kingjulio8238/Memary

The Open Source Memory Layer For Autonomous Agents

58
/ 100
Established

Implements a multi-layered memory architecture combining episodic memory streams, entity knowledge graphs (via FalkorDB or Neo4j), and dynamic user/system personas that automatically evolve through agent interactions. Supports both local models via Ollama (Llama 3, LLaVA) and OpenAI APIs with pluggable tools, enabling developers to integrate memory into existing LlamaIndex ReAct agents or use the built-in ChatAgent implementation with minimal code changes.

2,576 stars and 39 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 14 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

2,576

Forks

193

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 22, 2024

Monthly downloads

39

Commits (30d)

0

Dependencies

27

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/kingjulio8238/Memary"

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