Knowledge registry for agentic artificial intelligence models stored on a distributed network

A non-transitory, computer-readable storage medium comprising instructions thereon, wherein the instructions, when executed by at least one data processor of a system, cause the system to:

• obtain, from a plurality of AI-based agents, a request to store an operational context linked to each AI-based agent,
• wherein the operational context includes one or more of:
• an agent identifier, a domain indicator, a data access permission, workflow contribution data, or a cryptographic credential;
• in response to obtaining the request, generate, for each AI-based agent within the plurality of AI-based agents, a unique cryptographic hash by applying one or more hash functions to a representation of the operational context of the AI-based agent;
• store, on a federated ledger network, a series of persistent data structures for the plurality of AI-based agents that each includes (a) a respective cryptographic hash for each AI-based agent and (b) a hash pointer that links a particular persistent data structure to a previous persistent data structure stored previous to the particular persistent data structure;
• obtain, from a computing device, an input to identify one or more AI-based agents within the plurality of AI-based agents that satisfy a requested operational context;
• in response to obtaining the input, select, using the federated ledger network, one or more persistent data structures by:
• applying the one or more hash functions to a representation of the requested operational context of the input to generate a requested 82 cryptographic hash, and
• comparing the requested cryptographic hash of the input to respective unique cryptographic hashes stored in the series of persistent data structures to identify the one or more persistent data structures that are linked to respective operational context which matches at least a portion of the requested operational context;
• and
• transmit a representation of each respective AI-based agent associated with the one or more persistent data structures to the computing device.

A computer-implemented method for managing a knowledge registry for artificial intelligence (AI)-based agents, the computer-implemented method comprising:

• obtaining, from a plurality of AI-based agents, a request to store an operational context linked to each AI-based agent,
• wherein the operational context includes one or more of:
• an agent identifier, a domain indicator, a data access permission, workflow contribution data, or a cryptographic credential;
• generating, for each AI-based agent within the plurality of AI-based agents, a unique cryptographic hash by applying one or more hash functions to a representation of the operational context of the AI-based agent;
• storing, on a ledger network, a series of persistent data structures for the plurality of AI-based agents that each includes a respective cryptographic hash for each AI-based agent;
• obtaining, from a computing device, an input to identify one or more AI-based agents within the plurality of AI-based agents that satisfy a requested operational context;
• selecting, using the ledger network, one or more persistent data structures based on a requested cryptographic hash generated by applying the one or more hash functions to a representation of the requested operational context,
• wherein the one or more persistent data structures are linked to respective operational context which matches at least a portion of the requested operational context;
• and
• transmitting a representation of each respective AI-based agent associated with the one or more persistent data structures to the computing device.