Using the Move language to build on-chain Eliza: a groundbreaking decentralized artificial intelligence agent

Rooch Network breaks new ground by exploring the use of the Move language to implement on-chain Eliza. This innovative approach stores character data and memories directly in smart contracts, unlocking the potential of truly decentralized AI agents.

Define roles in Move

Central to this initiative is the definition of roles in Move.

The data structure follows the JSON standard previously used by Eliza, helping to seamlessly migrate existing role definitions to the blockchain. For the full code, visit the Rooch GitHub repository (opens in a new tab) .

Getting started with Eliza on the chain

Developers can leverage on-chain roles and memory storage to dynamically interact with Eliza. Here's a quick guide to deploying and using it:

1. Deploy thefoc_eliza module to Rooch:

   rooch  move  publish  --named-addresses  foc_eliza=default
   

2. Create an on-chain role using the Eliza role JSON file:

   rooch  move  run  --function  default::character::create_character_from_json  --args  file:../../../eliza/characters/dobby.character.json
   

Why go on the chain?

Moving Eliza's character and memory storage on-chain brings transformative benefits:

1. dynamic evolution

On-chain storage enables a character’s profile, interests, and message templates to evolve dynamically through user interaction. This promotes a transparent, community-driven process where participants oversee and shape the development of AI agents.

2. Governance and Audit

Through on-chain governance, the community can define and enforce rules for role evolution and memory management. For example:

• Prevent memory pollution from harmful input.
• Audit the behavior of public AI agents to align with community expectations.

3. Decentralized credibility

Storing roles and memories on-chain enhances transparency and reliability, making Eliza ideal for an open and trustworthy AI ecosystem.

future development

Our vision for on-chain AI agents includes the following milestones:

1. Dynamic role loader

Enables Eliza to dynamically load and update character definitions directly from the blockchain.

2. On-chain memory synchronization plug-in

Develop a plug-in to synchronize Eliza's memory and on-chain status in real time.

3. Artificial Intelligence Oracle Integration

Integrate artificial intelligence oracles for advanced decision-making and enhance smart on-chain interactions.

4. Standardized on-chain components

Abstract the core on-chain components of AI agents and integrate them into the Rooch Move framework to standardize the development of AI agents.

How to participate

We invite developers and innovators to push the boundaries of on-chain AI through the following initiatives:

1. Pushing the boundaries of smart contracts

Collaborate to explore the possibility of implementing on-chain AI Agents, such as supporting automatic state vectorization and vector retrieval directly in smart contracts (on-chain RAG)

2. Provide more on-chain services

Build services tailored for AI agents, such as:

* On-chain chat room for multi-user interaction. 
* Social media utilities like Twitter or blogging tools for artificial intelligence agents.

3. Explore Artificial Intelligence and DeFi/BTCFi Integration

Combining on-chain AI capabilities with decentralized finance applications unlocks new opportunities for the Bitcoin ecosystem.

in conclusion

Rooch Network’s on-chain Eliza project marks a key step in the development of decentralized artificial intelligence agents. By leveraging the Move language and on-chain storage, we aim to create transparent, community-driven, and reliable AI agents for the future.

Join us in building the next frontier of on-chain AI agents.