# YourGPT Copilot SDK Documentation > Build AI copilots with app context awareness. Multi-provider LLM support, streaming, tools, and beautiful UI components. ## Documentation - [Deploy](https://copilot-sdk.yourgpt.ai/docs/deploy): Deploy your Copilot backend to any platform - [Examples](https://copilot-sdk.yourgpt.ai/docs/examples): Real-world Copilot SDK implementations - [Generative UI](https://copilot-sdk.yourgpt.ai/docs/generative-ui): Render rich React components from AI tool results — per-tool custom renderers or AI-driven built-in components - [Getting Started](https://copilot-sdk.yourgpt.ai/docs/getting-started): Get up and running in 2 minutes - [Introduction](https://copilot-sdk.yourgpt.ai/docs): Production-ready AI Copilots for any product. Connect any LLM, deploy on your infrastructure, own your data. Built for speed and control. - [Overview](https://copilot-sdk.yourgpt.ai/docs/overview): What is Copilot SDK - [Playground](https://copilot-sdk.yourgpt.ai/docs/playground): Interactive sandbox to experiment with Copilot SDK features - [Why Copilot SDK](https://copilot-sdk.yourgpt.ai/docs/why-copilot-sdk): Build production-ready AI copilots in minutes, not months. Self-hosted, enterprise-grade, zero lock-in. - [Conversation Branching](https://copilot-sdk.yourgpt.ai/docs/advanced/branching): Edit messages to create parallel conversation paths, just like ChatGPT and Claude.ai - [Message History Compaction](https://copilot-sdk.yourgpt.ai/docs/advanced/compaction): Auto-summarize old messages to keep long conversations within the AI's context window - [Token Tracking](https://copilot-sdk.yourgpt.ai/docs/advanced/token-tracking): Monitor context window usage in real time with useContextStats - [Chat](https://copilot-sdk.yourgpt.ai/docs/api-reference/chat): Chat UI component and customization - [Core](https://copilot-sdk.yourgpt.ai/docs/api-reference/core): Core utilities, built-in tools, and types - [API Reference](https://copilot-sdk.yourgpt.ai/docs/api-reference): Complete API documentation - [Attachments](https://copilot-sdk.yourgpt.ai/docs/chat/attachments): Send images, PDFs, and files alongside chat messages - [Chat](https://copilot-sdk.yourgpt.ai/docs/chat): Pre-built chat component - [Storage](https://copilot-sdk.yourgpt.ai/docs/chat/storage): Persist chat sessions, threads, and conversation history across reloads and devices - [Copilot UI](https://copilot-sdk.yourgpt.ai/docs/chat/ui): Pre-built chat components and styling setup - [UI Primitives](https://copilot-sdk.yourgpt.ai/docs/customizations/chat-primitives): Headless building blocks for composing fully custom chat UIs - [CSS Class Reference](https://copilot-sdk.yourgpt.ai/docs/customizations/css-classes): Complete list of all csdk-* CSS classes exposed by the SDK for targeting and customization - [Custom Message View](https://copilot-sdk.yourgpt.ai/docs/customizations/custom-message-view): Full control over how the message list is rendered via the messageView prop - [Headless Copilot](https://copilot-sdk.yourgpt.ai/docs/customizations/headless): Build fully custom chat UIs using raw SDK primitives — no built-in components required - [Customizations](https://copilot-sdk.yourgpt.ai/docs/customizations): Create custom themes, extend components, and brand your copilot - [Headless Copilot](https://copilot-sdk.yourgpt.ai/docs/headless): Build fully custom chat UIs using raw SDK primitives — no built-in components required - [useCopilotEvent](https://copilot-sdk.yourgpt.ai/docs/headless/use-copilot-event): Subscribe to raw stream chunks as they arrive — build any custom real-time UI - [useMessageMeta](https://copilot-sdk.yourgpt.ai/docs/headless/use-message-meta): Reactive per-message custom metadata — attach any data to a message ID and react to changes - [generateText()](https://copilot-sdk.yourgpt.ai/docs/llm-sdk/generate-text): Generate complete text responses - [Overview](https://copilot-sdk.yourgpt.ai/docs/llm-sdk): Unified API for any LLM provider - [streamText()](https://copilot-sdk.yourgpt.ai/docs/llm-sdk/stream-text): Stream text responses