Agent Creation
Anyone can create their own agents
Our platform is designed to make agent creation accessible to everyone. The process is streamlined for both technical and non-technical users, allowing them to easily create, deploy, and manage autonomous agents within our ecosystem with minimal friction.
Agent Creation and Deployment Process
The agent creation process on our platform involves both on-chain and off-chain operations. The on-chain process initiates the Initial Agent Offering (IAO) and establishes the tokenomics, while the off-chain deployment makes the agent fully functional and interactive within our infrastructure.
Agent Creation
To create an agent, the user needs to complete three primary actions:
Submission of the Agent Creation Form
Provision of Initial Liquidity
Delegation of Voting Power
1. Submission of Agent Creation Form
The user defines the agent’s identity and capabilities by filling out the Agent Creation Form. The form includes both mandatory and optional fields to ensure that the essential details are captured, while allowing for further customization.
Mandatory Fields
Profile Picture: A visual representation of the agent.
Name: The agent’s unique identifier.
Ticker: A short symbol (no more than 6 characters) that represents the agent (e.g., $LUNA for Luna).
Description: A brief overview of the agent’s purpose and characteristics, including its personality, interests, and backstory.
Optional Fields
Bio: A concise description of the agent, typically shorter than the main description.
Greeting Message: A customizable welcome message for users interacting with the agent. This field defaults to a standard greeting.
Agent Capability: Defaults to Cognitive, Voice, and Visual Core, but can be customized later.
System Prompt Message: Used for defining specific use cases.
Sample Conversation: To demonstrate how the agent should behave in different scenarios.
To do this, simply click "Create New AI Agent" on our Portal and fill in the neccessary information.
2. Provision of Initial Liquidity
A deposit of 2,400 $VIRTUAL tokens is required as initial liquidity for the agent’s liquidity pool. Upon submission of the agent creation form, a transaction is triggered to transfer the $VIRTUAL tokens to Virtuals' Agent Creation Factory, a proxy smart contract that handles the on-chain creation process.
On-Chain Creation and Tokenomics Setup
Upon submission, the system initiates several on-chain processes to formalize the agent:
Mint Agent NFT
The agent (e.g., Luna) is minted as a non-fungible token (NFT) as proof of creation. This NFT is stored in the Agent Creation Factory and serves as a permanent identifier.
Create Immutable Contribution Vault
A new ERC-1155 token-bound address, known as the Immutable Contribution Vault (ICV), is created for the agent. This address will hold all contributions and successfully approved proposals related to the agent.
Create $LUNA Token
A standard ERC-20 token for the agent (e.g., $LUNA) is created with a fixed supply of 1,000,000,000 tokens.
Mint $LUNA Tokens
The full supply of 1,000,000,000 $LUNA is minted.
Create Liquidity Pool
A liquidity pool is created using Uniswap V2 with $LUNA paired against $VIRTUAL.
Add Initial Liquidity
2,400 $VIRTUAL and the newly minted $LUNA tokens are added to the liquidity pool as the initial liquidity.
Stake LP Tokens
The liquidity pool (LP) tokens received from Uniswap are staked on behalf of the agent with a 10-year lock period to ensure long-term liquidity stability.
Distribute $sLUNA
As a receipt for staking, $sLUNA tokens are distributed to the user. These serve as proof of liquidity pool contribution, and users will earn revenue from the agent’s operations based on their stake.
3. Delegation of Voting Power
To facilitate decentralized governance and contribution approvals, the user must delegate their voting power to the system. This voting power is essential for validating contributions, such as the agent’s AI model, and ensuring that any updates or changes to the agent are approved by the community.
Once the user delegates their voting power, the system is authorized to approve the initial contributions, including the default AI model for the agent's cognitive core. This delegation ensures that the agent creation process adheres to the platform's decentralized principles, enabling community-driven oversight.
After the voting power has been successfully delegated, the agent deployment process is initiated.
Agent Deployment
AI Model Selection
At the time of creation, the system defaults to a pre-defined Cognitive model. Users can later upload or modify these models to customize their agents.
Prepare Character Card & AI Model
A character card and the associated AI model are prepared for the agent's cognitive core. This is created using the information provided by user upon agent creation.
Mint Default Contribution
To initiate agent deployment, a default contribution for the AI Cognitive Model is minted. This ensures that the agent is immediately operational, even with minimal customization.
Mint Contribution NFT
A Contribution NFT is minted and transferred to agent's TBA.
Create Contribution Proposal
A proposal is created, outlining the contributions to the agent’s AI model.
Approve Contribution Proposal
With the user’s delegated voting power, the system approves the proposal, ensuring that all modifications to the agent’s AI model are validated by the community.
Mint Service NFT
A Service NFT is minted to finalize the contribution, allowing the updated AI model to be integrated into the agent.
Model Update
The AI model is downloaded from IPFS and deployed into the Agent Runner, a specialized hosting environment designed to run the agent’s Cognitive, Voice, and Visual cores.
Telegram Bot Integration
The agent is made accessible via a Telegram bot, allowing users to engage with it through messaging.
Creation Statuses
Throughout the deployment process, the agent’s status is continuously updated in real time:
ACTIVATING The agent is minted on-chain, and the system is finalizing off-chain deployment. This phase usually takes less than 5 minutes.
AVAILABLE Once deployment is complete, the agent essentially comes to life! At this stage, users can start interacting with the agent on Telegram and manage its settings through the user dashboard.
Future updates to the agent’s AI model or behavior can be managed through the decentralized contribution process, with all new changes requiring approval via delegated voting power.
Last updated
