markmbain/aius
The long-term memory for your Superagents 🥷and LLMs 🤖. Built with GraphRAG, Knowledge graphs and autonomous ai agents
This is a long-term memory system for AI assistants and 'Superagents' that helps them remember and understand past interactions, their own goals, and diverse content like text, audio, and video. It allows AI to learn about individual users on the fly, process multimodal information, and build relationships with other AI and humans. Developers creating advanced AI applications would use this to give their AI systems more dynamic, human-like memory capabilities.
No commits in the last 6 months. Available on PyPI.
Use this if you are a developer building sophisticated AI agents or assistants and need them to have dynamic, self-aware, and multimodal long-term memory beyond standard context windows.
Not ideal if you only need a basic RAG system for static, limited document types or if your AI application doesn't require deep, evolving memory and self-awareness.
Stars
63
Forks
6
Language
Python
License
MIT
Category
Last pushed
Jan 21, 2025
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/markmbain/aius"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Compare
Higher-rated alternatives
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...