.
The operational boundary is client configuration. A desktop app that connects to many providers and MCP servers can quietly become a routing point for sensitive prompts, files, local model endpoints, external tools, and backup destinations.
Use Cases
- Use one desktop client for several cloud and local LLM providers.
- Compare outputs through multi-model conversations.
- Run assistant workflows over local documents, PDFs, images, and Office files.
- Connect local Ollama or LM Studio models without a browser-only workflow.
- Add selected MCP servers to an everyday desktop AI client.
- Back up or sync app data with a reviewed WebDAV endpoint.
- Evaluate a team-oriented desktop client before deciding whether Enterprise Edition features are needed.
Source Review
Verified on 2026-06-18:
- GitHub reports
CherryHQ/cherry-studioas an AGPL-3.0 repository with active development, 47,000+ stars, and latest releasev1.9.11. - The repository description presents Cherry Studio as an AI productivity studio with smart chat, autonomous agents, 300+ assistants, and unified access to frontier LLMs.
- The README describes Cherry Studio as a desktop client for Windows, Mac, and Linux with multiple LLM provider support.
- The README lists cloud LLM services, AI web service integration, local model support with Ollama and LM Studio, 300+ preconfigured assistants, custom assistants, multi-model simultaneous conversations, document/image/Office/PDF handling, WebDAV file management and backup, Mermaid chart visualization, global search, topic management, translation, mini programs, and MCP server support.
- The README documents a roadmap that includes MCP Marketplace, knowledge management, OCR, TTS, plugin system, ASR, and mobile/platform work.
- The README describes an Enterprise Edition with centralized model management, employee management, shared knowledge base, access control, data backup, and private deployment positioning.
package.jsonidentifies the project as a private Electron/Vite desktop app, declares Node.js>=24.11.1, and lists desktop build targets for Windows, macOS, and Linux.
Safety and Privacy
Cherry Studio can sit in the middle of many data flows: local files, model providers, local model servers, assistant definitions, MCP tools, WebDAV backup, mini programs, and enterprise services. Review those flows before importing private documents or enabling broad MCP servers.
For organizational use, decide whether the AGPL community edition, release builds, source builds, or Enterprise Edition are appropriate. Also define which providers, local servers, assistants, MCP servers, backups, and knowledge sources are approved.
Duplicate Check
Checked current content/tools/, content/mcp/, content/agents/,
content/skills/, guides, collections, README output, open pull requests, and
repository-wide content for CherryHQ/cherry-studio, Cherry Studio, Cherry
Studio MCP, Cherry Studio AI client, AI desktop client, local model desktop
client, Ollama LM Studio client, AI assistants desktop app, Cherry Studio
OpenClaw, Cherry Studio Codex, and MCP desktop client. Existing content only
mentions Cherry Studio as an MCP-compatible client in the TrendRadar MCP entry;
no dedicated Cherry Studio tools entry, exact source URL duplicate, target file,
or open duplicate PR was found.
Source citations
Add this badge to your README
Show that Cherry Studio is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/tools/cherry-studio)How it compares
Cherry Studio side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Cherry Studio Cross-platform AI desktop client with multiple LLM providers, local model support, 300+ assistants, document and image handling, WebDAV backup, MCP server support, mini programs, and enterprise deployment options. Open dossier | AnythingLLM Local-first AI application for private chat, document RAG, workspace agents, MCP-compatible tools, model routing, memories, scheduled tasks, multimodal workflows, multi-user Docker deployments, and self-hosted agent automation. Open dossier | Cua Computer-Use Agents MIT-licensed infrastructure for computer-use agents: background desktop drivers, MCP server support, Python SDKs, local/cloud sandboxes, macOS, Windows, Linux, Android, Cua Bench, GUI automation skills, and Lume virtualization for agents that see, click, type, and verify real desktops. Open dossier | Hermes Agent Nous Research AI agent with terminal UI, messaging gateway, skills, memory, MCP integration, scheduled automations, subagents, terminal backends, OpenClaw migration, model switching, and persistent cross-session workflows. Open dossier |
|---|---|---|---|---|
| Trust | ||||
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Category | tools | tools | tools | tools |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | CherryHQ | Mintplex Labs | TryCua | Nous Research |
| Added | 2026-06-18 | 2026-06-18 | 2026-06-18 | 2026-06-18 |
| Platforms | CLI | CLI | CLI | CodexCLI |
| Source repo | — | — | — | — |
| Safety notes | ✓Cherry Studio is a desktop AI client that can connect to multiple cloud providers, local model servers, MCP servers, mini programs, document parsers, backup services, and enterprise backends; review each integration before adding sensitive data. MCP server support can expose model-callable tools. Only connect servers you trust, and scope file, shell, browser, SaaS, and write-capable tools carefully. Document and image processing can read local files and generate derived text, charts, summaries, or code blocks that may persist in app state or backups. WebDAV backup and sync can move local conversation or document state to a remote storage provider; verify endpoint, encryption, retention, and restore behavior. The README describes Enterprise Edition and private deployment options; confirm licensing, access control, data backup, and team management requirements before rollout. | ✓AnythingLLM can run agents, scheduled tasks, MCP-compatible tools, browser-like workspace actions, developer APIs, and external model calls; scope tools and credentials before