Context engineering platform that gives AI agents long-term memory via a temporal knowledge graph, Graph RAG, and context assembly. SDKs for Python/TS/Go, MCP server support, and usage-based pricing.
At a Glance
About Zep
Zep is a context engineering platform for AI agents. It builds and maintains a temporal knowledge graph from chat histories and business data, then retrieves and assembles only the most relevant context for each request. This improves accuracy and personalization while reducing hallucinations and token spend. Zep includes agent memory, Graph RAG, and context assembly services with managed cloud APIs and SDKs for Python, TypeScript/JavaScript, and Go. Developers can ingest messages and structured/unstructured records, define custom entity/edge types, and query or retrieve subgraphs on demand. Zep also ships an experimental Knowledge Graph MCP Server so MCP clients like Claude Desktop or Cursor can persist and recall context locally or against Zep Cloud. Enterprise options add SOC 2 Type II, HIPAA BAA, audit logs, SSO, SLA, and BYOC/VPC deployment.
Community Discussions
Be the first to start a conversation about Zep
Share your experience with Zep, ask questions, or help others learn from your insights.
Pricing
Free (Metered)
Get started with Zep at no cost with 2,500 messages free per month and 2.5 MB graph data free per month.
- 2,500 messages free per month
- 2.5 MB graph data free per month
- Up to 5 projects
- Discord/community support
Metered (Pay-as-you-go)
Metered (Pay-as-you-go) plan with $1.25 per 1,000 messages and $2.50 per MB of graph data ingested.
- $1.25 per 1,000 messages
- $2.50 per MB of graph data ingested
- Unlimited retrieval requests
- In-app chat support (with upgrade)
Enterprise
Enterprise-grade solution with Custom limits & committed rate limits and SOC 2 Type II, HIPAA BAA and dedicated support.
- Custom limits & committed rate limits
- SOC 2 Type II, HIPAA BAA
- SSO, API & audit logs, SLA
- Single-tenancy & BYOC/VPC deployment
- Dedicated account manager & Slack support
Capabilities
Key Features
- Temporal knowledge graph memory for users, sessions, and business data
- Graph RAG for dynamic, real-time retrieval from evolving data
- Context assembly to compile the smallest relevant context window
- SDKs for Python, TypeScript/JavaScript, and Go
- Structured data extraction from chat histories
- Semantic & keyword search across messages and graph episodes
- Custom entity/edge schemas with typed attributes
- Knowledge Graph MCP Server for Claude Desktop, Cursor, and other MCP clients
- Managed cloud with usage-based billing and generous free tier
- Enterprise controls: SOC 2 Type II, HIPAA BAA, SSO, audit logs, SLA, BYOC/VPC
Integrations
Demo Video
