Agent developers who need dated, permission-aware memory of users and accounts; free plan to start, then a big jump to $125 a month.
Kenning's take
What it does
Zep takes in a company's business data, documents and chat conversations and builds a dated graph of facts for each user, customer or account. When an agent needs to act, Zep returns only the facts that task depends on, filtered by access policies, in a single call. It is aimed at cutting token use compared with agents pulling whole records from each system.
- Context Graph per user, account or domain
- Ingests business data, documents and conversations
- Facts dated and updated as data changes
- Policy-filtered retrieval with request logging
- Memory MCP Server
- Context Lake running on Zep's Konig graph database
Who it suits. Developers building AI agents that need reliable memory of users and business data.
Key facts
- Category
- Developer tools
- Made by
- Zep
- How to get it
- self-serve sign-up with a free plan; Enterprise through sales
- Works on
- API, web dashboard
- Free plan
- free plan with monthly credits that do not roll over
- API price
- credit-based: Flex overage $25 per 10,000 credits, Flex Plus $75 per 40,000 credits
Pricing
| Plan | Price | Billed |
|---|---|---|
| Flex | $125 | month |
| Flex Plus | $375 | month |
| Enterprise | Custom pricing | Not stated |
FAQ
What is Zep?
A service that builds a graph of facts from business data and conversations so AI agents can retrieve the context a task needs.
How much does Zep cost?
There is a free plan. Flex costs $125 a month and Flex Plus $375 a month, with Enterprise priced on request.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools

Claude Keychain
A free Mac menu bar app that keeps API keys in the macOS Keychain so Claude Code can use them without seeing them.
OpenAI Agent Builder
OpenAI's visual canvas for building multi-agent workflows, being withdrawn on 30 November 2026.
ElevenLabs Agent Workflows
Visual editor in ElevenLabs' agent platform for designing branching conversation flows for voice and chat agents.

AgentOps
Monitoring and debugging platform that records what AI agents do, what they cost and where they fail.