> ## 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. # Feature Configs • AI Agent SDK > Feature Configuration Classes for PraisonAI Agents. # feature\_configs AI Agent Feature Configuration Classes for PraisonAI Agents. Provides dataclasses for consolidated feature configuration: * MemoryConfig: Memory and session management * KnowledgeConfig: RAG and knowledge retrieval * PlanningConfig: Planning mode settings * ReflectionConfig: Self-reflection settings * GuardrailConfig: Safety and validation * WebConfig: Web search and fetch All configs follow the agent-centric pattern: * False: Feature disabled (zero overhead) * True: Feature enabled with safe defaults * Config: Custom configuration * Instance: Pre-configured manager/engine Usage: from praisonaiagents import Agent, MemoryConfig, KnowledgeConfig # Simple enable agent = Agent(instructions="...", memory=True) # With config agent = Agent( instructions="...", memory=MemoryConfig(backend="redis", user\_id="user123"), knowledge=KnowledgeConfig(sources=\["docs/"], rerank=True), ) ## Import ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonaiagents.config import feature_configs ``` ## Classes Memory storage backends. Scope for learning data visibility. Configuration for continuous learning within memory system. Configuration for agent memory and session management. Knowledge chunking strategies. Configuration for RAG and knowledge retrieval. Configuration for planning mode. Configuration for self-reflection. Action to take when guardrail fails. Configuration for guardrails and safety validation. Web search providers. Configuration for web search and fetch capabilities. Output style presets. Configuration for agent output behavior. Execution mode presets. Configuration for agent execution limits. Configuration for prompt templates. Configuration for caching behavior. Configuration for agent hooks/callbacks. Configuration for agent skills. Configuration for multi-agent orchestration hooks/callbacks. Configuration for multi-agent output behavior. Configuration for multi-agent execution limits. Configuration for multi-agent planning mode. Configuration for multi-agent shared memory. Autonomy levels for agent behavior. ## Functions Resolve memory= parameter following precedence ladder. Resolve knowledge= parameter following precedence ladder. Resolve planning= parameter following precedence ladder. Resolve reflection= parameter following precedence ladder. Resolve guardrails= parameter following precedence ladder. Resolve web= parameter following precedence ladder. Resolve output= parameter following precedence ladder. Resolve execution= parameter following precedence ladder. Resolve caching= parameter following precedence ladder. Resolve autonomy= parameter following precedence ladder. *** ## Related Documentation