# Zep

> Context layer that builds governed, time-aware context graphs from business data so agents retrieve what tasks need

Source: https://dontaskagain.com/zep
Website: https://www.getzep.com/?utm_source=dontaskagain
Pricing: Freemium
Categories: [Memory](https://dontaskagain.com/categories/memory.md)
Listed: 2026-10-18
Updated: 2026-10-18

Zep is a context and memory platform for AI agents. It ingests business data, documents and conversations, builds a context graph for each user, customer, account or domain, and returns only the facts a task depends on, so developers' agents work from shared, current context instead of pulling whole records from each system.

**Key features:**

- Send business data, documents and chat history as episodes, with each record linked to its source.
- Build time-aware context graphs whose facts are dated and updated as data changes.
- Retrieve task-relevant context in one call, filtered by policy.
- Control what each agent may retrieve and log every request.
- Define custom entity and edge types and extraction instructions.
- Expose context to agents through Context MCP Server seats.

Zep runs on Zep Cloud, optionally with customer-managed encryption keys, or in a customer VPC, with SOC 2 Type II and a HIPAA BAA. Self-serve plans are credit based: a free tier gives 10,000 credits a month, Flex is $125/month and Flex Plus $375/month, and Enterprise is priced through sales.

## More memory agents

- [Mem0](https://dontaskagain.com/mem0.md): Open-source memory layer that lets AI agents store, compress and recall user context across sessions
- [Letta](https://dontaskagain.com/letta.md): Research lab behind MemGPT building stateful agents with persistent, self-improving memory
- [Supermemory](https://dontaskagain.com/supermemory.md): Memory and continual-learning engine that stores agent context in a time-aware graph and injects it at runtime