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

41
/ 100
Emerging
No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 13 / 25
Community 8 / 25

How are scores calculated?

Stars

41

Forks

3

Language

Python

License

AGPL-3.0

Category

agent-memory-systems

Last pushed

Mar 12, 2026

Commits (30d)

0

GitHub
Agent Memory Systems · 143 tools

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.

Featured in

Agent Memory in 2026: What Actually Works for Persistent AI

Higher-rated alternatives

topoteretes/cognee

Knowledge Engine for AI Agent Memory in 6 lines of code

80

divagr18/memlayer

Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory...

65

verygoodplugins/automem

AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:

64

CortexReach/memory-lancedb-pro

Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder...

62

CaviraOSS/OpenMemory

Local persistent memory store for LLM applications including claude desktop, github copilot,...

61

Explore Vector Databases

All categories Trending Vector Database directory Insights