Daniel Chalef
Defending Agent Memory Against Poisoning
One poisoned message, web page, or document can shape every later session that reads the same memory. Persistent memory makes prompt injection durable. We explain how memory poisoning works and which controls contain it, in your application and in Zep.
Why we built a graph database service for agent memory
Konig, Zep's graph database service, is the data plane beneath our agent memory platform. This post covers why we built it, how it works, and what we learned along the way.
Memory for every agent your team uses
A knowledge worker's agents don't share what they know: Claude and ChatGPT often can't reach company context, and the agents you build never see what Claude and ChatGPT learn. The Memory MCP Server gives each user one agent memory across all of them, governed by policy.
Evaluating Nemotron 3 Embed for agent memory
Zep's graph retrieval starts from entrypoints selected by semantic and BM25 search, so embedding recall bounds everything downstream. We benchmarked NVIDIA's Nemotron 3 Embed 1B, released today, on 5,954 production recall queries: first place against our production incumbent and two other models.
How Zep tracks provenance in agent memory
Agent memory is synthesized: an LLM derives facts from chat histories, documents, and business data. A derived fact matches no source word-for-word, so nothing ties it back to where it came from. Zep records that lineage; debugging, source-scoped retrieval, and compliance all depend on it.
Unified agent memory in any MCP client
Your team's agents are split across surfaces: the desktop assistant, the coding tool, the agents you build in-house. Each keeps its own memory or none at all. The Memory MCP Server puts them on one governed user graph, gated by your enterprise single sign-on.
Building Agents in Go Without a Framework
A production agent is a long-running, concurrent, I/O-bound process that spends most of its time waiting on a model, a tool, or a human. That shape fits Go's runtime. This post explains why, surveys the Go framework options, and shows how to build an agent without one.
Sycophancy is a design choice
Writer's "Recalling Too Well" paper says memory systems amplify sycophancy. Its own data traces the amplification to two design decisions — one in Writer's experiment itself, one in a competitor's memory product.
The Retrieval Tradeoff: What 50 Experiments Taught Us About Context Engineering
Zep builds temporal knowledge graphs from conversations and business data, then automatically retrieves relevant context when your agent needs it.
Graphiti Hits 20K Stars! + MCP Server 1.0
Graphiti crossed 20,000 GitHub stars today! Thanks for building with us.
How We Scaled Zep 30x in 2 Weeks (and Made It Faster)
Our infrastructure broke under 30x growth. Six weeks later, we made Zep faster than before: 10x better latency, 92% faster processing.
Zep v3: Context Engineering Takes Center Stage
Context engineering > prompt engineering: Zep v3 assembles memory & business data for agents that work.
Graphiti Adds FalkorDB Support as Project Approaches 14,000 Stars
FalkorDB contributes integration to Graphiti. Project approaching 14K stars & 25K weekly PyPI downloads.
What is Context Engineering, Anyway?
From Prompt Engineering to Context Engineering: The Why's and How.
The Private Agent Memory Fallacy
AI memory wallets sound appealing but face insurmountable economic, technical, and security challenges in practice.
Stop Using RAG for Agent Memory
Here's why you shouldn't be using RAG for agent memory—and what to do instead.
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 claims State-of-the-Art in Agent Memory, but Zep outperforms it by 24%. We unpack why.
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
Introducing Metered Billing and BYOC Deployments
Flexible, Scalable Pricing for High-Growth Companies and Enhanced Data Privacy for Enterprises
Cursor IDE: Adding Memory With Graphiti MCP 🤖⚡️
Upgrade Cursor with persistent memory using Graphiti MCP. Now your favorite AI coding agent remembers your preferences, standards, and specs across sessions.
Building a Memory Agent with the OpenAI Agents SDK and Zep
A video walkthrough demonstrating using Zep's agent memory and the new OpenAI Agents SDK to build an AI agent with long-term memory.
Zep Feature Retirements: May 2025
Several features will be retired after May 31, 2025. Read this post for important information on migrating to alternatives.
🎉 Big News! Graphiti is Launching on Product Hunt
Graphiti to launch on Product Hunt this Wednesday, February 19th!
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.
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.
December 2024 Round-up
Explore User and Group Graphs, Fact Ratings, and SOC 2 Type 2 Certification!
Building A Russian Election Interference Knowledge Graph
How we built a Knowledge Graph-based app for exploring Russian interference in the run-up to the 2024 US elections.
Exploring Russian Election Interference with a Knowledge Graph
We built a visual exploration tool and AI assistant for analyzing Russian interference in the run-up to the 2024 US elections.
Beyond Chat Memory: Making AI Interactions More Personal
Zep now connects user conversations and business data to help AI agents understand and serve users better.
Beyond Static Graphs: Engineering Evolving Relationships
Knowledge Graphs aren't adept at modeling changes in facts. This article explores the challenges we faced building time-aware Knowledge Graphs and our approaches to solving them.
Announcing: Zep Community Edition
Zep Community Edition, open-sourced today, is the first Zep product powered by a Knowledge Graph, allowing you to build more accurate and personalized Agents.
Graphiti: Temporal Knowledge Graphs for Agentic Apps
Graphiti builds dynamic, temporally aware knowledge graphs that represent complex, evolving relationships between entities over time.
