Decentralised
AI Apps

Build and deploy powerful agentic AI Applications powered by the Decentralised SubQuery Network using the SubQuery AI Apps Framework

Introducing the SubQuery AI App Framework

The AI App Framework allows you to build, deploy, and run production agentic AI apps on the SubQuery Network in a trusted and decentralised environment.

AI Apps are self contained and easily scalable AI agents that you can use to power your intelligent applications. Using the latest LLMs, they are sandboxed to a trusted runner and can be easily distributed and scaled horizontally across the SubQuery Network.

Learn more about how to build, deploy, and run your own AI Applications to power your next intelligent web3 dApp.

Start building now

Driving an AI revolution

The world has woken to the potential AI brings for transforming the way we approach everything we do, across all industries, including within web3.

SubQuery is the infrastructure provider for decentralised AI, allowing you to quickly deploy your own open source AI Apps to production infrastructure to power the next generation of intelligent applications.

Your private AI workloads and agents are distributed across a decentralised network of inference and infrastructure providers, and securely processed in a decentralised way.

Your own custom AI Applications

Anyone can build intelligent dApps with the SubQuery AI App framework, providing a shortcut for developers to start incorporating AI into their applications in a decentralised and secure way today.

SubQuery's AI App Framework is a powerful but intuitive SDK to help you build advanced AI applications in minutes. It's built on typescript, is extremely easy to use, and supports advanced features like RAGs and function tooling.

Support for the latest AI models, RAGs, and Function Tooling

With both Ollama and OpenAI support, you can choose the best AI model for your use case. The AI App Framework also supports RAGs and Function Tooling, allowing you to build advanced AI applications in minutes that can connect to and integrate with your real-world applications.

Deep integration with the SubQuery Indexing SDK

Users will be able to run conversational queries against their custom indexed datasets using the latest AI models, and get answers that can be explained in plan text. This will help unlock detailed web3 insights for those without a data engineering background.