Zep
Context engineering and agent memory platform for AI agents
Zep is a context engineering and agent memory platform designed for AI agents. It automatically extracts entities, relationships, and facts from chat messages, JSON business data, and documents into a temporal context graph. When an agent needs context, Zep retrieves and assembles the most relevant information in a token-efficient format for any LLM framework.
Zep ingests data, builds a temporal context graph by extracting entities and relationships, and automatically assembles relevant context for the agent on each request in under 200ms.
developers and teams building AI agents
Background.
- Status
- launched
- Business model
- freemium
- Company
- Zep AI
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.