Features
Register existing React components for agent use
Automatic component selection and prop streaming
Generative components (one-shot) and interactable components (persistent)
Built-in agent – no external LLM framework required
Streaming and state management
Conversation history and message threads
Error states, cancellation, and loading handling
MCP (Model Context Protocol) support
User authentication integration (inherits user permissions)
Tools system for custom actions
Analytics and observability
Component library included
Self-hostable backend (open-source)
@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
