gengxy1216/FlockMem
✦ FlockMem is a lightweight, local-first long-term collective memory bus for multi-agents, optimized for edge deployment with a minimal memory footprint under 50MB. It combines text-based, vector similarity, and knowledge graph retrieval with traceable citations.
This tool provides a local, private, and lightweight memory system for AI agents, allowing them to recall information effectively. It takes various forms of information, like text, and allows agents to search and retrieve relevant data using keywords, similar concepts, or relationships, providing a 'memory trace' for context. It is designed for developers building single or multiple AI agents that need to remember and share information without relying on external cloud services.
Available on PyPI.
Use this if you are a developer building AI agents and need a reliable, private, and lightweight memory system that can run directly on your machine or edge devices, enabling agents to remember past interactions and collaborate effectively.
Not ideal if you need a heavy-duty, cloud-based memory solution with advanced security compliance or massive data storage beyond typical edge deployments.
Stars
9
Forks
3
Language
Python
License
MIT
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Dependencies
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/gengxy1216/FlockMem"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
thedotmack/claude-mem
A Claude Code plugin that automatically captures everything Claude does during your coding...
Open-Source-Legal/OpenContracts
Humans and AI agents, building knowledge bases together. Self-hosted document annotation,...
volcengine/MineContext
MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）
omega-memory/omega-memory
Persistent memory for AI coding agents
winstonkoh87/Athena-Public
The Linux OS for AI Agents — Persistent memory, autonomy, and time-awareness for any LLM. Own...