Zep - Build Agents That Recall What Matters

Observations: Patterns and Insights from the Context Graph

Observations are a new context type in Zep that capture patterns and insights across your Context Graphs, automatically discovered and surfaced to agents.

Zep's 5 Context Types: How to Use and Combine Each One

Zep produces five distinct types of context from a user's graph. Each captures something different. Here's when to reach for each, and how to combine them in one prompt.

Context You Can Trace, Filter, and Trust

Every fact in your agent's context graph came from somewhere. Zep's provenance architecture traces facts back to their source data — and lets you filter retrieval by origin.

Stop Letting Your Agent Decide What It Needs to Know

Your agent has the tools. It just doesn't call them — and smarter models won't fix that. Here's why the unknown unknowns problem is the hardest challenge in agent context, and what to do about it.

3 Decisions That Shape Every Agent's Context Architecture

Every agent context architecture comes down to three decisions: scope, data sources, and retrieval strategy. A framework for reasoning about persistent context for AI agents.

Evaluation and Control: Evaluation Framework, zepctl CLI, and Dashboard Overhaul

An evaluation framework for testing Zep against your data, a redesigned dashboard with analytics, and zepctl — a CLI for administering Zep projects.

Build Better Context Graphs: Custom Instructions, Search Filters, and Webhooks

Custom extraction instructions, property-level search filters, exclusion filters, and webhooks — more control over how you build and query context graphs.

Context Templates: Context Engineering Made Simple

Key Takeaways * Context templates let you declare what context an agent gets (user summary, edges, entities, episodes, with per-section limits and types) instead of writing sequential retrieval calls in code. * Save a template once and reference it by ID, so your context configuration is version-controlled and reproducible across agent calls

The Retrieval Tradeoff: What 50 Experiments Taught Us About Context Engineering

Key Takeaways * Context retrieval shows diminishing returns: moving from a 5/2 to a 20/20 configuration adds +10.4 points of accuracy at roughly 4x the tokens, while pushing on to 30/30 adds just 0.26. * Completeness, not accuracy, tells you whether retrieval is robust. At the minimal

How Zep Works: A Visual Guide to Knowledge Graphs for AI Agents

Key Takeaways * Agents don't fail because the model is weak; they fail because the right context isn't there. Chat memory only sees conversations, static RAG goes stale, tool calls are slow, and context stays scattered across systems. * Unified: Zep ingests any text source (chat messages, documents,

Building Voice Agents with Memory: Zep x LiveKit

Create personalized voice agents with long-term memory with minimal added latency

Agents That Always Remember What Matters

💡NEW User Summary Instructions: Zep now offers steerable user summaries. This post explores why these are useful and how best to implement them. Zep is a context engineering platform for AI agents built on a temporal knowledge graph that captures evolving user interactions and business data. On every chat turn,

Graphiti Hits 20K Stars! + MCP Server 1.0

Graphiti crossed 20,000 GitHub stars today! Thanks for building with us. Graphiti is a temporal knowledge graph that powers memory for AI agents. It's a foundational technology for Zep's context engineering platform. Over the past few months we've seen rapid adoption across startups

How We Scaled Zep 30x in 2 Weeks (and Made It Faster)

This summer, our largest enterprise customers landed all at once. Service usage increased 30x in two weeks. We went from handling thousands of hourly requests to millions overnight. Our infrastructure didn't just bend under the load. It broke. Hard. 😬 Context retrieval latency spiked from a P95 of 200ms

Zep v3: Context Engineering Takes Center Stage

Context is what makes or breaks agent applications. Early on, everyone focused on prompt engineering—tweaking the exact wording to get better responses. But as we've built more complex agents, it's become clear the real work is in context engineering: systematically assembling the right information around

Graphiti Adds FalkorDB Support as Project Approaches 14,000 Stars

The Graphiti community is hitting major milestones: nearly 14,000 GitHub stars in just eight months, with 35+ contributors and 25,000 weekly PyPI downloads. This growth reflects real developer adoption, much of it driven by the popularity of the Graphiti MCP server, which gives AI assistants powerful knowledge graph

What is Context Engineering, Anyway?

Working with large language models reveals an interesting shift in how we talk about making these systems work well. The term "prompt engineering" dominated early discussions, but you'll increasingly hear engineers talking about "context engineering" instead. This isn't just semantic drift. It&

The Private Agent Memory Fallacy

This is the first in a series of articles exploring the business of agents, data strategy in the AI era, and how companies and regulators should respond. The concept sounds compelling: a secure "wallet" for your personal AI memory. Your context (preferences, traits, and accumulated knowledge) travels seamlessly

Zep Q2 Feature Round-up

In Q2, we focused on expanding the flexibility of Zep's knowledge graph capabilities, improving observability, and making it easier to work with episodes and relationships. Here’s a look at the major features and improvements shipped this quarter. Custom Entity Types This release introduces support for custom entity

Stop Using RAG for Agent Memory

Based on my recent talk at the AI Engineer World's Faire, here's why you shouldn't be using RAG for memory—and what to do instead. The Problem: Agents That Forget I'm Daniel, founder of Zep AI. We build memory infrastructure for AI

Introducing Entity Types: Smarter, Structured Memory for Agents

Zep's new Entity Types let developers precisely structure and recall domain-specific information for more accurate, personalized agents.

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

Mem0 recently published research claiming to be the State-of-the-Art in Agent Memory, besting Zep. In reality, Zep outperforms Mem0 by 10% on their chosen benchmark. Why the discrepancy? We dig in to understand. 💡December 9, 2015: We've published new LoCoMo scores for Zep: 80% at <200ms latency.

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.

The One-Token Trick

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

Announcing a New Direction for Zep's Open Source Strategy

Ending support for Zep Community Edition to fully focus our open-source efforts on Graphiti