What is Context Engineering?
Context Engineering assembles relevant information around an LLM for reliable task completion. Unlike basic prompting, it dynamically integrates user preferences, conversation history, and business data.
Agents often fail due to missing personalized context. Zep solves this by automatically creating temporal knowledge graphs to organize and retrieve context for each interaction through Agent Memory, Graph RAG, and automated context assembly.
Three Lines of Code to Production
Skip building complex infrastructure. Add personalized context to your agents in minutes.
# Add conversation to memory
zep.memory.add(session_id, messages)
# Get relevant context
memory = zep.memory.get(session_id)
context = memory.contextBuilt for Developer Experience
Production-ready tools and comprehensive documentation to get you building personalized agents fast.
SDKs & APIs
Documentation
Popular Integration Patterns
Real-world examples of how developers integrate Zep into their applications and workflows.
LangGraph Integration
Use Zep as an agentic tool to search for facts in user graphs within LangGraph workflows.
View GuideAutogen Memory
Enhanced memory capabilities for Autogen multi-agent applications with persistent context.
View GuideChainlit Integration
Build conversational AI applications with memory and context using Chainlit frameworks.
View Guide
