SDK Reference

PraisonAI SDK documentation - Classes, modules, and functions

SDK Reference

Complete SDK documentation for PraisonAI packages. This section covers all classes, modules, and functions available in the SDK.

Packages

praisonaiagents

Core agent framework with Agent, Task, Process, Memory, and more

praisonai

High-level wrapper with CLI, auto-generation, and deployment utilities

TypeScript SDK

TypeScript/JavaScript SDK for Node.js and browser environments

Quick Start

from praisonaiagents import Agent

agent = Agent(instructions="You are a helpful assistant")
response = agent.start("Hello!")
print(response)

Quick Links

Core Modules

Module	Description
Agent	Core agent class for AI interactions
Agents	Multi-agent orchestration
Task	Task definition and management
Process	Task execution flows

Agent Variants

Module	Description
ImageAgent	Vision and image processing agent
RouterAgent	Intelligent request routing
DeepResearchAgent	Multi-step research with citations
QueryRewriterAgent	Query optimization for RAG
PromptExpanderAgent	Prompt enhancement
ContextAgent	Context-aware processing

Data & Memory

Module	Description
Memory	Memory management for stateful agents
Knowledge	Knowledge base and RAG support
Session	Session management and persistence
DB	Database adapters and storage
Checkpoints	State checkpointing

Tools & Integration

Module	Description
Tools	Tool system and decorators
MCP	Model Context Protocol support
Handoff	Agent-to-agent handoffs
Workflows	Multi-step workflow execution
Skills	Agent Skills standard support

Safety & Control

Module	Description
Guardrails	Input/output validation
Planning	Planning mode support
Policy	Policy-based controls
Approval	Human-in-the-loop approval
Thinking	Extended thinking support

Observability

Module	Description
Telemetry	Observability and monitoring
Hooks	Event hooks and callbacks
Display	Console display utilities
Eval	Agent evaluation framework

praisonai Wrapper

Module	Description
PraisonAI	Main wrapper class
CLI	Command-line interface
Auto	Automated agent generation
Deploy	Deployment utilities
Scheduler	Task scheduling

Installation

# Core agents package
pip install praisonaiagents

# With memory support
pip install "praisonaiagents[memory]"

# With knowledge/RAG support
pip install "praisonaiagents[knowledge]"

# Full wrapper with all features
pip install "praisonai[all]"

See Also

• praisonaiagents Overview
• TypeScript SDK
• Quickstart Guide