> ## Documentation Index > Fetch the complete documentation index at: https://praison.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Session • AI Agent SDK > Session: A simple wrapper around PraisonAI's existing stateful capabilities. # Session > Defined in the [**session**](../modules/session) module. AI Agent A simple wrapper around PraisonAI's existing stateful capabilities. Provides a unified API for: * Session management with persistent state * Memory operations (short-term, long-term, user-specific) * Knowledge base operations * Agent state management * Remote agent connectivity ## Constructor No description available. No description available. No description available. No description available. No description available. No description available. ## Methods Lazy-loaded memory instance Lazy-loaded knowledge instance Create an agent with session context. Backward compatibility wrapper for Agent method Save session state data to memory. Restore session state from memory. Get a specific state value Set a specific state value Increment a numeric state value Add information to session memory. Search session memory. Add knowledge source to session. Search session knowledge base. Clear session memory. Build context from session memory and knowledge. Send a message to the remote agent or handle local session. Alias for chat() method to match Google ADK pattern. ## Usage ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # Local session with agent session = Session(session_id="chat_123", user_id="user_456") agent = session.Agent(name="Assistant", role="Helpful AI") # Remote agent session (similar to Google ADK) session = Session(agent_url="192.168.1.10:8000/agent") response = session.chat("Hello from remote client!") # Save session state session.save_state({"conversation_topic": "AI research"}) ``` ## Source `praisonaiagents/session.py` at line 23 *** ## Related Documentation