AI721
Make AI agent indexable and verifiable on the blockchain.
Last updated
Was this helpful?
Make AI agent indexable and verifiable on the blockchain.
Last updated
Was this helpful?
Version: 0.2
Last Updated: 2024-06-15
AI721 introduces a standard that extends the AI capabilities of ERC721. It's used to index AI agent on chain, describe the AI personality and copabilities of your AI agent, and verify if a specific personality belongs to a particular AI agent. This makes your AI agent become digital asset on the blockchain.
AI721 will not make any break changes on ERC721. It can be merged with ERC721, or deployed as an independent contract and associated with an existing ERC721 contract.
Yes, AI721 is essentially NFT(non-fungible token) with AI capabilities.
We call it AI-NFT for short.
LLMs enable everyone to create AI personalities with any prompt. You can create any kinds of characters with different personalities with some tools like . However, it's centralized, non-transparent, and unable to achieve consensus.
If we want to describe AI personalities in a decentralized environment , and access it without relying on any centralized 3rd parties, we need to define a standard to implement this process, ensuring that anyone can obtain the same AI personality through the same protocol.
AI721 is the key to make it happen.
In the AI721 protocol, the AI Personality of an AI-NFT is defined by these core components below:
LLM: The large language model that can comprehend and generate human language text. It provides basic AI capabilities for your AI-NFT.
Trait model: A collection-level function that inputs the AI-NFT's traits and outputs a set of prompt, defining the independent personality that is only related to its traits, as an initial state.
Memory: The memories, or knowledge that form the final AI personality, manifested through promps in conversation with the AI agent.
Public Memory: A predefined and public memory that anyone can use to form an AI personality.
Private Memory: A user-level private memory that shared with your AI agent, can be only read by the NFT owner.
AI721 defines a new kind of JSON metadata to describe an AI personality. The metadata standard includes three important parameters to index the AI personality. This metadata is different from the one for ERC721, and can be stored on-chain or off-chain.
llm
URI
The uri to access LLM that is stored in off-chain storages.
trait_model
string/URI
public_memories
URI
(Optional) The uri to access the list of public memories needed to form an AI agent.
workflow
URI
(Optional) The uri to access the workflow file that describes the action chain of an AI agent.
A typical traits array from the metadata of a certain NFT is like:
We need to convert it to:
Then the trait_model
could be like:
On the application side, after you retrieve trait_model
, you can render the final prompt by filling in specific traits data with Jinja2.
A single memory is described as a JSON file.
name
string
The name of this memory
description
string
(Optional) The description of this memory
logo
string
(Optional) The logo url or the memory
memory
string
The serialized form of this memory.
A workflow is a configuration described as a JSON file.
engine
string
version
number
(Optional) The engine version.
data
object
The DSL to describe the workflow of the AI agent.
Based on this design, AI721 can support various current and future AI agent workflow protocols, and use the corresponding engines to run AI agent services.
llm://{model}
Access a given LLM by calling APIs hosted by a party. This is only applicable for llm
.
For examples:
"gpt-4" means gpt-4 model or its extended versions provided by OpenAI.
"gemini-1.0" means gemini-1.0 model or its extended versions provided by Google.
"any" means any LLMs can be used.
*The name must follow the naming conventions used in the API parameters provided by major model manufacturers.
ipfs://{cid}
The resources stored in IPFS/Filecoin. e.g. ipfs://QmbWqxBEKC3P8tqsKc98xmWNzrzDtRLMiMPL8wBuTGsMnR
ar://{cid}
The resources stored in Arweave. e.g. ar://k2g_3kYsPx-meD-AlyHhkUDYbUczlZ-M-bsKO6_oqY4
http(s)://{domain}/{path}
An typical http(s) url to locate resources.
... More formats from DePIN partners
Call tokenURI
by tokenId of an AI721 contract, and pull the AI metadata of the NFT.
Retrieve the LLM by llm
and run as a service;
Retrieve the trait model by trait_model
. Input the traits set of the NFT to the model to obtain a set of prompt, and then integrate these prompt into the LLM you get in the previous step;
(Optional) Retrieve one of the public memories from the public_memories
, and integrate it into the LLM you get in the previous step. This allows you to quickly create a predefined AI personality.
(Optional) Retrieve workflow
and load it locally for the application layer to trigger at any time. If the workflow involves external LLMs, you can either replace them with the dedicated LLM from Step 4th or continue using the external LLM interface described by the DSL.
After these steps, you'll get your AI agent ready to use, with a pre-defined personality.
As what you have done for ERC721, you MUST implement tokenURI
and return a URI where we can find the metadata.
We recommend the application layer to firstly access AI metadata embedded in ERC721 contract to query AI personalities. If not found, then use AILinker to query.
Workflow: A workflow is defined as a structured sequence of operations that organizes tasks into manageable steps. Compatible with the data structure of the workflow on .
Check .
The prompt template that generates the final prompt from the traits and other storyline of AI-NFT, by using placeholders of the form ${trait_type}
, to define an independent and unique personality.
Check .
The application layer can choose from these memories to create specific AI agents, like a virtual lawyer, math teacher, or virtual girlfriend/boyfriend. Check and .
We use as the templating engine for trait model.{{Base}}, {{Eyes}}, {{Mouth}}
are all placeholders in the template that will be replaced with traits.Base
, traits.Eyes
and traits.Mouth
of a specific AI-NFT.
The engine that can run the workflow given by workflow.data
. For example, If the workflow originates from , or is compatible with this platform, set this field to “dify”.
The application layer can determine how to access these models' API endpoints, for example, by registering a developer account at
Check the .
Prepare AI metadata for your collection according to . If you want a quick start, you can choose from a selection of pre-trained AI metadata that we will make publicly available.