Announcing: Zep Fact Ratings
Not all user Facts extracted by Zep are relevant to your application. Fact Ratings help Zep understand the relevance of a Fact to your use case.
Zep for Structured Outputs from Chat History (Video Walkthrough)
An end-to-end walkthrough demonstrating how to quickly and accurately extract data from chat histories stored in Zep.
Launching Structured Outputs from Chat History
Zep’s Structured Data Extraction is a high-accuracy tool for extracting data from chat histories. It's also 10x faster than gpt-4o.
Zep v0.17 - Summary Search and Enrichment, Scalability Improvements
Zep now supports searching chat history summaries helping developers provide rich, succinct context to LLMs.
Announcing Zep Archive: Records Retention and Right To Be Forgotten
Zep Simplifies LLM App Compliance with Data Privacy Regulations like GDPR and CCPA
HNSW Indexes and Custom Prompts!
Zep v0.13.0, released today, now includes support for HNSW indexes and the ability to set custom prompts for summarization tasks.
Announcing Zep's New Web Admin UI! 🔥🎉
View, edit, and delete Users, Sessions, and Collections. See complete message histories, data enrichments, and more.
ICYMI: Zep Vector DB, User Store, LlamaIndex support & more!
Wow, despite the great August weather in California 🌴☀️, we shipped a ton of good stuff 🚀. Here's the run-down in case you missed it.
Introducing the Zep User Store
Zep v0.11.0, released today, now includes a User Store. A User represents an individual interacting with your application.
Foundations of LLM App Building in TypeScript
Learn how to build three foundational LLM apps using TypeScript, LangChain.js, and Zep.
Announcing Anthropic Claude Support! 🎉
Zep v0.10.0, released today, supports Anthropic's Claude family of LLMs for summarization and extraction tasks.
Zep ❤️ LlamaIndex: A Vector Store Walkthrough
LlamaIndex is a simple but powerful framework for building LLM apps. It's also an excellent tool for populating and searching Zep's Vector Store. This walkthrough demonstrates using LlamaIndex's new ZepVectorStore to do just that.
Introducing the Zep Document Vector Store
With the addition of a Document Vector Store, Zep is now a single, batteries-included platform for grounding LLM apps with long-term memory.
ICYMI: Zep X Langchain, Session Metadata, and more 🔥⚡️
July was a busy month at Zep! Just in case you missed anything, here's a roundup.
Diagnosing and Fixing Slow Chatbots with LangSmith and Zep
Poor chatbot response times can result in frustrated users and churn. Langchain’s new LangSmith service makes it easy to diagnose the cause of latency in an LLM app. In this article, we use LangSmith to analyze a very slow Langchain app and improve performance by an order of magnitude using Zep.
Session Metadata 👾, Custom OpenAI Endpoints 🔧, & Kubernetes Deployment 🔥
Zep now includes support for adding arbitrary metadata to Sessions and more deployment options
Improved Langchain Support!
Langchain now includes improved support for Zep, with a new ZepMemory class, access to enriched messages, and more.
Goodbye Web Forms, Hello Chat Messages
A Guide to Using OpenAI Functions and Langchain to Extract Structured Data from LLM App Conversations
Semantic Similarity as an Intent Router for LLM Apps
Ensuring your LLM app understands user intent is crucial in offering a great experience. We build an intent router using Langchain, which automatically selects the prompt best suited to a task.
New Features: JWT Authentication, Azure OpenAI APIs, & Configurable Hard Deletion
Zep now supports JWT Authentication, Azure OpenAI APIs and OpenAI OrgIDs, and a configurable, periodic purge of soft-deleted data.
Introducing Intents
Zep's Intent Extractor identifies the intent of a message, persisting this to message metadata. 💡 With intent data, developers can build richer, more personalized agent interactions. 🔥
Introducing Open Source Embeddings! 🔥
Zep now has support for open source embedding models. Search your LLM App's chat history faster and more cheaply.
A Survey of Embedding Models (and why you should look beyond OpenAI)
User experience can be severely impacted when AI chat apps and agents are slow to respond. Embedding model performance can contribute to this problem. Is OpenAI's embedding API always the best fit?
Personalizing LLM Interactions: Harnessing Generative Feedback Loops
LLM Applications can be personalized using Generative Feedback Loops through advanced memory & personalization.
Introducing Zep Hybrid Search and Custom Metadata
Zep now supports both vector search over message text and filtering on message metadata, including system metadata such as Named Entities and creation dates.
LangchainJS Now Supports Zep!
LangchainJS now supports Zep Memory and Retrievers, allowing developers to take advantage of Zep's long-term memory, auto-summarization, vector search, and named entity extraction.
Announcing Zep's Entity Extractor!
Today we're launching Zep's EntityExtractor, a Named Entity Recognition tool built using state-of-the-art NLP toolkit, spaCy.
Introducing Zep: Long-term Memory Storage and Enrichment for AI Apps
Zep allows developers to focus on developing their AI apps, rather than building memory persistence, search, and enrichment infrastructure.
Sign up for Zep’s Newsletter
Writings on Zep, LLMs, and AI ecosystem tools.