Zep

Active

GitHub Python Apache-2.0

Description

Zep is an AI agent memory management platform providing long-term memory, context management, and conversation history understanding through knowledge graph technology.

Key Features

End-to-end context engineering platform with sub-200ms latency for real-time agent context
Graph RAG: automatic relationship extraction and temporal knowledge graph maintenance
Relationship-aware context retrieval with valid_at/invalid_at timestamps for evolving facts
Multi-language SDKs: Python (pip install zep-cloud), TypeScript, and Go
Enterprise-grade with SOC2 Type 2 and HIPAA compliance via Zep Cloud
Powered by Graphiti, the open-source temporal knowledge graph framework

Use Cases

💡 Providing AI agents with long-term memory that understands how relationships evolve over time

💡 Assembling relationship-aware context blocks from chat history, business data, and events

💡 Building production AI applications that need accurate, current, and relevant contextual information

💡 Integrating with LangChain, LlamaIndex, AutoGen, and other agent frameworks for context management

Quick Start

pip install zep-cloud

Visit GitHub Visit Website

Related Projects

MemAgent

1.1k · Python

Normal

A MemAgent framework that can extrapolate to 3.5M context tokens, along with a training framework for RL training of any agent workflow.

memoryagentrag +2

A-MEM

1.1k · Python

Stale

An agentic memory system for LLM agents inspired by human memory mechanisms, enabling dynamic memory generation, retrieval, and consolidation with automatic memory evolution and self-organization.

memoryagentllm +1

SimpleMem

3.6k · Python

Active

SimpleMem: Efficient Lifelong Memory for LLM Agents — supports text and multimodal memory for long-term information retention and retrieval.

pythonagentmemory +1

MiroFish

67.6k · Python

Normal

Multi-agent swarm intelligence engine that extracts seed information from the real world, constructs a high-fidelity parallel digital world with thousands of agents, and predicts future trajectories through social evolution simulations.

multi-agentswarm-intelligenceknowledge-graph +3

Memory记忆系统长期记忆

Agent Memory Architecture: Working, Long-term, and Shared Memory Trade-offs

A systematic comparison of the three categories of agent memory -- working, long-term, and shared -- covering storage media, lifecycle, retrieval methods, typical frameworks, and design patterns, fully addressing agent personalization and multi-agent collaboration engineering.

Zep