Zep - Long-Term Memory for AI

Build AI agents that continually learn. Delight users with personalized and accurate experiences.

Get Started

Backed by

Long-Term Memory for AI Apps

Memory that learns from your users

Zep intelligently learns from user interactions, improving your AI agent's knowledge over time. Populate your prompts with the most relevant facts about users.

Easily Drop into LangChain

Zep's ChatHistory class makes production-ready personalization simple for any LangChain Expression Language or LangGraph app.

Just 2 lines of code to power your AI app with memory

SDKs are available for all major languages. Or use ready-made Zep components for your favorite framework.

Python

TypeScript

LangChain

n8n

LangFlow

Flowise

Ready for Production and Scale

Instant Memory Retrieval

Get relevant results from memory in milliseconds. Scale to millions of users with ease.

Granular Memory Controls

Tailor memory extraction and relevance with custom rating frameworks and controls.

Secure and Privacy Compliant

Be assured with SOC 2 Type II compliance. Zep also offers privacy controls to support CCPA and GDPR compliance.

Build Consistent and Correct LLM Apps

Recalling relevant user facts from long-term memory reduces hallucination and improves recall. Zep's Structured Output and Dialog Classification tools enhance these benefits, ensuring consistent user experiences.

Fast, Flexible Structured Output

Extract strongly-typed data from chat history, quickly & accurately

Get structured output from chat messages, more accurately and faster than your LLM provider's JSON or Structured Output mode. Zep offers built-in types for datetimes, floats, emails, RegEx patterns, and more.

Fill "Forms"

Build User Profiles

Run Biz Processes

Populate API Calls

Dialogue Classifier

Instantly classify conversation state

Understand user intent and emotion, segment users, and more. Route chains based on semantic context, and trigger events. All without adding latency to your user experience.

Understand Intent

Segment Users

Semantic Routers

Trigger Events

Up to 80% faster than DIY with major LLM providers

Zep won't slow down your user experience. Long-term memory recall, dialog classification, data extraction and more run in a fraction of the time of similar functionality implemented using leading LLM vendors.

Dialogue Classification Chart - P90 Latency

The Memory Foundation For Your AI Stack