Introducing Zep Agent Skills! Read the announcement. →
Zep

Older posts

Agent memory

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.

Governance and security

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.

Governance and security

Securing Agent Memory with ABAC

Attach policies to any Zep API key to control the exact endpoints it can call and the graph data it can read.

Integrations

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.

Agent memory

Agent memory placement can cut your token bill up to 2x

Agent memory has to refresh every turn, but putting it in the system prompt breaks prompt caching and re-bills the whole conversation each turn. Here is the one-message fix, and the token savings it led to in an experiment.

Agent memory

Markdown is not agent memory

Some of the most capable agents in production keep their memory in plain markdown files, and for a single agent and a single user it is hard to beat. The pattern breaks in predictable places: at scale, as facts change and errors compound, and under concurrent agents.

Engineering

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.

Benchmarks and evaluation

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.

Product updates

The Batch API: Load Large Datasets into Agent Memory

Zep's Batch API loads large datasets into agent memory faster, in batches up to 50,000 items, with a progress dashboard and no impact on real-time ingestion.

Retrieval

Smart Context Assembly: Fewer Tokens, Better Quality

Today we're announcing Smart Context Assembly, an upgrade to how Zep's default Context Block is built: higher accuracy from fewer tokens, with no code changes.

Context graphs

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.

Context engineering

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.

Sign up for Zep’s Newsletter

Writings on Zep, LLMs, and AI ecosystem tools.

No spam. Unsubscribe anytime.