> ## Documentation Index > Fetch the complete documentation index at: https://docs.praison.ai/llms.txt > Use this file to discover all available pages before exploring further. # praisonaiagents SDK > Documentation for the praisonaiagents package - Core agent framework # Module praisonaiagents The `praisonaiagents` package provides a lightweight, high-performance framework for building AI agents with support for multi-agent orchestration, memory, knowledge bases, and tool integration. ## Quick Start ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonaiagents import Agent agent = Agent(instructions="You are a helpful assistant") response = agent.start("Hello!") print(response) ``` ## Core Modules Core agent class for AI interactions Multi-agent orchestration Task definition and management Task execution flows ## Agent Variants Vision and image processing Intelligent request routing Multi-step research with citations Query optimization for RAG Prompt enhancement Context-aware processing ## Data & Memory Memory management for stateful agents Knowledge base and RAG support Session management and persistence Database adapters and storage State checkpointing Context management ## Tools & Integration Tool system and decorators Model Context Protocol support Agent-to-agent handoffs Multi-step workflow execution Agent Skills standard support LLM configuration and providers ## Safety & Control Input/output validation Planning mode support Policy-based controls Human-in-the-loop approval Extended thinking support Context compaction ## Observability Observability and monitoring Event hooks and callbacks Console display utilities Agent evaluation framework Data classes for task outputs Workflow visualization ## UI & Output UI components (AGUI, A2A) Output formatting Language Server Protocol Background task execution ## Import Patterns The SDK supports multiple import styles for different use cases: ### Simple Import (Recommended for Quick Start) ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonaiagents import Agent, AgentTeam, Task, tool, Tools ``` ### Organized Imports (Recommended for Projects) For larger projects, use sub-package imports for cleaner code organization: ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # Core classes from root from praisonaiagents import Agent, AgentTeam, Task # Configuration from config sub-package from praisonaiagents import MemoryConfig, OutputConfig, ExecutionConfig # Tools from tools sub-package from praisonaiagents import tool, BaseTool, Tools # Memory from memory sub-package from praisonaiagents import Memory, FileMemory # Workflows from workflows sub-package from praisonaiagents import AgentFlow, Pipeline, Route, Parallel ``` ### Namespace Style Use the `pa.` namespace for exploratory development: ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} import praisonaiagents as pa agent = pa.Agent(instructions="...") config = pa.config.MemoryConfig(user_id="u123") memory = pa.memory.Memory(config=config) ``` ### Backwards Compatibility All legacy imports continue to work via lazy loading: ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # These all work (backwards compatible) from praisonaiagents import MemoryConfig # via __getattr__ from praisonaiagents import AgentFlow # via __getattr__ from praisonaiagents import Memory # via __getattr__ ``` ### Sub-Packages Reference | Sub-Package | Key Exports | Description | | --------------------------- | ------------------------------------------------------------------------- | ----------------------------- | | `praisonaiagents.config` | `MemoryConfig`, `OutputConfig`, `ExecutionConfig`, `PlanningConfig`, etc. | Feature configuration classes | | `praisonaiagents.tools` | `tool`, `BaseTool`, `Tools`, `ToolResult`, `FunctionTool` | Tool creation and management | | `praisonaiagents.memory` | `Memory`, `FileMemory`, `RulesManager` | Memory and persistence | | `praisonaiagents.workflows` | `Workflow`, `Pipeline`, `Route`, `Parallel`, `Loop` | Workflow orchestration | ## Installation ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # Core package pip install praisonaiagents # With memory support pip install "praisonaiagents[memory]" # With knowledge/RAG support pip install "praisonaiagents[knowledge]" # With MCP support pip install "praisonaiagents[mcp]" ``` ## See Also * [SDK Reference](/docs/sdk/index) * [Agent Module](/docs/sdk/praisonaiagents/agent/agent) * [Quickstart Guide](/docs/quickstart)