Agentic AI Foundation Announces Four New Projects: Agent Skills, Open Responses, OpenEnv, and OpenSandbox

AAIF reaches 10 projects in its first year, with new contributions from Alibaba, Anthropic, Hugging Face, and OpenAI

Summary

• AAIF announced four new projects: Agent Skills, contributed by Anthropic; Open Responses, contributed by OpenAI; OpenEnv, contributed by Hugging Face; and OpenSandbox, contributed by Alibaba.
• AAIF has grown from three projects to 10 in its first year.
• Announced at AGNTCon + MCPCon North America, the new projects extend AAIF’s portfolio across agent capabilities, model interoperability, training environments, and secure execution, all under open, vendor-neutral governance.
  

The new projects address four layers of the agentic stack: how agents gain new skills, how applications talk to models across providers, how agents are trained and evaluated, and where agents run safely. They join the Agent2Agent (A2A) protocol, Agent Router, agentgateway, AGENTS.md, goose, and the Model Context Protocol (MCP) as AAIF projects, all operating under AAIF’s open, vendor-neutral governance.

“A year ago, AAIF launched with three projects and a bet that agentic AI needed a neutral home to thrive. Today we host 10,” said Manik Surtani, CTO and co-founder of the Agentic AI Foundation. “Agent Skills, Open Responses, OpenEnv, and OpenSandbox each cover a different part of that stack, from how agents gain capabilities to where they run, and four different companies chose to contribute them to neutral governance. That’s the job of this foundation: giving the community one place to build shared standards, protocols, and infrastructure, with no single company controlling the outcome in a way that puts the community first.”

The announcement coincides with AGNTCon + MCPCon North America, taking place October 22-23 at the San Jose McEnery Convention Center. The conference brings the open agentic AI community together to share implementation experience, discuss common challenges and advance approaches to building, securing and operating AI agents.

New Projects

Agent Skills is an open format for giving agents new capabilities and domain expertise. Skills package instructions, scripts and resources in a reusable manner that agents can load on demand, making specialized know-how portable across agent products and platforms.

“Without the right context, even the most intelligent agents fall short. We launched Agent Skills a year ago to give developers and enterprises alike an open standard to make their agents more capable. Today, we're donating Agent Skills to the AAIF to ensure that anyone building with skills can shape what's next. The AAIF has done important work in giving the Model Context Protocol (MCP) a neutral home since we donated it less than a year ago, and alongside the AAIF, we're committed to continuing to invest in open source agentic tooling for builders everywhere.” – David Soria Parra, Co-Creator and Lead Maintainer of MCP, Anthropic

Open Responses is an open specification for building multi-provider, interoperable LLM interfaces, based on the OpenAI Responses API. It defines a shared schema, consistent streaming events and extensible tooling, so developers can describe requests and outputs once and run them across model providers with minimal translation.

“Open Responses is thrilled to be joining the AAIF to further our mission of helping developers build great products on today's language models through simple, clean, and unified interfaces. AAIF has an amazing track record of boosting important projects across the industry and we're excited to keep pushing the frontier of what builders can achieve.” – Steve Coffey, Member of Technical Staff, OpenAI

OpenEnv is an open framework and community hub for creating RL environments that makes them interoperable, plug-and-play, easy to build, easy to share, and scalable. It does this through a simple containerized service that exposes a familiar agent interface, MCP, and the training protocol that training libraries use, Gym.

“We believe, now more than ever, that democratizing AI requires a fully open stack. Reinforcement Learning environments are a fundamental part of that stack because they teach agents the capabilities they will use in the real world. The committee behind OpenEnv is proud to bring AAIF into Reinforcement Learning by sharing what we’ve built and used at; Hugging Face, Microsoft, Reflection, Meta-PyTorch, Fleet, Mercor, RadixArk, Modal, Prime Intellect, and more.” – Ben Burtenshaw, Machine Learning Engineer, Hugging Face

OpenSandbox is a general-purpose sandbox platform for AI applications. It offers multi-language SDKs, unified sandbox APIs and Docker and Kubernetes runtimes for use cases including coding agents, GUI agents, agent evaluation, AI code execution and reinforcement learning training. It includes a sandbox protocol that defines lifecycle and execution APIs, so teams can extend it with custom runtimes.

"While OpenSandbox was created at Alibaba, we don't want its future to be defined by a single company. By bringing the project to AAIF, we're creating a path for more developers and organizations to help shape how sandbox environments work across the agent ecosystem." – Xiaobin Xu, Head of Development Infrastructure, Alibaba

About the Agentic AI Foundation
The Agentic AI Foundation (AAIF) is the neutral home for open standards, protocols, and infrastructure in agentic AI. With founding projects including MCP, goose, and AGENTS.md, AAIF governs the core standards, protocols, and frameworks that enable agents to operate interoperably across platforms. Through transparent governance and broad industry participation, AAIF is driving adoption and ensuring agentic AI infrastructure evolves openly, neutrally, and at production scale. For more information, please visit aaif.io.

Media Contact
Sarah Zonouzi
Agentic AI Foundation
pr@aaif.io