Hardware creativity: Does the submission connect a device type that has not been integrated before? Is the choice of hardware imaginative or unexpected?

Protocol correctness: Does the adapter correctly implement the OAHL lifecycle? Does it return conformant result envelopes? Does it handle failure paths cleanly?

Agent intelligence: How well does the AI agent reason about and utilise the hardware capability? Does it do something more than a simple script would?

Real-world relevance: Does the use case address a genuine problem or opportunity? Could someone deploy this in a real setting?

Documentation quality: Is the adapter documented well enough that another developer could use it? Is the README clear on setup, configuration, and capabilities?

Rules

Projects must use OAHL as the hardware interface layer. Wrappers around other protocols are acceptable as long as OAHL is the agent-facing interface.

All submissions must include a working code repository with a README covering setup, hardware requirements, and how to run the adapter.

A short demo video (maximum three minutes) showing the adapter or agent demonstration in action against real hardware is required. Simulated or mocked hardware is not acceptable for final judging, though it may be used during development.

Submissions must be new work created during the hackathon period. Existing projects may be extended but the OAHL integration must be new.

Any AI model, agent framework, or programming language is permitted. OAHL exposes a standard REST API so there is no language restriction.

Teams of up to three people are permitted. Solo submissions are equally welcome.