Zep blog

Announcing Zep Agent Skills
Zep Agent Skills turns your agent's runs into verified procedures. On business task benchmarks, smaller, lower-cost models with Skills reliably performed at or near Opus 5.5.
Latest posts

How agents can learn skills from traces
Agents in production meet problems that their prompts and skills did not anticipate, and what they learn solving them is lost. Our new paper describes how Zep Agent Skills turns verified traces into procedural agent memory.

What is a company brain and what does it let agents do?
Agents have the intelligence to do the job. They often lack the knowledge to do it right. A company brain gives agents the knowledge they need to complete work reliably.

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.

How Zep Context Graphs keep two timelines for every fact
Each fact records when it was true and when it was added to the graph, so agents get the right answer for any point in time.

Metadata is the easy part of a data context layer
The SQL runs, the numbers look right, and the answer is wrong. As models get better at writing queries, more data agent failures come from insufficient business context. We read 15 engineering write-ups of internal data agents to see how teams handle it.

7 reasons context graphs are unusually effective
Agents need facts that connect across data sources and stay current. Vector search using text chunks gives them neither.
Sign up for Zep’s Newsletter
Writings on Zep, LLMs, and AI ecosystem tools.
More posts

Everything we shipped in the Zep Context API
Zep v4 is the Context API for agents. This post explains each new feature and how the features help agents make better decisions with Zep Context Graphs.

Hyperedges: accurate answers when a fact has many entities
Agents can make poor decisions when their context has only part of a fact. Most context graphs split a fact about three or more entities into pairs, so a search can return one pair and miss the others. Zep hyperedges keep the full fact together.

Zep v4: the Context API for agents
Zep v4 lets your agent navigate a graph by its connections and read how Zep built it. Every error has a stable code that the agent can act on. v3 keeps working while you migrate.

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.