in real-time - [tool()](https://copilot-sdk.yourgpt.ai/docs/llm-sdk/tools): Define type-safe tools with Zod schemas - [Anthropic](https://copilot-sdk.yourgpt.ai/docs/providers/anthropic): Use Claude 3.5 Sonnet, Claude 3 Opus, and more - [Custom Provider](https://copilot-sdk.yourgpt.ai/docs/providers/custom-provider): Build your own LLM provider adapter - [Fallback](https://copilot-sdk.yourgpt.ai/docs/providers/fallback): Automatic failover and load distribution across LLM providers - [Fireworks](https://copilot-sdk.yourgpt.ai/docs/providers/fireworks): Fast open-source model inference — Llama, DeepSeek, Qwen, Mixtral and more - [Google (Gemini)](https://copilot-sdk.yourgpt.ai/docs/providers/google): Use Gemini 2.0, Gemini 1.5 Pro, and Flash models - [Providers Overview](https://copilot-sdk.yourgpt.ai/docs/providers): Connect to any LLM provider - [Ollama](https://copilot-sdk.yourgpt.ai/docs/providers/ollama): Run LLMs locally with no API keys - [OpenAI](https://copilot-sdk.yourgpt.ai/docs/providers/openai): Use GPT-4o, GPT-4, and GPT-3.5 models - [OpenRouter](https://copilot-sdk.yourgpt.ai/docs/providers/openrouter): Access 500+ models from any provider through a single API key - [Together AI](https://copilot-sdk.yourgpt.ai/docs/providers/togetherai): Cost-effective open-source model inference — Llama, DeepSeek, Qwen, Gemma and more - [xAI](https://copilot-sdk.yourgpt.ai/docs/providers/xai): Ultra-fast inference with Grok models - [Deployment](https://copilot-sdk.yourgpt.ai/docs/server/deployment): Deploy your Copilot backend to any platform - [Server Setup](https://copilot-sdk.yourgpt.ai/docs/server): Configure your backend API for the Copilot SDK - [Storage & Persistence](https://copilot-sdk.yourgpt.ai/docs/server/storage): Automatic session creation and message persistence with pluggable storage adapters - [Client-side Skills](https://copilot-sdk.yourgpt.ai/docs/skills/client): Register skills from React components using SkillProvider and useSkill - [Skills](https://copilot-sdk.yourgpt.ai/docs/skills): Instruction playbooks that shape the AI's behavior — loaded on demand - [Server-side Skills](https://copilot-sdk.yourgpt.ai/docs/skills/server): Load skills from files and URLs on the server with loadSkills() - [Multi-Step](https://copilot-sdk.yourgpt.ai/docs/tools/agentic-loop): Multi-step AI reasoning with continuous tool calls - [Server Tools](https://copilot-sdk.yourgpt.ai/docs/tools/backend-tools): Execute tools securely on the server with full API access - [Client Tools](https://copilot-sdk.yourgpt.ai/docs/tools/frontend-tools): Build client-side tools that run in the browser - [Tools](https://copilot-sdk.yourgpt.ai/docs/tools): Give the AI capabilities in your app - [MCP Integration](https://copilot-sdk.yourgpt.ai/docs/tools/mcp): Connect to MCP servers and use their tools in your app - [Angular](https://copilot-sdk.yourgpt.ai/docs/api-reference/frameworks/angular): Angular integration - [Vue](https://copilot-sdk.yourgpt.ai/docs/api-reference/frameworks/vue): Vue.js integration - [Components](https://copilot-sdk.yourgpt.ai/docs/api-reference/react/components): React components and providers - [Hooks](https://copilot-sdk.yourgpt.ai/docs/api-reference/react/hooks): React hooks for chat state and tools - [React](https://copilot-sdk.yourgpt.ai/docs/api-reference/react): React hooks, provider, and components - [Console Logs](https://copilot-sdk.yourgpt.ai/docs/tools/built-in/console): Give AI access to console output for debugging - [Built-in Tools](https://copilot-sdk.yourgpt.ai/docs/tools/built-in): Ready-to-use tools for common AI capabilities - [Screenshot](https://copilot-sdk.yourgpt.ai/docs/tools/built-in/screenshot): Capture viewport for visual context - [Web Search](https://copilot-sdk.yourgpt.ai/docs/tools/built-in/web-search): Real-time web search capabilities for your AI copilot --- ## Quick Links - [GitHub](https://github.com/YourGPT/copilot-sdk) - [NPM: @yourgpt/copilot-sdk](https://www.npmjs.com/package/@yourgpt/copilot-sdk) - [NPM: @yourgpt/llm-sdk](https://www.npmjs.com/package/@yourgpt/llm-sdk)