Features
Multimodal AI agents (text, images, audio, URLs)
Structured JSON generation from any schema
Serverless long-term memory stores (encrypted, persistent)
Serverless knowledge stores (RAG from files & websites)
Custom functions from your code
Google Search integration
Real-time streaming responses (text & voice)
Voice input & output sub-300ms
LLM output validation with retries
Built-in encryption for memory stores
Full type-safety (TypeScript)
Client and server SDKs (@scoopika/react, etc.)
Scalable global edge (26 regions)
Decorator-based LLM call pattern (@llm.call)
Automatic versioning with @ops.version
Tracing and cost tracking per call via @ops.trace
Built-in tool calling with @llm.tool
Agent loop with tool execution and response resume
Streaming response support
Thinking/reasoning with include_thoughts parameter
OpenTelemetry integration for observability
Structured output via Python type hints
Multi-provider support (OpenAI, Anthropic, Google)
Lightweight, minimal abstraction design
Provider-agnostic unified interface
Simple tool creation with function decorators
Cost tracking per interaction
GitHub open-source (MIT license)
