Zep

Zep is a context engineering platform for AI agents built on Graphiti, an open-source temporal knowledge graph engine. Unlike traditional memory systems that rely on static RAG or chat history alone, Zep automatically extracts entities, relationships, and facts from conversations and business data, then builds a unified context graph that evolves as information changes. When a fact is superseded (for example, when a user changes their preferences or a business relationship shifts), Zep automatically invalidates the old fact while preserving its historical context and provenance. This temporal awareness is what separates Zep from simpler vector-based memory systems such as mem0. The core workflow has three steps: ingest (chat messages, JSON business data, and documents sent via the API), build (Graphiti constructs a temporal knowledge graph with automatic entity extraction and fact invalidation), and assemble (Zep retrieves relevant context and formats it for the LLM at under 200ms P95 retrieval latency). On the LoCoMo benchmark, Zep achieves 80.32% accuracy at 189ms with single-shot retrieval and no slow agentic loops. On LongMemEval, Zep scores 63.8% on temporal retrieval tasks versus mem0's 49%, with accuracy improvements of up to 18.5% and 90% latency reduction versus baseline implementations. On the Deep Memory Retrieval benchmark, Zep scores 94.8% versus MemGPT's 93.4%. Pricing has four tiers: Free (full API access, no credit card required), Flex ($125/month, 50,000 credits included, 5 projects, 10 custom entity types, auto-topup), Flex Plus ($375/month, 200,000 credits, analytics, webhooks, custom extraction instructions, API logs), and Enterprise (custom, on-premises deployment, SSO, HIPAA BAA, dedicated SLA). The Graphiti MCP Server gives Claude Desktop, Cursor, VS Code with Copilot, and other MCP-compatible clients persistent knowledge graph memory across sessions. The open-source Graphiti library requires Docker, FalkorDB or Neo4j, and an LLM API key for self-hosted deployment. Python, TypeScript, and Go SDKs are available. Works with LangChain, LangGraph, CrewAI, and any agent framework. Customers include AWS, Samsung, HoneyBook, Twin Health, and Thrive AI Health. Founded 2023. SOC 2 Type 2 and HIPAA certified.