This is the Python SDK documentation. The SDK has been completely refactored to provide a modular, Backend-as-a-Service architecture for enterprise AI agent development.
Core Architecture
The SDK is built around five main modules:Backend
Agents Backend - Get framework specific arguments for AI agents.
Agents
Agent Management - Create, configure, and manage AI agents with tools, knowledge bases, and execution capabilities.
Tasks
Task Execution - Handle complex task workflows, execution management, and real-time streaming.
Tools Repository
Tools Integration - Register local tools, manage external integrations, and handle MCP servers.
Knowledge Bases
Knowledge Management - Create and search knowledge repositories with semantic search capabilities.
Events
Event Handling - Event-driven programming with decorators, real-time streaming, and background processing.
Installation
Key Features
- 🤖 Agent Management: Create, configure, and manage AI agents with comprehensive lifecycle control
- ⚡ Task Execution: Handle complex multi-step workflows with real-time event streaming
- 🔧 Tools Integration: Register local tools and integrate with external services via MCP
- 📚 Knowledge Bases: Semantic search across document repositories with AI-powered insights
- 🎯 Event-Driven: Event handling with decorators for responsive agent applications
- 🔄 Async/Sync Support: Both asynchronous and synchronous interfaces for flexibility
- 📊 Real-time Monitoring: Track agent performance, metrics, and execution in real-time
- 🏗️ Modular Architecture: Five independent modules that work seamlessly together
Quick Start Example
Asynchronous Usage
Synchronous Usage
Event-Driven Development
The SDK supports event-driven programming with decorators for task handling and lifecycle management:Asynchronous Usage
Synchronous Usage
Lifecycle Management
Module Documentation
Agents Module
Agent creation, management, and execution with tools and knowledge bases
Tasks Module
Task lifecycle management, execution control, and real-time streaming
Tools Repository
Local tool registration, external integrations, and MCP server management
Knowledge Bases
Document management and semantic search across knowledge repositories
Events Module
Event-driven programming, decorators, and background task processing
Configuration
SDK configuration, authentication, and environment setup
Types
Data types, enumerations, and models used across the SDK
Authentication
The SDK supports multiple authentication methods:- Environment Variables (Recommended)
- Explicit Configuration
- From File