# Repository: CherryHQ/cherry-studio # Stars: 43672 ## CLAUDE.md # AI Assistant Guide This file provides guidance to AI coding assistants when working with code in this repository. Adherence to these guidelines is crucial for maintaining code quality and consistency. ## Guiding Principles (MUST FOLLOW) - **Keep it clear**: Write code that is easy to read, maintain, and explain. - **Match the house style**: Reuse existing patterns, naming, and conventions. - **Search smart**: Prefer `ast-grep` for semantic queries; fall back to `rg`/`grep` when needed. - **Log centrally**: Route all logging through `loggerService` with the right context—no `console.log`. - **Research via subagent**: Lean on `subagent` for external docs, APIs, news, and references. - **Always propose before executing**: Before making any changes, clearly explain your planned approach and wait for explicit user approval to ensure alignment and prevent unwanted modifications. - **Lint, test, and format before completion**: Coding tasks are only complete after running `pnpm lint`, `pnpm test`, and `pnpm format` successfully. - **Write conventional commits**: Commit small, focused changes using Conventional Commit messages (e.g., `feat:`, `fix:`, `refactor:`, `docs:`). - **Sign commits**: Use `git commit --signoff` as required by contributor guidelines. ## Pull Request Workflow (CRITICAL) When creating a Pull Request, you MUST use the `gh-create-pr` skill. If the skill is unavailable, directly read `.agents/skills/gh-create-pr/SKILL.md` and follow it manually. ## Review Workflow When reviewing a Pull Request, do NOT run `pnpm lint`, `pnpm test`, or `pnpm format` locally. Instead, check CI status directly using GitHub CLI: - **Check CI status**: `gh pr checks ` - View all CI check results for the PR - **Check PR details**: `gh pr view ` - View PR status, reviews, and merge readiness - **View failed logs**: `gh run view --log-failed` - Inspect logs for failed CI runs Only investigate CI failures by reading the logs, not by re-running checks locally. ## Issue Workflow When creating an Issue, you MUST use the `gh-create-issue` skill. If the skill is unavailable, directly read `.agents/skills/gh-create-issue/SKILL.md` and follow it manually. ### Branch Strategy (Effective April 3, 2026) > **IMPORTANT**: The `main` branch is now under **code freeze**. Only critical bug fixes submitted via `hotfix/*` branches are accepted. Fix PRs must be minimal in scope and must not include any refactoring code. > > All new features, refactoring, and optimizations should be developed on the **`v2` branch**. We welcome every developer to actively participate in v2 development! > > The `v2` branch will only accept new feature submissions after all current features have been fully refactored. ## Development Commands - **Install**: `pnpm install` — Install all project dependencies (requires Node ≥22, pnpm 10.27.0) - **Development**: `pnpm dev` — Runs Electron app in development mode with hot reload - **Debug**: `pnpm debug` — Starts with debugging; attach via `chrome://inspect` on port 9222 - **Build Check**: `pnpm build:check` — **REQUIRED** before commits (`pnpm lint && pnpm test`) - If having i18n sort issues, run `pnpm i18n:sync` first - If having formatting issues, run `pnpm format` first - **Full Build**: `pnpm build` — TypeScript typecheck + electron-vite build - **Test**: `pnpm test` — Run all Vitest tests (main + renderer + aiCore + shared + scripts) - `pnpm test:main` — Main process tests only (Node environment) - `pnpm test:renderer` — Renderer process tests only (jsdom environment) - `pnpm test:aicore` — aiCore package tests only - `pnpm test:watch` — Watch mode - `pnpm test:coverage` — With v8 coverage report - `pnpm test:e2e` — Playwright end-to-end