What is A2A (Agent-to-Agent)?
A2A is an open protocol that lets one AI agent find another, send it work, follow its progress, and receive the result.
Standards · 20 sourced records
Which rules do AI agents follow?
AI agent standards are shared rules for how agents talk, use tools, prove who they are, and stay within safe limits. Some are firm specs. Others are drafts. This index tells you which is which, names the group behind each item, and links to its published source.
20 shown
What is A2UI?
A2UI is an open format that lets an agent describe an interface, such as a form or card, so a trusted application can draw it with its own components.
What is AG-UI?
AG-UI is an open protocol that carries messages, events, shared state, and user actions between an agent and the application a person sees.
What is Agent Identity Protocol?
Agent Identity Protocol is a draft set of rules for proving an AI agent's identity, permissions, delegation, and accountability.
What is Agent Payments Protocol?
Agent Payments Protocol is an open set of rules for payments that an agent starts only after a user gives clear authority.
What is Agentic Resource Discovery?
Agentic Resource Discovery is an open specification for publishing and finding tools, skills, agents, and other AI capabilities on the web.
What is Agentify?
Agentify is a command-line tool that turns an OpenAPI description into instructions and tool files for several AI-agent platforms.
What is AGENTS.md?
AGENTS.md is a file that tells coding agents how to work inside a particular software repository.
What is HCS (Hashgraph Consensus Service)?
Hashgraph Consensus Service gives agents shared rules for identity, messages, and ordering records on Hedera's public network.
What is MCP (Model Context Protocol)?
Model Context Protocol is an open standard that gives AI applications one consistent way to connect models with tools and data.
What is MCP Apps?
MCP Apps lets a tool return an interactive form, chart, or dashboard that appears inside an agent conversation.
What is MCP Gateways?
MCP Gateways sit between agents and their tools to control access, route requests, and record what happened.
What is MCP Tasks?
MCP Tasks extends Model Context Protocol so an agent can start work that continues after the first request ends.
What is Microsoft Agent Governance Toolkit?
Microsoft Agent Governance Toolkit applies runtime policies and safety checks to agents built on Azure.
What is NIST AI Agent Standards Initiative?
The NIST AI Agent Standards Initiative develops guidance for agents that must work together, prove identity, use authority safely, and resist attacks.
What is OpenAI Function Calling?
OpenAI Function Calling lets a model request a named software function and supply arguments that follow a JSON schema.
What is OpenAPI?
OpenAPI is a widely used specification for describing web application programming interfaces in a machine-readable form.
What is Tool Use (Anthropic)?
Anthropic Tool Use lets Claude request a named tool and return structured arguments for software to execute.
What is Universal Commerce Protocol?
Universal Commerce Protocol is an open standard for how agents discover products, complete purchases, and handle what happens after a sale.
What is Verifiable Intent?
Verifiable Intent records what a user allowed an agent to do in a form that later changes cannot quietly alter.