kingjulio8238/Memary
The Open Source Memory Layer For Autonomous Agents
Memary helps developers create AI agents that can remember and learn over time, much like humans do. It takes in user and system personas, along with past interactions and knowledge stores, to produce agents capable of more complex and continuous reasoning. This tool is designed for AI developers and researchers building autonomous agents or conversational AI systems.
2,576 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are developing AI agents and want them to retain information, evolve their understanding, and make decisions based on past interactions without extensive manual memory management.
Not ideal if you are looking for a simple, off-the-shelf chatbot solution or if your application does not require sophisticated, human-like memory for AI agents.
Stars
2,576
Forks
193
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 22, 2024
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.
Featured in
Compare
Related tools
MemoriLabs/Memori
SQL Native Memory Layer for LLMs, AI Agents & Multi-Agent Systems
volcengine/OpenViking
OpenViking is an open-source context database designed specifically for AI Agents(such as...
mem0ai/mem0
Universal memory layer for AI Agents
zjunlp/LightMem
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
MemTensor/MemOS
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill...