We're hiring! Come build with us →
Zep
Platform

The Context Lake

Unify enterprise data into shared context, with access controls for every user and agent.

Read the S&P report
Teams that use Zep
Fortune 500 Tech Co.
Twin Health
Praktika.ai
Thrive AI Health
AGI Inc
Zscaler
Quorum
Nasdaq-100 Tech Company

Context is scattered across the business

Agents need the right context to complete tasks correctly. That context spans business systems, documents, and conversations. Unifying it across agents requires governance, isolation, and retrieval at scale.

The Context Lake unifies that context in one governed system, serving what each agent’s task requires.

Across every agent. Every user.
Every source of data.
Context Lake
one system of record across all of it

Inside the Context Lake

The Context Lake manages graphs for users, customers, teams, and topics. Each graph connects facts from conversations, documents, events, and business records.

Agent Runtime

LangGraph·Vercel AI SDK·Pydantic AI·Google ADK·custom

Use the Zep SDK with your agent framework or custom application.

Ingestion

chat·JSON·documents·app events

Add conversations, JSON data, documents, and application events.

entity extraction·relationships·ontology·invalidation

Graphiti extracts facts and relationships to construct Context Graphs.

Context Assembly

context blocks·templates·token-efficient

Zep selects context and assembles it into blocks for agent prompts.

Retrieval

sub-200ms·auto-optimized·provenance-linked·policy-filtered

Zep selects context for the task within the specified token budget.

Governance

ABAC·multi-tenant isolation·customer key encryption·retention policies·audit·provenance

Zep applies access policies to reads and writes. It records source information and applies retention policies.

Konig

entities·facts & edges·decision traces·episodes

Konig serves Context Graphs with source information and records of changes over time.

Built on Konig

Konig is Zep’s graph database service, built to manage millions of isolated graphs with temporal history.

Context Lake · section A–Adrawing 06 · engine
Working set · RAM

Hot graphs, served at memory speed.

Snapshots · object store
  • snapshot · 2026-05-25 · 18:00
  • snapshot · 2026-05-25 · 12:00
  • snapshot · 2026-05-24
  • snapshot · 2026-05-22
  • snapshot · 2026-05-15
  • snapshot · 2026-04
Rehydrate · ~40 µs
hot · in-memory working setcold · object-store snapshotsscale 1:∞

Next to your data lake, not instead of it

Keep your data lake for analytics. Use the Context Lake to provide context for agents.

Data
Your Data Lake

Structured, quantitative

Tables, transactions, logs, metrics.

Context Lake

Structured and unstructured data

Use records, documents, conversations, and events as sources of context.

Query model
Your Data Lake

SQL, batch analytics

Optimized for aggregation and retrospective analysis.

Context Lake

Graph traversal, semantic

Temporal context graphs with entity-aware retrieval.

Latency
Your Data Lake

Seconds-to-minutes

Batch jobs, scheduled pipelines, dashboard refresh.

Context Lake

Sub-200ms retrieval

Real-time context at agent inference speed.

Consumers
Your Data Lake

Dashboards & ML

BI tools, data scientists, reporting pipelines.

Context Lake

Agents & assistants

Agents and assistants retrieve context for their tasks.

Governance
Your Data Lake

Row & column ACLs

Table-level permissions, role-based access.

Context Lake

Entity-level ABAC

Attribute-based policies, retention rules, full audit trail.

Recognition

Context infrastructure for the enterprise.

S&P GlobalMarketIntelligence

Zep tackles agent memory limitations through its temporal context graph.

S&P Global Market Intelligence · April 2026
“We can easily see Zep becoming a de facto partner in this layer of the enterprise agent stack.”
— Melissa Incera, S&P Global Market Intelligence

Shared context, governed access

Share context across your organization while controlling what each user and agent can access.

Access control

Attribute-based access control

Use attributes to control what context each agent can access and what it can do with it.

Retention

Retention policies

Data expires on the schedule you set. Legal hold blocks deletion when compliance requires it.

Audit trail
22:14/graph/search200115ms
22:11/entity/search4034ms
22:09/graph/search200110ms
Audit

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.

Managed

Cloud

Use Zep's managed service. No infrastructure to run. Start in minutes.

  • SOC 2 Type II
  • HIPAA BAA
BYOK

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
BYOC

Bring Your Own Cloud

Deploy Zep inside your VPC. Your network, your perimeter, your compliance boundary.

Start with the Context Lake