tests - **Lint**: `pnpm lint` — oxlint + eslint fix + TypeScript typecheck + i18n check + format check - **Format**: `pnpm format` — Biome format + lint (write mode) - **Typecheck**: `pnpm typecheck` — Concurrent node + web TypeScript checks using `tsgo` - **i18n**: - `pnpm i18n:sync` — Sync i18n template keys - `pnpm i18n:translate` — Auto-translate missing keys - `pnpm i18n:check` — Validate i18n completeness - **Bundle Analysis**: `pnpm analyze:renderer` / `pnpm analyze:main` — Visualize bundle sizes - **Agents DB**: - `pnpm agents:generate` — Generate Drizzle migrations - `pnpm agents:push` — Push schema to SQLite DB - `pnpm agents:studio` — Open Drizzle Studio ## Project Architecture ### Electron Structure ``` src/ main/ # Node.js backend (Electron main process) renderer/ # React UI (Electron renderer process) preload/ # Secure IPC bridge (contextBridge) packages/ aiCore/ # @cherrystudio/ai-core — AI SDK middleware & provider abstraction shared/ # Cross-process types, constants, IPC channel definitions mcp-trace/ # OpenTelemetry tracing for MCP operations ai-sdk-provider/ # Custom AI SDK provider implementations extension-table-plus/ # TipTap table extension ``` ### Key Path Aliases | Alias | Resolves To | |---|---| | `@main` | `src/main/` | | `@renderer` | `src/renderer/src/` | | `@shared` | `packages/shared/` | | `@types` | `src/renderer/src/types/` | | `@logger` | `src/main/services/LoggerService` (main) / `src/renderer/src/services/LoggerService` (renderer) | | `@mcp-trace/trace-core` | `packages/mcp-trace/trace-core/` | | `@cherrystudio/ai-core` | `packages/aiCore/src/` | ### Main Process (`src/main/`) Node.js backend services. Key services: | Service | Responsibility | |---|---| | `WindowService` | Electron window lifecycle management | | `MCPService` | Model Context Protocol server management | | `KnowledgeService` | RAG / knowledge base (via `@cherrystudio/embedjs`) | | `AnthropicService` | Anthropic API integration | | `LoggerService` | Winston-based structured logging (daily rotate) | | `StoreSyncService` | Syncs Redux state to/from main process | | `BackupManager` | Data backup/restore (WebDAV, S3, Nutstore) | | `ApiServerService` | Express HTTP API server (Swagger docs at `/api-docs`) | | `AppUpdater` | electron-updater auto-update | | `ShortcutService` | Global keyboard shortcuts | | `ThemeService` | System theme detection/application | | `SelectionService` | Text selection toolbar feature | | `CopilotService` | GitHub Copilot OAuth integration | | `PythonService` | Pyodide WASM Python runtime | | `OvmsManager` | OpenVINO model server management | | `NodeTraceService` | OpenTelemetry trace export | Agents subsystem (`src/main/services/agents/`): - Drizzle ORM + LibSQL (SQLite) schema at `database/schema/index.ts` - Migrations in `resources/database/drizzle/` - **Currently undergoing v2 refactor** — only critical bug fixes accepted ### Renderer Process (`src/renderer/src/`) React 19 + Redux Toolkit SPA. Key structure: ``` aiCore/ # Legacy middleware pipeline (deprecated, migrating to packages/aiCore) api/ # IPC call wrappers (typed electron API calls) components/ # Shared UI components (Ant Design 5 + styled-components + TailwindCSS v4) databases/ # Dexie (IndexedDB) — topics, files, message_blocks, etc. hooks/ # React hooks (useAssistant, useChatContext, useModel, etc.) pages/ # Route pages (home, settings, knowledge, paintings, notes, etc.) services/ # Frontend services (ApiService, ModelService, MemoryService, etc.) store/ # Redux Toolkit slices types/ # TypeScript type definitions workers/ # Web Workers windows/ # Multi-window entry points (mini, selection toolbar, trace) ``` ### Redux Store (`src/renderer/src/store/`) Slices (redux-persist enabled): | Slice | State | |---|---| | `assistants` | AI assistant configurations | | `settings` | App-wide settings | | `llm` | LLM provider/model configs | | `mcp` | MCP server configs | | `messageBlock` | Message block rendering state | | `knowledge` | Knowledge base entries | | `paintings` | Image generation state | | `memory` | Memory system config | | `websearch` | Web search settings | | `shortcuts` | Keyboard shortcuts | | `tabs` | Tab management | > **BLOCKED**: Do not add new Redux slices or change existing state shape until v2.0.0. ### Database Layer - **IndexedDB** (Dexie): `src/renderer/src/databases/index.ts` - Tables: `files`, `topics`, `settings`, `knowledge_notes`, `translate_history`, `quick_phrases`, `message_blocks`, `translate_languages` - Schema versioned with upgrade functions (`upgradeToV5`, `upgradeToV7`, `upgradeToV8`) - **BLOCKED**: Do not modify schema until v2.0.0. - **SQLite** (Drizzle ORM + LibSQL): `src/main/services/agents/` - Used for the agents subsystem - DB path: `{userData}/Data/agents.db` (e.g., on macOS: `~/Library/Application Support/CherryStudioDev/Data/agents.db` in dev, `~/Library/Application Support/CherryStudio/Data/agents.db` in prod) ### IPC Communication - Channel constants defined in `packages/shared/IpcChannel.ts` - Renderer → Main: `ipcRenderer.invoke(IpcChannel.XXX, ...args)` via `api.*` wrappers in `src/preload/index.ts` - Main → Renderer: `webContents.send(channel, data)` - Tracing: `tracedInvoke()` in preload attaches OpenTelemetry span context to IPC calls - Typed API surface exposed via `contextBridge` as `window.api` ### AI Core (`packages/aiCore/`) The `@cherrystudio/ai-core` package abstracts AI SDK providers: ``` src/core/ providers/ # Provider registry (HubProvider, factory, registry) middleware/ # LanguageModelV2Middleware pipeline (manager, wrapper) plugins/ # Built-in plugins runtime/ # Runtime execution options/ # Request option preparation ``` - Built on Vercel AI SDK v5 (`ai` package) with `LanguageModelV2Middleware` - `HubProvider` aggregates multiple provider backends - Supports: OpenAI, Anthropic, Google, Azure, Mistral, Bedrock, Vertex, Ollama, Perplexity, xAI, HuggingFace, Cerebras, OpenRouter, Copilot, and more - Custom fork of openai package: `@cherrystudio/openai` ### Multi-Window Architecture The renderer builds multiple HTML entry points: - `index.html` — Main application window - `miniWindow.html` — Compact floating window (`src/renderer/src/windows/mini/`) - `selectionToolbar.html` — Text selection action toolbar - `selectionAction.html` — Selection action popup - `traceWindow.html` — MCP trace viewer ### Logging ```typescript import { loggerService } from "@logger"; const logger = loggerService.withContext("moduleName"); // Renderer only: loggerService.initWindowSource('windowName') first logger.info("message", CONTEXT); logger.warn("message"); logger.error("message", error); ``` - Backend: Winston with daily log rotation - Log files in `userData/logs/` - Never use `console.log` — always use `loggerService` ### Tracing (OpenTelemetry) - `packages/mcp-trace/` provides trace-core and trace-node/trace-web adapters - `NodeTraceService` exports spans via OTLP HTTP - `SpanCacheService` caches span entities for the trace viewer window - IPC calls can carry span context via `tracedInvoke()` ## Tech Stack | Layer | Technologies | |---|---| | Runtime | Electron 38, Node ≥22 | | Frontend | React 19, TypeScript ~5.8 | | UI | Ant Design 5.27, styled-components 6, TailwindCSS v4 | | State | Redux Toolkit, redux-persist, Dexie (IndexedDB) | | Rich Text | TipTap 3.2 (with Yjs collaboration) | | AI SDK | Vercel AI SDK v5 (`ai`), `@cherrystudio/ai-core` | | Build | electron-vite 5 with rolldown-vite 7 (experimental) | | Test | Vitest 3 (unit), Playwright (e2e) | | Lint/Format | ESLint 9, oxlint, Biome 2 | | DB (main) | Drizzle ORM + LibSQL (SQLite) | | DB (renderer) | Dexie (IndexedDB) | | Logging | Winston + winston-daily-rotate-file | | Tracing | OpenTelemetry | | i18n | i18next + react-i18next | ## Conventions ### TypeScript - Strict mode enabled; use `tsgo` (native TypeScript compiler preview) for typechecking - Separate configs: `tsconfig.node.json` (main), `tsconfig.web.json` (renderer) - Type definitions centralized in `src/renderer/src/types/` and `packages/shared/` ### Code Style - Biome handles formatting (2-space indent, single quotes, trailing commas) - oxlint + ESLint for linting; `simple-import-sort` enforces import order - React hooks: `eslint-plugin-react-hooks` enforced - No unused imports: `eslint-plugin-unused-imports` ### File Naming - React components: `PascalCase.tsx` - Services, hooks, utilities: `camelCase.ts` - Test files: `*.test.ts` or `*.spec.ts` alongside source or in `__tests__/` subdirectory ### i18n - All user-visible strings must use `i18next` — never hardcode UI strings - Run `pnpm i18n:check` to validate; `pnpm i18n:sync` to add missing keys - Locale files in `src/renderer/src/i18n/` ### Packages with Custom Patches Several dependencies have patches in `patches/` — be careful when upgrading: - `antd`, `@ai-sdk/google`, `@ai-sdk/openai`, `@anthropic-ai/vertex-sdk` - `@google/genai`, `@langchain/core`, `@langchain/openai` - `ollama-ai-provider-v2`, `electron-updater`, `epub`, `tesseract.js` - `@anthropic-ai/claude-agent-sdk` ## Testing Guidelines - Tests use Vitest 3 with project-based configuration - Main process tests: Node environment, `tests/main.setup.ts` - Renderer tests: jsdom environment, `tests/renderer.setup.ts`, `@testing-library/react` - aiCore tests: separate `packages/aiCore/vitest.config.ts` - All tests run without CI dependency (fully local) - Coverage via v8 provider (`pnpm test:coverage`) - **Features without tests are not considered complete** ## Important Notes ### V2 Refactoring in Progress The `main` branch is under code freeze. All development has moved to the `v2` branch. - **`main` branch**: Only accepts critical bug fixes via `hotfix/*` branches. Minimal changes, no refactoring. - **`v2` branch**: All new features, refactoring, and optimizations go here. Files marked with the following header are **blocked for feature changes**: ```typescript /** * @deprecated Scheduled for removal in v2.0.0 * ⚠️ NOTICE: V2 DATA&UI REFACTORING * STOP: Feature PRs affecting this file are currently BLOCKED. */ ``` Do not introduce new features to these files. Bug fixes only. ### Security - Never expose Node.js APIs directly to renderer; use `contextBridge` in preload - Validate all IPC inputs in main process handlers - URL sanitization via `strict-url-sanitise` - IP validation via `ipaddr.js` (API server) - `express-validator` for API server request validation ## README.md
🌐 Language

banner

English | 中文 | Official Site | Documents | Development | Feedback

[![][deepwiki-shield]][deepwiki-link] [![][twitter-shield]][twitter-link] [![][discord-shield]][discord-link] [![][telegram-shield]][telegram-link]
[![][github-release-shield]][github-release-link] [![][github-nightly-shield]][github-nightly-link] [![][github-contributors-shield]][github-contributors-link] [![][license-shield]][license-link] [![][commercial-shield]][commercial-link] [![][sponsor-shield]][sponsor-link]
Featured｜HelloGitHub CherryHQ%2Fcherry-studio | Trendshift Cherry Studio - AI Chatbots, AI Desktop Client | Product Hunt
