Skip to content

About OpenGradient

Upload, deploy, and run inference any AI model from anywhere within seconds: secure, permissionless, and fully decentralized.

What is OpenGradient?

OpenGradient is the first decentralized infrastructure platform for AI model hosting, secure execution, agentic reasoning, and application deployment.

OpenGradient’s novel heterogeneous compute architecture enables permissionless AI inference, statistical analysis, data processing, and agent execution to be securely and scalably run end-to-end from a smart contract. Accompanying the infrastructure are a Web2 platform and SDK which makes our infrastructure accessible to anyone.

OpenGradient empowers developers with the ability to seamlessly harness open-source models and leverage compute for features like risk management, ML optimization, AI agents, Sybil resistance, DeFi mechanism design, and more.

OpenGradient Products

  • ​OpenGradient Network: EVM-compatible blockchain network enables developers to host or run inference AI models, deploy applications, or run AI agents.
  • Decentralized Model Hosting: Decentralized filestore infrastructure allows anyone to permissionlessly access, upload, or download any models and immediately use them on the OpenGradient Network or SDK.
  • ​Model Hub: The Web platform is an interface to Decentralized Model Hosting. Users can upload, browse, and experiment with various models powered by OpenGradient's infrastructure. In the future, this will include hosting/deploying agents as well.
  • OpenGradient Research: In-house research team that builds models, customized AI oracles, or AI applications for clients. The team also open-sources a lot of this research to help create universal AI modeling primitives and public goods for Web3.

What can you do with OpenGradient?

You can build anything with OpenGradient. Here are a couple of examples:

  • Upload an AI or ML model and be able to run inference securely on-chain from a smart contract within seconds.
  • Build secure web2 AI applications by leveraging our Web2 platform and SDK​.
  • Create an on-chain AI-driven application secured from data access, to data pre-processing, inference computation, and data post-processing.
  • Create an LLM-backed AI agent within a smart contract.
  • Create composable AI model ensembles or mixture-of-expert applications.

OpenGradient 2024