Build agents that
do the job right
Zep is the enterprise context layer for reliable agents, providing governed access to company knowledge and skills built from agent tasks.
Reliable agents need context and skills,
and governance to run in production.
Unified business context
Agents gain a complete and current understanding of your business at runtime using the Context Lake.
Self-improving agents
Agents get more tasks right and use fewer tokens with skills Zep builds from their runs.
Governance as infrastructure
Policies decide what each user and agent can read, with every request logged.
What teams build with Zep
Company brain
A governed company brain provides accurate context to internal agents.
Customer context
A unified view of each customer from all your data sources, with user and agent access controls.
Vertical agents for regulated industries
Legal, finance, and healthcare agents access domain knowledge and isolated customer data, with access controls and retention policies.
Context infrastructure for the enterprise
“We can easily see Zep becoming a de facto partner in this layer of the enterprise agent stack.”
One solution for agent knowledge and skills.
Agents that know your business
and learn what works.
Zep gives each agent company knowledge and skills at runtime.
The Context Lake unifies business data into governed context graphs for agents.
Zep Agent Skills turns your agents' tasks into skills they follow.
Works with any agent, model, or harness.
Agents connect to Zep through MCP or the Zep SDKs, each with its own access controls.
LangGraph
Google ADK
Microsoft Agent Framework
Mastra
Claude
ChatGPT
Grok
OpenClaw
Claude Code- Codex
Cursor
GitHub Copilot
Gemini CLI
Connect the systems
where your context lives
Connectors sync the channels, folders, and libraries you choose into context graphs.
Slack
Microsoft Teams
Gmail
Granola
Google Drive
SharePoint
Notion
Snowflake
Databricks
BigQuery
Built for the enterprise
Shared context, governed access
Policies decide what context each agent can retrieve and which skills it can use. Every request is logged.
Attribute-based access control
Use attributes to control what context each agent can retrieve.
Retention policies
Data expires on the schedule you set. Legal hold blocks deletion when compliance requires it.
Audit and API logs
Detailed logs of every request and access decision, ready for audit.
Choose where to deploy Zep
Zep Cloud, Zep Cloud with your own encryption keys, or a deployment in your VPC.
Cloud
Use Zep's managed service. No infrastructure to run. Start in minutes.
- SOC 2 Type II
- HIPAA BAA
Cloud + Your Own Keys
Use Zep's managed service with your own encryption keys. You control the keys that encrypt data at rest.
- SOC 2 Type II
- HIPAA BAA
Bring Your Own Cloud
Deploy Zep inside your VPC. Your network, your perimeter, your compliance boundary.
SOC 2 Type II · HIPAA BAAs · Trust Center
What teams are saying
“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.”
Start building with Zep
Latest from the Zep blog
View all posts
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.