Features
OpenUI Lang – compact line-oriented language up to 67% more token-efficient than JSON
Streaming-first UI rendering – renders progressively as model responds
Cross-platform support: React, React Native, Vue
Define custom component libraries via defineComponent and createLibrary
Automatic system prompt generation from component definitions
Reactive state, queries, and mutations wired to tools
Safe by default – model only composes registered components
Live data integration via MCP servers and custom tools
Supports all major LLMs (OpenAI, Anthropic, Gemini, Mistral, xAI, DeepSeek)
Compatible with agent frameworks (Vercel AI SDK, LangChain, CrewAI, OpenAI Agents SDK)
Built-in component libraries (ShadCN, Material Design, DaisyUI, Base UI)
Editable artifact generation (PPTX, PDF, reports, dashboards) in OpenUI Cloud
Output validation and error correction in Cloud tier
Observability and audit trail in Cloud tier
@ai_fn decorator for LLM-powered Python functions
@ai_classifier decorator for text classification
Structured data extraction via Pydantic models
Agent loops with tool calling and function calling
Built-in streaming (SSE) support
Async-first API for concurrent applications
Rate limiting and automatic retries
LLM response caching for performance
Concurrency control for workload management
CLI tool for monitoring and debugging
SQLite state store for persistence
OpenAI and Anthropic model support
Embeddings generation for semantic search
Local execution with no cloud dependency
Self-hosted deployable as a library
