For the complete documentation index, see llms.txt. This page is also available as Markdown.

πŸ“ˆAbstract

Cluster Protocol is a unified AI infrastructure layer for the decentralized web and an orchestration layer for autonomous workflows. It consolidates three foundational primitives - AI model inference, tokenized data, and compute, into a single orchestration platform with one API, one settlement layer, and singular AI economy on Base (Ethereum L2).

The platform provides an AI inference gateway serving 500+ AI models across multiple modalities (text, image, audio, embeddings, reranking), a tokenized data marketplace where datasets are stored on IPFS and ownership is represented as on-chain NFTs with automatic revenue distribution, and a compute layer that provisions GPU resources for custom model hosting and fine-tuning workloads.

Payments across the stack are settled natively on Base via smart contracts, with support for x402, an HTTP-native micropayment protocol that enables AI agents and developers to pay per request without accounts, API keys, or pre-deposited balances.

Coupled with a browser based IDE, an prompt-to-dApp application layer built on top of Cluster's infrastructure, enables anyone to create, deploy, and distribute fully on-chain applications using natural language, consuming Cluster inference, data, and compute natively in the process.

This paper describes the architecture, components, and mechanisms of Cluster Protocol.

Last updated