Block, Anthropic, and OpenAI Launch the Agentic AI Foundation

An initiative to advance open source agentic AI under the Linux Foundation umbrella

Today, the industry is making a pivotal choice. Block, Anthropic, OpenAI, and other leaders in AI are launching the Agentic AI Foundation (AAIF) to ensure agentic AI develops as an open, collaborative ecosystem. Agentic AI refers to artificial intelligence systems that can take initiative, make decisions, and act independently to achieve goals with minimal human direction.

The AAIF is a vendor-neutral home for open source agentic AI projects where no single company dominates, providing funding for critical community programs and research, and building open protocols that let systems from different builders work together seamlessly. Block is contributing its open source agent goose to the AAIF, along with Anthropic’s Model Context Protocol (MCP) and OpenAI’s AGENTS.md.

In addition to the three founding members, the AAIF’s top tier members include Microsoft, Google, Bloomberg, Amazon Web Services, and Cloudflare. Gold tier members include Arcade.dev, Cisco, Datadog, Docker, JetBrains, Oracle, Runlayer, SAP, Snowflake, Temporal, Tetrate.io, and Twilio Inc. Silver members of the AAIF include Chronosphere, Cosmonic, Elasticsearch, Eve Security, Hugging Face, Kubermatic, KYXStart, LanceDB, NinjaTech AI, Obot.ai, Prefect.io, Pydantic, Spectro Cloud, Inc., Stacklok, SUSE, WorkOS, and ZED.

AI systems represent one of the most significant technological shifts in decades. These systems are fundamentally reshaping how developers build software, how businesses operate, and how people solve complex problems. Use of autonomous agents promises to accelerate this even further.

But we're at a critical juncture. We have an unprecedented opportunity to shape how this technology develops. Will we build open, interoperable infrastructure that serves everyone? Or will we see fragmentation that limits this powerful technology's potential? Without collaborative open development, we risk missing the full potential of agentic AI where everyone benefits thanks to open standards, open protocols, and open systems on which other tools are built. We also risk concentrating the power in the hands of a few, which dampers competition and restricts accessibility. In a proprietary, siloed ecosystem, breakthrough ideas can't easily build on each other, integration challenges slow enterprise adoption and limit use cases, accessibility barriers prevent smaller organizations from benefiting, and research limitations slow academic and independent innovation.

History proves there’s a better path. The Internet, Linux, and the Web succeeded precisely because they were open. They empowered anyone with talent and determination to build, innovate, and create value on top of open infrastructure. Agentic AI deserves the same opportunity. We hope that the AAIF can become what the W3C is for the Web: a set of standards and protocols that guarantee interoperability, open access, and freedom of choice with open source reference implementations.

The Agentic AI Foundation provides a neutral home where companies, researchers, and independent developers can collaborate on open source agentic AI.

Following the Linux Foundation's trusted governance model, AAIF will operate on several core principles:

Open Governance: AAIF operates under a transparent and inclusive governance model where contributors from all backgrounds are empowered to shape the direction of the foundation and its projects. Decisions, policies, and criteria are open and accessible to members.

AI Innovation: AAIF encourages agentic AI innovation and exploration from a diverse and collaborative ecosystem of open source developers, researchers, and practitioners. We move at the speed of AI, keeping governance small and responsive.

Sustainability and Neutrality: AAIF provides neutral infrastructure and funding mechanisms to ensure long-term sustainability of projects. Project inclusion is based on demonstrated adoption, quality, and community health - not how well funded it may be.

Focused, not broad: The AAIF exists to further open source agentic AI - not to cover all of open source AI, machine learning, or data science.

AAIF launches with contributions from Block, Anthropic, and OpenAI:

goose, Block's open source agentic AI framework, will transition to community governance under AAIF. Since its release earlier this year, goose has become a reference implementation for Anthropic's Model Context Protocol (MCP) and has attracted thousands of developers worldwide. Under AAIF, goose will maintain its open source license and commercial-friendly terms while gaining the benefits of neutral governance and broader community input.

Model Context Protocol (MCP), developed by Anthropic, is an open protocol that enables seamless integration between AI systems and external data sources, providing a standardized way for AI agents to access context. MCP demonstrates AAIF's potential as the neutral hub for cross-industry agentic AI standards. From MCP’s very first release, Block engineers have been active contributors, and several continue to participate as members of the MCP steering committee.

AGENTS.md, developed by OpenAI, is an open format for guiding coding agents. It is used by more than 20,000 open source projects and serves as a README for agents: a dedicated, predictable place to provide the context and instructions to help AI coding agents work on projects.

Additional projects from other member organizations have been proposed and are being evaluated to join, and will be selected based on demonstrated adoption, strong governance, and alignment with AAIF's mission to advance open source agentic AI.

AAIF succeeds only if it truly represents the community. Whether you're a developer, researcher, company, or simply someone who believes AI should be open, there are multiple ways to participate:

Contribute to projects: All AAIF projects welcome community contributions. Check project repositories for contribution guidelines and good first issues.

Join the conversation & propose new projects: Have an agentic AI project that could benefit from neutral governance, foundation support, collaboration with leaders in agentic AI, and more visibility? Projects that promote the agentic AI ecosystem, operate under OSI-approved open source licenses, demonstrate open governance, and foster community growth are welcome to apply. For more information about the AAIF and how to become a member, please visit AAIF.io.

Attend events: Participate in AAIF-sponsored conferences, hackathons, and meetups to connect with the community and learn about the latest developments.

The foundation's governance structure ensures that community voices matter, not just corporate interests. Technical decisions will be made by project maintainers and steering committees, with AAIF providing resources and neutral oversight.

The next decade of AI development will be defined by choices we make today. By establishing the AAIF, the industry is making a clear statement: agentic AI will be open, accessible, and community-driven. The world has repeatedly proven that open collaboration produces better outcomes than competition in isolation. The AAIF provides the structure for that open collaboration to flourish in agentic AI.

This isn't just about technology: it's about values. It's about ensuring that powerful tools serve everyone. It's about creating an ecosystem where the best ideas win, regardless of where they come from.

The future is being written in the open. Join us.