Show HN: Zep – Long-Term Memory Store for Conversational AI Apps

• zep

  16 2,054 8.8 Go

  Zep: Long-Term Memory for ‍AI Assistants.

  

Zep is a long-term memory store designed for conversational AI applications that are built using modern LLMs. It handles the storage, summarization, embedding, indexing, and enrichment of chat histories, and offers developers a simple, low-latency API to this data. Chat history storage is an infrastructure challenge all developers and enterprises face as they look to move from prototypes to deploying conversational AI applications that provide rich and intimate experiences to users.

Key features include long-term memory persistence, auto-summarization, vector search, auto-token counting, and Python and JavaScript SDKs. Upcoming features include Langchain Memory and Retrievers, integrations with other conversational AI frameworks, entity extraction, and much more.

Github repo: https://github.com/getzep/zep

Long-term memory persistence enables a variety of use cases, including:

- Personalized re-engagement of users based on their chat history.

• zep-js

  3 19 9.0 TypeScript

  Zep - Long-Term Memory for ‍AI Assistants (TypeScript Client)

  

- When storing messages long-term, developers are exposed to privacy and regulatory obligations around PII, retention, and deletion of user data.

Zep aims to solve these challenges.

Zep and its Python and [Ja](https://github.com/getzep/zep-js)vascript client libraries have been open-sourced under the Apache License.

Learn more and contribute:

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• zep-python

  1 55 8.7 Python

  Zep: Long-Term Memory for ‍AI Assistants (Python Client)

  

Suggest a related project