# 🍒 Cherry Studio Cherry Studio is a desktop client that supports multiple LLM providers, available on Windows, Mac and Linux. 👏 Join [Telegram Group](https://t.me/CherryStudioAI)｜[Discord](https://discord.gg/wez8HtpxqQ) | [QQ Group(575014769)](https://qm.qq.com/q/lo0D4qVZKi) ❤️ Like Cherry Studio? Give it a star 🌟 or [Sponsor](docs/zh/guides/sponsor.md) to support the development! # 🌠 Screenshot ![](https://github.com/user-attachments/assets/36dddb2c-e0fb-4a5f-9411-91447bab6e18) ![](https://github.com/user-attachments/assets/f549e8a0-2385-40b4-b52b-2039e39f2930) ![](https://github.com/user-attachments/assets/58e0237c-4d36-40de-b428-53051d982026) # 🌟 Key Features 1. **Diverse LLM Provider Support**: - ☁️ Major LLM Cloud Services: OpenAI, Gemini, Anthropic, and more - 🔗 AI Web Service Integration: Claude, Perplexity, [Poe](https://poe.com/), and others - 💻 Local Model Support with Ollama, LM Studio 2. **AI Assistants & Conversations**: - 📚 300+ Pre-configured AI Assistants - 🤖 Custom Assistant Creation - 💬 Multi-model Simultaneous Conversations 3. **Document & Data Processing**: - 📄 Supports Text, Images, Office, PDF, and more - ☁️ WebDAV File Management and Backup - 📊 Mermaid Chart Visualization - 💻 Code Syntax Highlighting 4. **Practical Tools Integration**: - 🔍 Global Search Functionality - 📝 Topic Management System - 🔤 AI-powered Translation - 🎯 Drag-and-drop Sorting - 🔌 Mini Program Support - ⚙️ MCP(Model Context Protocol) Server 5. **Enhanced User Experience**: - 🖥️ Cross-platform Support for Windows, Mac, and Linux - 📦 Ready to Use - No Environment Setup Required - 🎨 Light/Dark Themes and Transparent Window - 📝 Complete Markdown Rendering - 🤲 Easy Content Sharing # 📝 Roadmap We're actively working on the following features and improvements: 1. 🎯 **Core Features** - Selection Assistant with smart content selection enhancement - Deep Research with advanced research capabilities - Memory System with global context awareness - Document Preprocessing with improved document handling - MCP Marketplace for Model Context Protocol ecosystem 2. 🗂 **Knowledge Management** - Notes and Collections - Dynamic Canvas visualization - OCR capabilities - TTS (Text-to-Speech) support 3. 📱 **Platform Support** - HarmonyOS Edition (PC) - Android App (Phase 1) - iOS App (Phase 1) - Multi-Window support - Window Pinning functionality - Intel AI PC (Core Ultra) Support 4. 🔌 **Advanced Features** - Plugin System - ASR (Automatic Speech Recognition) - Assistant and Topic Interaction Refactoring Track our progress and contribute on our [project board](https://github.com/orgs/CherryHQ/projects/7). Want to influence our roadmap? Join our [GitHub Discussions](https://github.com/CherryHQ/cherry-studio/discussions) to share your ideas and feedback! # 🌈 Theme - Theme Gallery: - Aero Theme: - PaperMaterial Theme: - Claude dynamic-style: - Maple Neon Theme: Welcome PR for more themes # 🤝 Contributing We welcome contributions to Cherry Studio! Here are some ways you can contribute: 1. **Contribute Code**: Develop new features or optimize existing code. 2. **Fix Bugs**: Submit fixes for any bugs you find. 3. **Maintain Issues**: Help manage GitHub issues. 4. **Product Design**: Participate in design discussions. 5. **Write Documentation**: Improve user manuals and guides. 6. **Community Engagement**: Join discussions and help users. 7. **Promote Usage**: Spread the word about Cherry Studio. Refer to the [Branching Strategy](docs/en/guides/branching-strategy.md) for contribution guidelines ## Getting Started 1. **Fork the Repository**: Fork and clone it to your local machine. 2. **Create a Branch**: For your changes. 3. **Submit Changes**: Commit and push your changes. 