Advancing Developing Growing Agentic AI Together.

The AAIF provides a neutral, open foundation to ensure this critical capability evolves transparently, collaboratively, and in ways that advance the adoption of leading open source AI projects

News and Views from the AAIF

5.28.26

OpenAI Launches Secure MCP Tunnels For Private Enterprise Agents 🔐🌉🧠: OpenAI launched Secure MCP Tunnel, enabling secure outbound-only access to private MCP servers without exposing internal infrastructure. —OpenAI
Snowflake Buys Natoma for Governed MCP Access ❄️🔐🧰: Snowflake is acquiring Natoma to add identity, policy, and audit controls for MCP-based agent access. —Snowflake
Red Hat and IBM put $5B Behind Open Source AI Infrastructure 🐧🔓🛡️: IBM and Red Hat launched Project Lightwell, focused on secure open source infrastructure for enterprise AI agents. —Red Hat

Subscribe to the Daily Agentic AI LinkedIn Newsletter →

Upcoming Events

In agentic AI, the real breakthroughs happen in the room.

Ideas move faster face-to-face, and trust is built in real time. AAIF is bringing the agentic AI community together through events around the world—turning conversations into collaboration.

View All Upcoming Events

Event Videos

Discover how the future of intelligent systems is unfolding—watch recordings from recent Agentic AI Foundation conferences and events.

Watch Videos

Blog and Announcements

May 29, 2026 in Blog

The Tool Abstraction Problem: Lessons Learned Building 1000+ MCP Tools

Most MCP tools are designed for programmers. Agents are not programmers. Building tools around tasks and intents, then obsessing over description quality, produces dramatically better selection accuracy and fewer failures…

May 28, 2026 in Blog

Datadog’s 5 Tips for Building AI Agents

Getting an AI agent to work is a different problem from getting it to run in production without someone watching it. Datadog built its first hundred agents across SRE, code…

May 27, 2026 in Blog

MCP Is Growing Up

The next MCP specification release candidate is a big one. The headline change is that MCP is becoming stateless at the protocol layer, but the more useful story is what…

Model Context Protocol

An open protocol that enables seamless integration between LLM applications and external data sources and tools.

goose

An open source, extensible AI agent that goes beyond code suggestions. Install, execute, edit, and test with any LLM.

AGENTS.md

A dedicated, predictable place to provide the context and instructions to help AI coding agents work on your project.

Submit a Project

Contribute to the future of open, community-driven AI by submitting your project proposal through the official GitHub process—your ideas can help shape a transparent and collaborative ecosystem for agentic technologies.

Submit Project Proposal

Members

Agentic AI Foundation would not be possible without the support, development efforts, and open collaboration of our members.

Founding Platinum Members

View Benefits View All Members