enabling them for users. The upstream Docker guide includes examples that add the SYS_ADMIN capability to the container. Review whether that capability is acceptable for the host before copying production run commands. Multi-user Docker deployments need normal production controls: authentication, TLS, network isolation, secret management, persistent-volume ownership, backups, and upgrade planning. Agent tools, custom agents, model routing, memories, and scheduled tasks can change behavior over time; use least privilege, logging, review gates, and rollback plans for write-capable workflows. Localhost services such as Ollama, Chroma, LocalAI, or LM Studio may need Docker host routing adjustments; avoid exposing local provider ports wider than intended. | ✓Cua can give agents eyes and hands on a computer: screenshots, clicks, typing, dragging, shell commands, window control, file paths, and desktop automation. Treat it as high-impact automation. The README documents remote shell and PowerShell installer commands for Cua Driver and Lume. Review script contents, pin versions where possible, and avoid blind execution on sensitive machines. The GUI automation skill includes form fuzzing examples and shell/file actions; use only on authorized apps, test environments, or isolated sandboxes. Host-machine mode and background desktop control can interact with real apps without stealing focus. Keep host consent, allowlists, window targeting, and stop controls explicit. Cua Bench, Cua sandboxes, Lume, Docker, QEMU, cloud VMs, Windows sandbox, Android images, and BYOI environments need resource limits, cleanup, network policy, and credential isolation. Optional third-party components have separate license and safety implications; the README calls out Kasm, OmniParser, and optional `cua-agent[omni]` dependencies. | ✓Hermes Agent can run tools, shell commands, terminal sessions, scheduled jobs, subagents, skills, MCP servers, messaging gateways, and remote backends; review permissions before using it on sensitive systems. The README documents one-line shell installers for some platforms. Inspect installer scripts and prefer isolated package installs or disposable environments when evaluating the agent. OpenClaw migration can import settings, memories, skills, command allowlists, messaging settings, API keys, audio assets, and workspace instructions; use dry-run and non-secret presets before migrating real profiles. Scheduled automations and messaging gateways can run unattended and deliver results to external chat systems, so restrict allowed users, home directories, credentials, and write-capable tools. Terminal backends such as local shell, Docker, SSH, Singularity, Modal, and Daytona can touch local files, containers, remote hosts, cloud sandboxes, and GPU infrastructure. |
| Privacy notes | ✓Prompts, model responses, local documents, images, Office files, PDFs, assistant settings, topic history, MCP tool arguments, WebDAV backups, provider keys, and logs may contain sensitive data. Cloud model providers, AI web services, local model servers, MCP servers, WebDAV endpoints, mini programs, and enterprise services may receive data depending on configuration. Keep provider API keys, WebDAV credentials, enterprise endpoints, local model URLs, MCP config, document contents, and exported chats out of public prompts, screenshots, issues, and examples. For team use, define which models, assistants, MCP servers, backups, knowledge bases, and enterprise admin controls are approved. | ✓Uploaded documents, parsed chunks, embeddings, workspace memories, prompts, chat history, agent state, scheduled task inputs, MCP payloads, provider responses, logs, and API calls may contain sensitive data. The README documents anonymous telemetry and an opt-out through DISABLE_TELEMETRY=true or the in-app privacy setting; review this before using regulated or confidential data. Even with telemetry disabled, outbound calls may still go to configured LLMs, embedding models, vector databases, external tools, cdn.anythingllm.com, GitHub, or GitHubusercontent depending on the deployment. Keep provider keys, JWT secrets, workspace invite links, storage paths, private documents, and generated citations out of public prompts, screenshots, issues, and examples. | ✓Computer-use sessions can capture screenshots, typed text, window titles, app contents, browser pages, files, clipboard-like content, shell output, paths, downloads, and user workflows. Cua trajectories are recorded under `~/.cua/trajectories/...`; sharing trajectories can upload or expose screenshots, actions, commands, and replayable workflow details. Cloud sandboxes, Cua cloud, E2B-like backends, Docker registries, Lume images, MCP clients, model providers, and AI annotation features may process or store prompts, screenshots, tool actions, and environment metadata. Do not use host or cloud computer-control flows on confidential documents, customer systems, authenticated browser sessions, secrets, payments, destructive admin panels, or regulated data unless policy explicitly allows it. | ✓Conversation history, memory files, user profiles, skill outputs, session search indexes, tool arguments, tool results, model responses, gateway messages, audio transcripts, and logs may contain sensitive data. Model providers, messaging platforms, search/image/TTS/browser tool gateways, MCP servers, and remote terminal backends may receive prompts, files, commands, account identifiers, or generated outputs depending on configuration. OpenClaw migration may copy memories, persona files, skills, API keys, messaging settings, command allowlists, TTS assets, and workspace instructions into the Hermes profile. Keep provider keys, bot tokens, OAuth grants, migrated secrets, workspace paths, generated summaries, and session search data out of public prompts, screenshots, issues, and examples. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | — | — | — | — |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Featured in
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.