4. **Open a Pull Request**: Describe your changes and reasons. For more detailed guidelines, please refer to our [Contributing Guide](CONTRIBUTING.md). Thank you for your support and contributions! # 🔧 Developer Co-creation Program We are launching the Cherry Studio Developer Co-creation Program to foster a healthy and positive-feedback loop within the open-source ecosystem. We believe that great software is built collaboratively, and every merged pull request breathes new life into the project. We sincerely invite you to join our ranks of contributors and shape the future of Cherry Studio with us. ## Contributor Rewards Program To give back to our core contributors and create a virtuous cycle, we have established the following long-term incentive plan. **The inaugural tracking period for this program will be Q3 2025 (July, August, September). Rewards for this cycle will be distributed on October 1st.** Within any tracking period (e.g., July 1st to September 30th for the first cycle), any developer who contributes more than **30 meaningful commits** to any of Cherry Studio's open-source projects on GitHub will be eligible for the following benefits: - **Cursor Subscription Sponsorship**: Receive a **$70 USD** credit or reimbursement for your [Cursor](https://cursor.sh/) subscription, making AI your most efficient coding partner. - **Unlimited Model Access**: Get **unlimited** API calls for the **DeepSeek** and **Qwen** models. - **Cutting-Edge Tech Access**: Enjoy occasional perks, including API access to models like **Claude**, **Gemini**, and **OpenAI**, keeping you at the forefront of technology. ## Growing Together & Future Plans A vibrant community is the driving force behind any sustainable open-source project. As Cherry Studio grows, so will our rewards program. We are committed to continuously aligning our benefits with the best-in-class tools and resources in the industry. This ensures our core contributors receive meaningful support, creating a positive cycle where developers, the community, and the project grow together. **Moving forward, the project will also embrace an increasingly open stance to give back to the entire open-source community.** ## How to Get Started? We look forward to your first Pull Request! You can start by exploring our repositories, picking up a `good first issue`, or proposing your own enhancements. Every commit is a testament to the spirit of open source. Thank you for your interest and contributions. Let's build together. # 🏢 Enterprise Edition Building on the Community Edition, we are proud to introduce **Cherry Studio Enterprise Edition**—a privately-deployable AI productivity and management platform designed for modern teams and enterprises. The Enterprise Edition addresses core challenges in team collaboration by centralizing the management of AI resources, knowledge, and data. It empowers organizations to enhance efficiency, foster innovation, and ensure compliance, all while maintaining 100% control over their data in a secure environment. ## Core Advantages - **Unified Model Management**: Centrally integrate and manage various cloud-based LLMs (e.g., OpenAI, Anthropic, Google Gemini) and locally deployed private models. Employees can use them out-of-the-box without individual configuration. - **Enterprise-Grade Knowledge Base**: Build, manage, and share team-wide knowledge bases. Ensures knowledge retention and consistency, enabling team members to interact with AI based on unified and accurate information. - **Fine-Grained Access Control**: Easily manage employee accounts and assign role-based permissions for different models, knowledge bases, and features through a unified admin backend. - **Fully Private Deployment**: Deploy the entire backend service on your on-premises servers or private cloud, ensuring your data remains 100% private and under your control to meet the strictest security and compliance standards. - **Reliable Backend Services**: Provides stable API services and enterprise-grade data backup and recovery mechanisms to ensure business continuity. ## ✨ Online Demo **🔗 [Cherry Studio Enterprise](https://enterprise.cherry-ai.com)** ## Version Comparison | Feature | Community Edition | Enterprise Edition | | :---------------- | :----------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------- | | **Open Source** | ✅ Yes | ⭕️ Partially released to customers | | **Cost** | [AGPL-3.0 License](https://github.com/CherryHQ/cherry-studio?tab=AGPL-3.0-1-ov-file) | Buyout / Subscription Fee | | **Admin Backend** | — | ● Centralized **Model** Access
● **Employee** Management
