Open Source Summit + Embedded Linux Conference North America 2026

In its fourth year, the State of Tech Talent report is now a landmark in the Linux Foundation’s research program. The report provides key insights for employers and practitioners to gain a realistic understanding of the talent landscape as it flexes to meet technical priorities for the current and upcoming years. The 2026 study, which will go live at Open Source Summit North America, examines the survey’s findings on which skills are truly influencing hiring decisions, what current hiring and skilling expectations are, and how AI and emerging technologies are impacting roles and career paths.

In this fireside chat, Anna Hermansen from LF Research and Clyde Seepersad from LF Education will discuss the survey findings from the wider perspective of their work and communities. Anna will review how recent LF research on AI, cloud native, and the Cyber Resiliency Act provides added insight into the tech talent market, and Clyde will lend his training expertise as SVP and general manager of the Linux Foundation’s education program. Both aim to provide wider context to frame the survey findings and distill for audience members the key takeaways to prepare for talent needs this year.

Special-purpose agentic systems can access proprietary enterprise information or private user information, such as financial, health, or employment data, that isn’t available to large public LLMs. But, by their nature, specialized agents are limited to specialized knowledge. However, more complex applications can be composed of several collaborating agents, each with a specific expertise.
Manual integration of information from several agents by users is possible, but time-consuming and clumsy, and the agents wouldn’t benefit from each other’s knowledge. A better approach would be for agents to converse directly with each other. A standard messaging protocol would enable independent agents to converse and collaborate on tasks.
This presentation will outline two protocols that enable multi-agent systems to collaborate. The first is the Linux Foundation’s Agent-to-Agent protocol, and the second is the Linux Foundation AI & Data Open Voice Interoperability Initiative’s Open Floor Protocol. We will describe each protocol and explain how they complement one another with demonstrations of collaborating agents.

AI agents don’t fail like traditional software. They don’t just throw exceptions, they drift. They misinterpret tools, invoke the wrong functions or behave differently across environments. When deploying Arm’s Open Source custom MCP server to power AI assistants for architecture development, migration, and optimization, we faced a critical question: how do we test a system built for nondeterministic interaction? In this talk, I’ll share how we moved from manual validation to a repeatable, CI-enforced testing strategy using Pytest and Testcontainers. We spin up real MCP server in Docker during tests, validating tool discovery, invocation, and protocol compliance end-to-end.
This isn’t about mocking LLM output. It’s about testing the contract between agents and tools. The key insight: treat your MCP server like production infrastructure, not experimental glue code. Because “it worked on my machine” is not a deployment strategy.
Session takeaways:
• A demo of Arm’s Open Source MCP server(github.com/arm/mcp)
• Why unit tests are insufficient for agent-facing systems
• How we run MCP server inside containerized test environments
• How GitHub Actions automate CI integration testing

This quick tutorial walks through the camera calibration/configuration, uxrce dds service, Isaac ROS setup, and PX4 parameters required to fuse stereo VIO in EKF2. The platform is a quadcopter with an Ark Jetson computer.

This talk dives in to what you don't know about QGC. Hidden features, how to make changes, why things are the way they are.

We will go over: Text overlay on videos, Advanced Vs. Standard Mode, new joystick integrations, new bluetooth connections support, AND MORE!!!

Learn the intricacies of QGC as you never have before while also discovering brand new features!