OpenVector
  • OpenVector
  • Introduction
    • Our Thesis
    • Our Solution
    • Other Approaches
    • Benchmarks
  • Network Architecture
    • Overview
    • Networking
    • Deploy Compute Node
    • Deploy CoFHE Node
    • Deploy Client Node
  • Quick start
    • Overview
    • Setting up Client Node
    • Encrypting Data
    • Tensor Multiplication
    • Decrypting the Ouput
    • Verifying the Output
    • Running the Program
  • Tutorials
    • Building MLP Block
  • Use Cases
    • Confidential LLM Inference
    • Training on Encrypted Data
    • Vector Search on Encrypted Data
    • Encrypted Data Access Control
  • API references
    • CryptoSystem Interface
    • ClientNode Class
    • ComputeRequest Class
    • ComputeResponse Class
  • PYTHON API REFERENCES
    • Overview
    • Tensor
    • nn.Module
    • nn.Functional
  • Contribution
    • Call for Research
    • CoFHE Library
Powered by GitBook
On this page

OpenVector

NextOur Thesis

Last updated 5 months ago

Bitcoin exemplifies sovereign money by operating on a decentralised network of nodes, granting users true ownership of their assets without reliance on centralised intermediaries. Similarly, achieving sovereignty in AI requires eliminating centralised points of control. Current AI agents, hosted through API providers or within Trusted Execution Environments (TEEs), lack this sovereignty. The TEE manufacturer or host retains ultimate control, with the ability to terminate operations at any time. To create truly sovereign and autonomous AI agents, it is essential to build a decentralised network of nodes that ensures independence from external influence, including that of the operator. We introduce OpenVector, a decentralised computing network designed to bring the principles of sovereignty and decentralisation to AI. OpenVector enables Large Lan- guage Model (LLM) computations to occur entirely within an encrypted domain using a novel cryptographic primitive called CoFHE (Collaborative Fully Homomorphic Encryption). This ensures fast and secure computation while decentralising the decryption key, addressing the twin challenges of data privacy and centralisation. This comprehensive guide is designed for anyone who wants to explore how OpenVector works and learn about building sovereign AI system using the network.

Jump right in

Introduction

Learn about OpenVector initiative

Network Architecture

Learn about node types and process to deploy them

Tutorial

Learn about APIs usage provided by OpenVector

Use Cases

Learn about apps you can build using OpenVector

Contribution

Learn about supporting OpenVector initiative

Page cover image