# getzep/zep

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/getzep-zep).**

4,076 stars · 573 forks · Python · apache-2.0

## Links

- GitHub: https://github.com/getzep/zep
- Homepage: https://help.getzep.com
- awesome-repositories: https://awesome-repositories.com/repository/getzep-zep.md

## Topics

`ai` `knowledge-graphs` `language-model` `llm`

## Description

Zep is a long-term memory layer and persistent storage system for large language model applications. It functions as a memory service and vector database orchestrator that manages chat history, user preferences, and context retrieval to reduce hallucinations in AI agents.

The system maintains a temporal knowledge graph that stores interaction data as dated facts to track how user preferences and environments evolve over time. It combines these knowledge graphs with a store for persisting unstructured message data at the user and session levels.

The platform provides capabilities for AI context optimization through semantic and graph-based search, as well as AI privacy management tools for executing data deletion requests and compliance tasks across user records.

## Tags

### Artificial Intelligence & ML

- [Long-term Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/memory-management-systems/long-term-memory-stores.md) — Provides a persistent storage system for retaining user and session context across multiple AI interactions.
- [AI Context Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-context-optimization.md) — Fetches concise and relevant information for LLMs to improve response accuracy and reduce hallucinations.
- [Graph-Based Context Retrieval](https://awesome-repositories.com/f/artificial-intelligence-ml/graph-based-context-retrieval.md) — Searches for pertinent facts using combined semantic and graph methods to maintain precise context for AI generation. ([source](https://cdn.jsdelivr.net/gh/getzep/zep@main/README.md))
- [Knowledge Graphs](https://awesome-repositories.com/f/artificial-intelligence-ml/knowledge-graphs.md) — Organizes user interaction data as a graph of dated facts to provide persistent memory for AI agents.
- [Persistent Chat Histories](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/ai-memory-systems/persistent-chat-histories.md) — Saves messages and unstructured data at the user or session level for long-term conversational context. ([source](https://cdn.jsdelivr.net/gh/getzep/zep@main/README.md))
- [Stateful LLM Application Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/stateful-llm-application-servers.md) — Provides a stateful server architecture that manages conversation threads, user preferences, and long-term memory.
- [Prompt-Optimized Context Retrieval](https://awesome-repositories.com/f/artificial-intelligence-ml/on-demand-context-retrieval/layered-context-retrievers/prompt-optimized-context-retrieval.md) — Retrieves concise and governed data from a central source to improve AI response accuracy and reduce hallucinations. ([source](https://help.getzep.com/))

### Data & Databases

- [Temporal Knowledge Graphs](https://awesome-repositories.com/f/data-databases/entity-relationships/temporal-knowledge-graphs.md) — Maintains a graph of dated facts to track how user preferences and environments evolve over time.
- [Hybrid Vector-Graph Databases](https://awesome-repositories.com/f/data-databases/hybrid-vector-graph-databases.md) — Combines vector embeddings with knowledge graphs to support both semantic and relational queries for high-precision context.
- [Agent Interaction Memory Stores](https://awesome-repositories.com/f/data-databases/local-data-stores/local-interaction-stores/agent-interaction-memory-stores.md) — Builds a temporal knowledge graph from documents and chats to maintain a persistent memory of users and contexts. ([source](https://help.getzep.com/))
- [Semantic Retrieval Engines](https://awesome-repositories.com/f/data-databases/semantic-retrieval-engines.md) — Uses mathematical embeddings to find relevant context by calculating the distance between queries and stored documents.
- [Document Versioning](https://awesome-repositories.com/f/data-databases/document-versioning.md) — Tracks historical changes to source materials to ensure retrieved context reflects the most current knowledge base state.
- [User and Session Hierarchies](https://awesome-repositories.com/f/data-databases/in-memory-session-stores/relational-database-session-stores/user-and-session-hierarchies.md) — Organizes chat histories into user and session hierarchies to enable efficient retrieval and privacy-compliant data deletion.

### DevOps & Infrastructure

- [Vector Database Orchestrators](https://awesome-repositories.com/f/devops-infrastructure/automation-orchestration/vector-database-orchestrators.md) — Implements a management layer for indexing and retrieving semantic context and unstructured data to reduce LLM hallucinations.

### Security & Cryptography

- [AI Session Privacy Management](https://awesome-repositories.com/f/security-cryptography/ai-session-privacy-management.md) — Manages the deletion and pruning of conversational AI history to meet regulatory privacy requirements.
- [Privacy Compliance Tools](https://awesome-repositories.com/f/security-cryptography/data-privacy-management/privacy-compliance-tools.md) — Provides utilities for executing data deletion requests and privacy compliance tasks across user and session records. ([source](https://cdn.jsdelivr.net/gh/getzep/zep@main/README.md))