ascottbell/maasv
Memory Architecture as a Service — cognition layer for AI assistants. 3-signal retrieval, knowledge graphs, memory lifecycle.
This project provides a "cognition layer" that allows all your AI assistants and tools to share a single, persistent understanding of your information. It takes raw conversations, documents, and data from various sources, extracts key entities and relationships, and organizes them into a knowledge graph. The output is a highly contextualized and structured understanding of information, enabling your AI agents to remember past interactions and connect disparate pieces of information across different tools and sessions.
Used by 1 other package. Available on PyPI.
Use this if you manage multiple AI assistants or tools and need them to share a consistent, evolving understanding of your data and past interactions without constant re-explanation.
Not ideal if you only use a single AI tool in isolated sessions or do not require deep, cross-tool contextual understanding and memory management.
Stars
17
Forks
7
Language
Python
License
—
Category
Last pushed
Feb 27, 2026
Commits (30d)
0
Dependencies
1
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/ascottbell/maasv"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
aiming-lab/SimpleMem
SimpleMem: Efficient Lifelong Memory for LLM Agents
zilliztech/memsearch
A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.
microsoft/kernel-memory
Research project. A Memory solution for users, teams, and applications.
zilliztech/GPTCache
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
TeleAI-UAGI/telemem
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication,...