Nexus STC: Distributed search engine and AI tools that grant access to knowledge (github.com)

The Nexus STC project has launched a distributed search engine and AI toolkit aimed at providing free access to a wealth of academic literature and fictional works. It combines the capabilities of the Summa search engine with databanks hosted on the InterPlanetary File System (IPFS), enabling users to perform searches without downloading entire datasets. This initiative supports developers by allowing them to set up their own STC instances locally, utilize a browser-based interface, and access high-quality scholarly texts programmatically through Python or Telegram bots. Significantly, Nexus STC's decentralized architecture addresses issues of data censorship and loss that can occur with centralized servers. The system includes features such as an easy-to-use API for accessing scholarly publications, integration with AI tools for data analysis, and plans for global replication to ensure widespread access. Additionally, it aims to create a community-driven platform where users can engage in discussions about scientific topics and challenge copyright issues surrounding scholarly work. This innovative approach not only enhances knowledge accessibility but also promotes collaborative learning and research within the AI/ML community.