ResearchTwin is an open - source federated platform that transforms researchers' papers, datasets, and code repositories into conversational digital twins. Based on a bimodal glial - neural optimization architecture, it supports collaboration between humans and AI agents to accelerate scientific discovery.

This project integrates Fujitsu's social digital twin and digital exercise API with the Model Context Protocol (MCP), enabling large language models (LLMs) to access Fujitsu's digital exercise API through natural language and achieve functions such as traffic simulation and scenario comparison.

MiniMe-MCP is an upgraded project for an AI development assistant. By creating a digital twin of the developer, it enables persistent memory and intelligent pattern recognition across projects. It solves the problem that traditional AI assistants lack memory and context understanding, provides personalized coding suggestions based on historical experience, supports multiple IDE tools, and can run locally to ensure data privacy.