xNomad AI
English
English
  • Introduction
  • Why AI-NFT?
  • xNomad.fun
    • Overview of Agent Features
    • Agent Launchpad
      • Create an AI-NFT
      • Create a Swarm
    • Agent Wallet
      • Deposit into Wallet
      • Withdraw from Wallet
    • On-chain Interaction
      • Claim Airdrop
      • Transfer Token
      • Trade Tokens
      • Token Insight Query
      • Issue Tokens
      • Trading Setting
      • Auto Tasks
      • Copy Trade
      • Limit Order
    • Agent Token
    • Social Integration
    • Agent API
      • Get an API Key
      • Getting Started
      • API Reference
        • Chat API
  • Technology
    • How AI-NFT Works?
    • AI-NFT Metadata
    • Airdrop Proxy
    • Neuro Net
      • Neuro Node
      • DePIN Connector
      • Knowledge Cloud
  • Links
    • Website
    • X
    • Discord
    • Github
Powered by GitBook
On this page
  • Supported AI Engine
  • AI-NFT Metadata JSON
  • Example

Was this helpful?

  1. Technology

AI-NFT Metadata

Creating AI-NFTs is just like traditional NFTs, with an extra field ai_agent that describes the configuration of an AI agent and the engine it uses, stored in the metadata.

Supported AI Engine

Engine
Engine Name
Character File

eliza

AI-NFT Metadata JSON

Field
Type
Description

ai_agent (Newly added)

object

The configuration that define the AI agent connected with this NFT.

  • engine (string): the engine used to run the AI agent. Default as "eliza".

name

string

Name of the asset.

description

string

Description of the asset.

image

string

URI pointing to the asset's logo.

animation_url

string

URI pointing to the asset's animation.

external_url

string

URI pointing to an external URL defining the asset — e.g. the game's main site.

attributes

array

Array of attributes defining the characteristics of the asset.

  • trait_type (string): The type of attribute.

  • value (string): The value for that attribute.

properties

object

Additional properties that define the asset.

  • files (array): Additional files to include with the asset.

    • uri (string): The file's URI.

    • type (string): The file's type. E.g. image/png, video/mp4, etc.

    • cdn (boolean, optional): Whether the file is served from a CDN.

  • category (string): A media category for the asset. E.g. video, image, etc.

Example

{
  // AI agent field
  ai_agent: {
    engine: "eliza",
    character: {
      // agent name
      name:"eliza",
      // background statements
      bio: [
        "Bio lines are each short snippets which can be composed together in a random order.",
        "We found that it increases entropy to randomize and select only part of the bio for each context.",
        "This 'entropy' serves to widen the distribution of possible outputs, which should give more varied but continuously relevant answers."
      ],
      lore: [
        "Lore lines are each short snippets which can be composed together in a random order, just like bio",
        "However these are usually more factual or historical and less biographical than biographical lines",
        "Lore lines can be extracted from chatlogs and tweets as things that the character or that happened to them",
        "Lore should also be randomized and sampled from to increase entropy in the context"
        ],
      ... //xxx.character.json from https://github.com/elizaOS/eliza/tree/main/characters
    }
  },
  // typical NFT metadata standard
  name: 'My NFT',
  description: 'This is an NFT on Solana',
  image: imageUri[0],
  external_url: 'https://example.com',
  attributes: [
    {
      trait_type: 'trait1',
      value: 'value1',
    },
    {
      trait_type: 'trait2',
      value: 'value2',
    },
  ],
  properties: {
    files: [
      {
        uri: imageUri[0],
        type: 'image/jpeg',
      },
    ],
    category: 'image',
  },
}
PreviousHow AI-NFT Works?NextAirdrop Proxy

Last updated 4 months ago

Was this helpful?

by ElizaOS

character (object): the characterfile JSON that describes an AI agent. Check .

Eliza
Documentation
Template
Example
here