The Foundational Memory Layer for AI

Equip your agents with the knowledge to complete tasks, from the mundane to monumental.

Trusted by:

Build Personalized & Accurate AI Agents

Memory that learns from users & business data

Give LangChain agents access to chat messages & business data
Zep intelligently collects data into a Knowledge Graph
Send relevant user facts to your LangChain agent through a single API call

Enable Agent Temporal Reasoning

Memory that updates as facts change

As Zep incorporates new information, superseded facts are marked as invalid
Zep identifies and stores temporal context on the graph
Retaining a history of facts enables agents to reason with changing user state

Framework and Platform Agnostic

Develop agents in Python, TypeScript, or Go - with any framework or none at all.

Python

TypeScript

Go

LangChain

AutoGen

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.

Add Agent Memory in Minutes

With minimal code changes, enable your agent with rich, relevant context from chat and business data.

 
# Add a chat message to the graph
await zep_client.memory.add(session_id, messages=[
	Message(role="Jane", role_type="user", content="I can't log in!")
])
# Add business data to the graph
await zep_client.graph.add(user_id=user_id, type="json", data={"account_status": "suspended"})

# get memory relevant to the current conversation
memory = zep_client.memory.get(session_id="session_id")
print(memory.context)

"""FACTS and ENTITIES represent relevant context to the current conversation.
# These are the most relevant facts and their valid date ranges
# format: FACT (Date range: from - to)
<FACTS>
  - Emily is experiencing issues with logging in. (2024-11-14 02:13:19+00:00 - present) 
  - Emily's account has a suspended status due to payment failure. (2024-11-14 02:03:58+00:00 - present) 
...
</FACTS>"""

 
// Add a chat message to the graph
await zepClient.memory.add("session_id", [
    { role: "Jane", roleType: "user", content: "I can't log in!" }
]);

// Add business data to the graph
await zepClient.graph.add(userId, "json", { account_status: "suspended" });

// Get memory relevant to the current conversation
const memory = await zepClient.memory.get("session_id");
console.log(memory.context);

```
FACTS and ENTITIES represent relevant context to the current conversation.
# These are the most relevant facts and their valid date ranges
# format: FACT (Date range: from - to)
<FACTS>
  - Emily is experiencing issues with logging in. (2024-11-14 02:13:19+00:00 - present) 
  - Emily's account has a suspended status due to payment failure. (2024-11-14 02:03:58+00:00 - present) 
...
</FACTS>
```

 
client.Memory.Add(context.TODO(), "sessionId", &v2.AddMemoryRequest{
	Messages: []*v2.Message{{Content: "I can't log in!", RoleType: v2.RoleTypeUser}},
})

client.Graph.Add(context.TODO(), &v2.AddDataRequest{
	UserId: userID, Type: "json", Data: map[string]interface{}{"account_status": "suspended"},
})

memory, _ := zepClient.Memory.Get(context.TODO(), "session_id")
fmt.Println(memory.Context)

```
FACTS and ENTITIES represent relevant context to the current conversation.
# These are the most relevant facts and their valid date ranges
# format: FACT (Date range: from - to)
<FACTS>
  - Emily is experiencing issues with logging in. (2024-11-14 02:13:19+00:00 - present) 
  - Emily's account has a suspended status due to payment failure. (2024-11-14 02:03:58+00:00 - present) 
...
</FACTS>
```

Backed by Leading Investors

And angels at industry-leading companies including Vercel, Google, and Airtable.

Y Combinator

Engineering Capital

Step Function

Build Consistent and Correct LLM Apps

Build your agent in Python, TypeScript, or Go using your favorite framework, or none at all.

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

Speed

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.

Get Started