Zep unifies business data, documents, and conversations into shared, governed context so agents can complete tasks correctly.
Agents cannot complete tasks correctly when essential context is missing. Zep connects related information across your business, with access policies that govern what each agent can retrieve.
Any Source
Facts, and how they change over time
Context for the task
Account: Acme
Renewal: October 31
SSO setup is blocked.
Confirm SSO setup
before renewal.The Context Lake unifies enterprise data into millions of Context Graphs, managed and governed as one system. It runs on Konig, Zep’s graph database service.
Zep retrieves context in under 200 milliseconds, regardless of graph size or count.
Zep enforces access and retention policies across graphs and records query activity for audit—all within the data layer.
Learn moreRobbie strongly favors Adidas shoes.
“I only wear Adidas shoes. I love them!”
Trace each fact to the source it came from, and audit any answer back to its origin.
Unify knowledge about customers, projects, and business domains into shared context for agents across your organization.
Give agents context from past conversations, user activity, and changing preferences.
Unify account records, conversations, and events so agents understand each customer’s situation.
We can easily see Zep becoming a de facto partner in this layer of the enterprise agent stack.
When new information contradicts a fact in the graph, Zep invalidates the old fact and keeps it as history.
Agents reason with what is true now, or with what was true on any past date.
Reason for return
Additional comments
Zep records patterns across your data as Observations, giving agents context beyond individual facts and summaries.
Use the Zep API to add business data and conversations, then retrieve context for your agents. Works with any agent framework, or none.
# Add messages and get context in one callresponse = client.thread.add_messages( thread_id=thread_id, messages=[Message(name="Jane", role="user", content="I'd like to upgrade my plan...")], return_context=True,) # Add business data to the user's graphclient.graph.add( user_id=user_id, type="json", data=json.dumps({"event": "plan_upgrade", "to": "pro", "mrr": 49}),) # Get relevant contextuser_context = client.thread.get_user_context(thread_id=thread_id)// Add messages and get context in one callconst response = await client.thread.addMessages(threadId, { messages: [{ name: "Jane", role: "user", content: "I'd like to upgrade my plan..." }], returnContext: true,}); // Add business data to the user's graphawait client.graph.add({ userId, type: "json", data: JSON.stringify({ event: "plan_upgrade", to: "pro", mrr: 49 }),}); // Get relevant contextconst userContext = await client.thread.getUserContext(threadId);// Add messages and get context in one callresp, _ := client.Thread.AddMessages(context.TODO(), threadID, &v3.AddThreadMessagesRequest{ Messages: []*v3.Message{ {Name: v3.String("Jane"), Role: "user", Content: "I'd like to upgrade my plan..."}, }, ReturnContext: v3.Bool(true), },) // Add business data to the user's graphevent, _ := json.Marshal(map[string]interface{}{"event": "plan_upgrade", "to": "pro", "mrr": 49})client.Graph.Add(context.TODO(), &v3.AddDataRequest{ UserID: &userID, Type: v3.GraphDataTypeJSON, Data: string(event),}) // Get relevant contextuserContext, _ := client.Thread.GetUserContext(context.TODO(), threadID, nil)Share context across your organization while controlling what each user and agent can access.
Use attributes to control what context each agent can access and what it can do with it.
Data expires on the schedule you set. Legal hold blocks deletion when compliance requires it.
Detailed logs of every request and access decision, ready for audit.
Agent context and memory systems often trade accuracy, latency, and token use against each other. Zep leads on all three.
Monitor data ingestion, context retrieval, latency, and errors across your projects.
Usage, latency, and reliability for your account.
New graphs over time.
New users over time.
New episodes over time.
Context retrieval and graph search requests.
Choose Zep Cloud, Zep Cloud with your own encryption keys, or deployment in your VPC. Learn more.
Use Zep's managed service. No infrastructure to run. Start in minutes.
Use Zep's managed service with your own encryption keys. You control the keys that encrypt data at rest.
Deploy Zep inside your VPC. Your network, your perimeter, your compliance boundary.
Voices from the teams running Zep in production.
Zep is one of the most exciting things I've seen for real-world agent use cases in a long time.
Unlike other systems that only retrieve static documents, Zep uses a temporal knowledge graph to combine conversations and structured business data, keeping track of how things change over time.
Zep AI was instrumental in enabling the Sidekick's personalized experience through dynamic memory retrieval.
By organizing memories into structured episodes and extracting key insights, it builds smarter, more intuitive AI agents that revolutionize how businesses harness intelligence.
Zep is one of the most exciting things I've seen for real-world agent use cases in a long time.
Unlike other systems that only retrieve static documents, Zep uses a temporal knowledge graph to combine conversations and structured business data, keeping track of how things change over time.
Zep AI was instrumental in enabling the Sidekick's personalized experience through dynamic memory retrieval.
By organizing memories into structured episodes and extracting key insights, it builds smarter, more intuitive AI agents that revolutionize how businesses harness intelligence.
Loading latest articles…
