Overview
What is decentralized AI?
Decentralized artificial intelligence (DeAI or decentralized AI) is a form of AI and machine learning that utilizes blockchain technologies and decentralized protocols such as ICP. ICP enables truly decentralized AI by running services on-chain, providing a permissionless and secure way to run machine learning applications.
Canisters can be used to host AI services and run machine learning algorithms using popular AI/ML frameworks and libraries. HTTPS outcalls can be used to make API calls to external AI APIs like OpenAI.
ICP AI projects
Several community projects that showcase how to use AI on ICP are available:
ArcMind AI: An autonomous agent using Chain of Thoughts for reasoning and actions. Try the app in-browser.
ArcMind Vector DB: A vector database that supports text, image, and audio embedding.
DeVinci: An AI chatbot that uses an open-source LLM. Check out the canister yourself.
ICGPT: A React frontend that uses a C/C++ backend running an LLM fully on-chain. Check it out yourself.
ic-mnist: A sort of machine learning 'Hello, world!' running on ICP. Try it here.
ELNA AI: A fully on-chain AI agent platform and marketplace. Supports both on-chain and off-chain LLMs. Try it here.
Tensorflow on ICP: An Azle example that uses a pre-trained model for making predictions.
MotokoLearn: A Motoko package that enables on-chain machine learning.
Tract-IC-AI: An ICP variations of Tract.
Rust-Connect-Py-AI-to-IC: Open-source tool for deploying Python AI models.
Juno + OpenAI: An example using Juno and OpenAI to generate images from prompts.
AI resources
Machine learning programming:
Distributed AI compute:
Lightweight AI models:
Technical working group: DeAI
A technical working group dedicated to discussing decentralized AI and related projects meets bi-weekly on Thursdays at 5pm UTC. You can join via the community Discord server.
You can learn more about the group, review the notes from previous meetings, and ask questions on the DFINITY forum.