Papr-ai/memory-opensource

Predictive memory layer for AI agents. MongoDB + Qdrant + Neo4j with multi-tier caching, custom schema support & GraphQL. 91% Stanford STARK accuracy, <100ms on-device retrieval

38
/ 100
Emerging

This project provides a smart memory system for AI agents, allowing them to remember and use information more effectively. It helps AI agents store various data like text, documents, and even images, then find relevant information using natural language queries. The system automatically identifies and maps connections between different pieces of information, making AI agents more knowledgeable and context-aware. This is ideal for developers building intelligent assistants, enterprise AI solutions, or specialized agents in fields like finance, healthcare, or customer support.

Use this if you are a developer building AI agents and need a robust, scalable, and context-rich memory layer for them to store, retrieve, and understand information, especially across diverse data types.

Not ideal if you are an end-user looking for a pre-built AI application or a simple, no-code solution for data storage, as this project requires development expertise to implement and configure.

AI-agent-development knowledge-management-systems semantic-search enterprise-AI conversational-AI
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 13 / 25
Community 8 / 25

How are scores calculated?

Stars

41

Forks

3

Language

Python

License

AGPL-3.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/Papr-ai/memory-opensource"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.