Tool overview
Zep is listed under AI Infrastructure & MLOps AI tools.
What is Zep?
Zep is a managed agent-memory and context-engineering platform that converts conversations, documents, events, and business data into temporal Context Graphs. It serves governed, prompt-ready context for personalized agents with low-latency retrieval.
Best for
Teams deploying personalized, governed AI agents with evolving long-term memory
Who is it for?
Decision note
Rebuilt from the original export under V412/V411 independent factual verification. Preview only; Apply requires Failures = 0, Warnings = 0, Unmapped = 0, Missing = 0, reviewed explicit clears, image import disabled or V380 PASS, representative edit-screen comparison, and a zero-change post-Apply Preview.
Key features
Temporal Context Graphs with changing facts
Prompt-ready retrieval from a governed Context Lake
Python, TypeScript, and Go SDKs
Cloud, BYOK, and BYOC deployment options
Use cases
Add long-term memory to AI agents
Personalize assistants across sessions
Track evolving user and business facts
Serve governed context at enterprise scale
Pros
- Free plan includes monthly credits
- Unmetered retrieval, storage, and users
- Open-source Graphiti framework available separately
Limitations
Credit consumption depends on episode byte size and optional webhook use. Official multilingual graph creation is still on the roadmap
multilingual results depend on the connected LLM and prompts.
Pricing details
Billing options
Pricing note
Free includes 10,000 credits monthly. Flex includes 50,000 monthly credits at $104 per month billed annually, or $125 monthly; overage is $25 per 10,000 credits.
Supported languages
- English
Integrations
Neo4j
FalkorDB
Amazon Neptune
MCP
Webhooks
Please log in to join the discussion.