Interoperability

Function calling, now also called tool calling, lets an application describe external functions to a model, which then decides whether to emit JSON arguments for one of them — the route by which models reach data and actions outside their training data.

The Model Context Protocol (MCP) is an open standard for connecting AI assistants to the systems where data lives. Anthropic open-sourced it on 25 November 2024 and later donated it to the Agentic AI Foundation.

The Agentic AI Foundation is a Linux Foundation project launched in December 2025 to provide vendor-neutral governance for agent interoperability, security and accountability. It grew from three hosted projects to ten and passed 300 member organisations within a year.

The State Council is China's Central People's Government: the executive body of the highest organ of state power and the highest organ of state administration, led by a Premier who assumes overall responsibility.

NIST is a U.S. federal physical science laboratory founded in 1901 and now part of the Department of Commerce, which works on measurement science, standards and technology — and has recently become the home of the government's AI safety and evaluation work.

A non-profit founded in 1998 that stewards the Open Source Definition and, since 2024, the Open Source AI Definition, setting a shared standard for what counts as open source.

OWL is a W3C Recommendation published on 10 February 2004: a semantic markup language for publishing and sharing ontologies on the Web, giving software formal definitions of terms so it can process the meaning of information, not just display it.

ONNX is an open format for representing machine learning models, announced by Microsoft and Facebook in September 2017 so that developers can move models between frameworks instead of converting them between incompatible formats.

Prompt injection is an attack in which text inside a model's input overrides its original instructions, letting an adversary hijack a language-model application — including, as researchers showed in 2023, through content the application retrieves on its own.

GGUF is a binary file format introduced in 2023 by the llama.cpp project that packs model tensors and metadata into a single file, and is widely used for distributing quantized language models for local inference.

A UK government research body created in 2023 to study the most powerful AI models and AI safety, renamed in 2025 to focus on national security and serious crime. It advises government but has no regulatory power.

GPT Actions let a custom GPT call external APIs, turning a user's request into the JSON input an API needs. Introduced by OpenAI on 6 November 2023, they grew out of the plugins beta and rely on OpenAPI schemas plus authentication settings.

/llms.txt is a proposed standard file that a website publishes so AI agents can find clean, structured information about it. Jeremy Howard published the proposal on 3 September 2024, and a second version followed two years of adoption.

The Open Source AI Definition is a 1.0 standard, released by the Open Source Initiative in October 2024, that a model must meet to be called open source: reproducible design, disclosed training data, and freedom to use, modify and build on it.

AGNTCY is an open-source project, open sourced by Cisco in March 2025 and welcomed by the Linux Foundation in July 2025, that gives AI agents from different vendors shared infrastructure for discovery, identity, messaging and observability.

Google's 2025 open protocol for discovery, communication, and collaboration across agents from different vendors or frameworks.

An open protocol announced by Google on 17 September 2025 for securely initiating and settling payments carried out by AI agents across platforms, using signed Mandates as verifiable proof of a user's instructions.

An open standard released by OpenAI with Stripe in September 2025 that lets AI agents, people and businesses complete purchases together, and the basis of Instant Checkout in ChatGPT.

Agent Skills are folders of instructions, scripts and resources that Claude loads when they are relevant to a task. Anthropic introduced them on 16 October 2025 and donated the open standard to the Agentic AI Foundation in October 2026.

OpenSandbox is a general-purpose sandbox platform for AI applications, contributed by Alibaba to the Agentic AI Foundation. It offers multi-language SDKs, a unified sandbox API, Docker and Kubernetes runtimes, and a protocol that lets teams plug in custom runtimes.

Open Responses is an open specification and ecosystem, based on the OpenAI Responses API, that gives applications one shared schema for calling models, streaming results and composing agentic workflows across providers.

ACP (Agent Communication Protocol) is an open protocol for agent interoperability, connecting AI agents, applications and humans through a standardised RESTful API. It was developed under the Linux Foundation alongside BeeAI and now sits within A2A, with a migration guide for existing users.

The National Development and Reform Commission is a ministerial-level department of China's State Council that drafts and implements economic and social development plans, manages investment and coordinates macro-economic policy. It descends from the State Planning Commission established in 1952.

A multi-agent system is a computing system made of several interacting intelligent agents that coordinate to solve problems too hard for a single agent. Recent frameworks built on large language models let such agents talk to each other.

The Semantic Web is a W3C standards effort that uses RDF and OWL to describe data so different applications, enterprises and communities can share and reuse information, moving from research toward practical tools.

A jailbreak is an adversarial prompt that gets a safety-trained model to produce behaviour its training was meant to prevent. A 2023 analysis by Wei et al. traced these failures to competing objectives and mismatched generalization.

Red teaming is the practice of actively probing a model for harmful or unwanted behaviour before deployment. A 2022 method by Perez and colleagues automated it by using one language model to generate test cases for another.

AG-UI is an open, event-based protocol that connects AI agents to user-facing applications, standardising how agent state, UI intents and user interactions flow between an agent backend and a front end.

Content provenance is a checkable record of where a piece of media came from and how it was edited, attached to the file itself. The C2PA, founded in 2021 by Adobe, Arm, BBC, Intel, Microsoft and Truepic, publishes the technical standard behind it.

Text watermarking embeds a hidden statistical signal in generated text so that a short span of tokens can later be identified as machine output, while the text still reads normally to people.

OpenEnv is an open framework and community hub from Hugging Face for building reinforcement-learning environments as containerized services that expose an agent interface, MCP and the Gym training protocol. It was contributed to the Agentic AI Foundation in October 2026.

OASF is a standardized, extensible schema system from the AGNTCY project for describing AI agent attributes, skills and capabilities in machine-readable records, so that agents can discover and understand each other across protocols.

SLIM (Secure Low-Latency Interactive Messaging) is a secure transport protocol for agent traffic. It carries A2A, MCP and SLIMRPC over one encrypted overlay, lets agents connect outbound and be reached by name, and publishes SDKs for six languages.

NLWeb is a set of open protocols and open-source tools that give websites a conversational interface, returning Schema.org JSON over natural language and doubling as an MCP server so the same API serves people and AI agents.