Introducing Zep Agent Skills! Read the announcement. →
Zep

Preston Rasmussen

Portrait of Preston Rasmussen
Member of Technical Staff, Zep

8 posts

Context graphs

Your agent's context is only as precise as your entity types

In a flat ontology, entity types must not overlap, so each kind of record gets either a broad type or a specific type. Type hierarchies let a parent type contain its subtypes, so each entity or fact gets a broad type and the most specific subtype that fits. They are now generally available.

Benchmarks and evaluation

Lies, Damn Lies, & Statistics: Is Mem0 Really SOTA in Agent Memory?

Mem0 claims State-of-the-Art in Agent Memory, but Zep outperforms it by 24%. We unpack why.

Benchmarks and evaluation

GPT-4.1 and o4-mini: Is OpenAI Overselling Long-Context?

We put OpenAI’s latest models through the LongMemEval benchmark—here’s why raw context size alone isn't enough.

Retrieval

The One-Token Trick

How single-token LLM requests can improve RAG search at minimal cost and latency.

Benchmarks and evaluation

Zep Is The New State of the Art In Agent Memory

Setting a new standard for agent memory with up to 100% accuracy gains and 90% lower latency.

Agent memory

Zep: A Temporal Knowledge Graph Architecture for Agent Memory

We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art systems.

Retrieval

How do you search a Knowledge Graph?

Can you build graph search that's both elegant & powerful? Here's how we did it in Graphiti, Zep's open source temporal Knowledge Graph library.

Graphiti

Scaling LLM Data Extraction: Challenges, Design decisions, and Solutions

How we made building Knowledge Graphs faster and more dynamic

Sign up for Zep’s Newsletter

Writings on Zep, LLMs, and AI ecosystem tools.

No spam. Unsubscribe anytime.