● Shared **Knowledge Base**
● **Access** Control
● **Data** Backup | | **Server** | — | ✅ Dedicated Private Deployment | ## Get the Enterprise Edition We believe the Enterprise Edition will become your team's AI productivity engine. If you are interested in Cherry Studio Enterprise Edition and would like to learn more, request a quote, or schedule a demo, please feel free to contact us. - **For Business Inquiries & Purchasing**: **📧 [bd@cherry-ai.com](mailto:bd@cherry-ai.com)** # 🔗 Related Projects - [new-api](https://github.com/QuantumNous/new-api): The next-generation LLM gateway and AI asset management system supports multiple languages. - [one-api](https://github.com/songquanpeng/one-api): LLM API management and distribution system supporting mainstream models like OpenAI, Azure, and Anthropic. Features a unified API interface, suitable for key management and secondary distribution. - [Poe](https://poe.com/): Poe gives you access to the best AI, all in one place. Explore GPT-5, Claude Opus 4.1, DeepSeek-R1, Veo 3, ElevenLabs, and millions of others. - [ublacklist](https://github.com/iorate/ublacklist): Blocks specific sites from appearing in Google search results # 🚀 Contributors

# 📊 GitHub Stats ![Stats](https://repobeats.axiom.co/api/embed/a693f2e5f773eed620f70031e974552156c7f397.svg "Repobeats analytics image") # ⭐️ Star History Star History Chart # 📜 License The Cherry Studio Community Edition is governed by the standard GNU Affero General Public License v3.0 (AGPL-3.0), available at https://www.gnu.org/licenses/agpl-3.0.html. Use of the Cherry Studio Community Edition for commercial purposes is permitted, subject to full compliance with the terms and conditions of the AGPL-3.0 license. Should you require a commercial license that provides an exemption from the AGPL-3.0 requirements, please contact us at bd@cherry-ai.com. [deepwiki-shield]: https://img.shields.io/badge/Deepwiki-CherryHQ-0088CC?logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNy45MyAzMiI+PHBhdGggZD0iTTE5LjMzIDE0LjEyYy42Ny0uMzkgMS41LS4zOSAyLjE4IDBsMS43NCAxYy4wNi4wMy4xMS4wNi4xOC4wN2guMDRjLjA2LjAzLjEyLjAzLjE4LjAzaC4wMmMuMDYgMCAuMTEgMCAuMTctLjAyaC4wM2MuMDYtLjAyLjEyLS4wNS4xNy0uMDhoLjAybDMuNDgtMi4wMWMuMjUtLjE0LjQtLjQxLjQtLjdWOC40YS44MS44MSAwIDAgMC0uNC0uN2wtMy40OC0yLjAxYS44My44MyAwIDAgMC0uODEgMEwxOS43NyA3LjdoLS4wMWwtLjE1LjEyLS4wMi4wMnMtLjA3LjA5LS4xLjE0VjhhLjQuNCAwIDAgMC0uMDguMTd2LjA0Yy0uMDMuMDYtLjAzLjEyLS4wMy4xOXYyLjAxYzAgLjc4LS40MSAxLjQ5LTEuMDkgMS44OC0uNjcuMzktMS41LjM5LTIuMTggMGwtMS43NC0xYS42LjYgMCAwIDAtLjIxLS4wOGMtLjA2LS4wMS0uMTItLjAyLS4xOC0uMDJoLS4wM2MtLjA2IDAtLjExLjAxLS4xNy4wMmgtLjAzYy0uMDYuMDItLjEyLjA0LS4xNy4wN2gtLjAybC0zLjQ3IDIuMDFjLS4yNS4xNC0uNC40MS0uNC43VjE4YzAgLjI5LjE1LjU1LjQuN2wzLjQ4IDIuMDFoLjAyYy4wNi4wNC4xMS4wNi4xNy4wOGguMDNjLjA1LjAyLjExLjAzLjE3LjAzaC4wMmMuMDYgMCAuMTIgMCAuMTgtLjAyaC4wNGMuMDYtLjAzLjEyLS4wNS4xOC0uMDhsMS43NC0xYy42Ny0uMzkgMS41LS4zOSAyLjE3IDBzMS4wOSAxLjExIDEuMDkgMS44OHYyLjAxYzAgLjA3IDAgLjEzLjAyLjE5di4wNGMuMDMuMDYuMDUuMTIuMDguMTd2LjAycy4wOC4wOS4xMi4xM2wuMDIuMDJzLjA5LjA4LjE1LjExYzAgMCAuMDEgMCAuMDEuMDFsMy40OCAyLjAxYy4yNS4xNC41Ni4xNC44MSAwbDMuNDgtMi4wMWMuMjUtLjE0LjQtLjQxLjQtLjd2LTQuMDFhLjgxLjgxIDAgMCAwLS40LS43bC0zLjQ4LTIuMDFoLS4wMmMtLjA1LS4wNC0uMTEtLjA2LS4xNy0uMDhoLS4wM2EuNS41IDAgMCAwLS4xNy0uMDNoLS4wM2MtLjA2IDAtLjEyIDAtLjE4LjAyLS4wNy4wMi0uMTUuMDUtLjIxLjA4bC0xLjc0IDFjLS42Ny4zOS0xLjUuMzktMi4xNyAwYTIuMTkgMi4xOSAwIDAgMS0xLjA5LTEuODhjMC0uNzguNDItMS40OSAxLjA5LTEuODhaIiBzdHlsZT0iZmlsbDojNWRiZjlkIi8+PHBhdGggZD0ibS40IDEzLjExIDMuNDcgMi4wMWMuMjUuMTQuNTYuMTQuOCAwbDMuNDctMi4wMWguMDFsLjE1LS4xMi4wMi0uMDJzLjA3LS4wOS4xLS4xNGwuMDItLjAyYy4wMy0uMDUuMDUtLjExLjA3LS4xN3YtLjA0Yy4wMy0uMDYuMDMtLjEyLjAzLS4xOVYxMC40YzAtLjc4LjQyLTEuNDkgMS4wOS0xLjg4czEuNS0uMzkgMi4xOCAwbDEuNzQgMWMuMDcuMDQuMTQuMDcuMjEuMDguMDYuMDEuMTIuMDIuMTguMDJoLjAzYy4wNiAwIC4xMS0uMDEuMTctLjAyaC4wM2MuMDYtLjAyLjEyLS4wNC4xNy0uMDdoLjAybDMuNDctMi4wMmMuMjUtLjE0LjQtLjQxLjQtLjd2LTRhLjgxLjgxIDAgMCAwLS40LS43bC0zLjQ2LTJhLjgzLjgzIDAgMCAwLS44MSAwbC0zLjQ4IDIuMDFoLS4wMWwtLjE1LjEyLS4wMi4wMi0uMS4xMy0uMDIuMDJjLS4wMy4wNS0uMDUuMTEtLjA3LjE3di4wNGMtLjAzLjA2LS4wMy4xMi0uMDMuMTl2Mi4wMWMwIC43OC0uNDIgMS40OS0xLjA5IDEuODhzLTEuNS4zOS0yLjE4IDBsLTEuNzQtMWEuNi42IDAgMCAwLS4yMS0uMDhjLS4wNi0uMDEtLjEyLS4wMi0uMTgtLjAyaC0uMDNjLS4wNiAwLS4xMS4wMS0uMTcuMDJoLS4wM2MtLjA2LjAyLS4xMi4wNS0uMTcuMDhoLS4wMkwuNCA3LjcxYy0uMjUuMTQtLjQuNDEtLjQuNjl2NC4wMWMwIC4yOS4xNS41Ni40LjciIHN0eWxlPSJmaWxsOiM0NDY4YzQiLz48cGF0aCBkPSJtMTcuODQgMjQuNDgtMy40OC0yLjAxaC0uMDJjLS4wNS0uMDQtLjExLS4wNi0uMTctLjA4aC0uMDNhLjUuNSAwIDAgMC0uMTctLjAzaC0uMDNjLS4wNiAwLS4xMiAwLS4xOC4wMmgtLjA0Yy0uMDYuMDMtLjEyLjA1LS4xOC4wOGwtMS43NCAxYy0uNjcuMzktMS41LjM5LTIuMTggMGEyLjE5IDIuMTkgMCAwIDEtMS4wOS0xLjg4di0yLjAxYzAtLjA2IDAtLjEzLS4wMi0uMTl2LS4wNGMtLjAzLS4wNi0uMDUtLjExLS4wOC0uMTdsLS4wMi0uMDJzLS4wNi0uMDktLjEtLjEzTDguMjkgMTlzLS4wOS0uMDgtLjE1LS4xMWgtLjAxbC0zLjQ3LTIuMDJhLjgzLjgzIDAgMCAwLS44MSAwTC4zNyAxOC44OGEuODcuODcgMCAwIDAtLjM3LjcxdjQuMDFjMCAuMjkuMTUuNTUuNC43bDMuNDcgMi4wMWguMDJjLjA1LjA0LjExLjA2LjE3LjA4aC4wM2MuMDUuMDIuMTEuMDMuMTYuMDNoLjAzYy4wNiAwIC4xMiAwIC4xOC0uMDJoLjA0Yy4wNi0uMDMuMTItLjA1LjE4LS4wOGwxLjc0LTFjLjY3LS4zOSAxLjUtLjM5IDIuMTcgMHMxLjA5IDEuMTEgMS4wOSAxLjg4djIuMDFjMCAuMDcgMCAuMTMuMDIuMTl2LjA0Yy4wMy4wNi4wNS4xMS4wOC4xN2wuMDIuMDJzLjA2LjA5LjEuMTRsLjAyLjAycy4wOS4wOC4xNS4xMWguMDFsMy40OCAyLjAyYy4yNS4xNC41Ni4xNC44MSAwbDMuNDgtMi4wMWMuMjUtLjE0LjQtLjQxLjQtLjdWMjUuMmEuODEuODEgMCAwIDAtLjQtLjdaIiBzdHlsZT0iZmlsbDojNDI5M2Q5Ii8+PC9zdmc+ [deepwiki-link]: https://deepwiki.com/CherryHQ/cherry-studio [twitter-shield]: https://img.shields.io/badge/Twitter-CherryStudioApp-0088CC?logo=x [twitter-link]: https://twitter.com/CherryStudioHQ [discord-shield]: https://img.shields.io/badge/Discord-@CherryStudio-0088CC?logo=discord [discord-link]: https://discord.gg/wez8HtpxqQ [telegram-shield]: https://img.shields.io/badge/Telegram-@CherryStudioAI-0088CC?logo=telegram [telegram-link]: https://t.me/CherryStudioAI [github-release-shield]: https://img.shields.io/github/v/release/CherryHQ/cherry-studio?logo=github [github-release-link]: https://github.com/CherryHQ/cherry-studio/releases [github-nightly-shield]: https://img.shields.io/github/actions/workflow/status/CherryHQ/cherry-studio/nightly-build.yml?label=nightly%20build&logo=github [github-nightly-link]: https://github.com/CherryHQ/cherry-studio/actions/workflows/nightly-build.yml [github-contributors-shield]: https://img.shields.io/github/contributors/CherryHQ/cherry-studio?logo=github [github-contributors-link]: https://github.com/CherryHQ/cherry-studio/graphs/contributors [license-shield]: https://img.shields.io/badge/License-AGPLv3-important.svg?logo=gnu [license-link]: https://www.gnu.org/licenses/agpl-3.0 [commercial-shield]: https://img.shields.io/badge/License-Contact-white.svg?logoColor=white&logo=telegram&color=blue [commercial-link]: mailto:license@cherry-ai.com?subject=Commercial%20License%20Inquiry [sponsor-shield]: https://img.shields.io/badge/Sponsor-FF6699.svg?logo=githubsponsors&logoColor=white [sponsor-link]: https://github.com/CherryHQ/cherry-studio/blob/main/docs/sponsor.md