Website Source
Zep combines agent memory, Graph RAG, and context assembly capabilities to deliver comprehensive personalized context that reduces hallucinations and improves accuracy.
- Knowledge Graph: Zep’s unified knowledge store for agents. Nodes represent entities, edges represent facts/relationships. The graph updates dynamically in response to new data. Docs
- Zep’s Context Block: Optimized string containing a user summary and facts from the knowledge graph most relevant to the current thread. Also contains dates when facts became valid and invalid. Provide this to your chatbot as “memory”. Docs
- Fact Invalidation: When new data invalidates a prior fact, the time the fact became invalid is stored on that fact’s edge in the knowledge graph. Docs
- JSON/text/message: Types of data that can be ingested into the knowledge graph. Can represent business data, documents, chat messages, emails, etc. Docs
- Custom Entity/Edge Types: Feature allowing use of Pydantic-like classes to customize creation/retrieval of entities and relations in the knowledge graph. Docs
- Graph: Represents an arbitrary knowledge graph for storing up-to-date knowledge about an object or system. For storing up-to-date knowledge about a user, a user graph should be used. Docs
- User Graph: Special type of graph for storing personalized memory for a user of your application. Docs
- User: A user in Zep represents a user of your application, and has its own User Graph and thread history. Docs
- Threads: Conversation threads of a user. By default, all messages added to any thread of that user are ingested into that user’s graph. Docs
graph.add & thread.add_messages: Methods for adding data to a graph and user graph respectively. Docs Docsgraph.search & thread.get_user_context: Low level and high level methods respectively for retrieving from the knowledge graph. Docs Docs- User Summary Instructions: Customize how Zep generates entity summaries for users in their knowledge graph. Up to 5 custom instructions per user to guide summary generation. Docs
- Agentic Tool: Use Zep’s memory retrieval methods as agentic tools, enabling your agent to query for relevant information from the user’s knowledge graph. Docs
Tags:
backend
ai
cloud
Last modified 15 January 2026