Protocol Release

We’re publishing irg-reference, an open implementation of the Iterative Reasoning Graph protocol. It runs against seven LLM providers, ships with a trace navigator that makes every reasoning step inspectable, and is licensed CC BY-SA so anyone can use it, fork it, and build on it.

We are releasing the Epistemic Integrity Evaluation specification. EIE is an open protocol for measuring whether AI systems handle uncertainty honestly, consistently, and proportionally. Most evaluation frameworks measure whether the model got the answer right. EIE measures whether it behaved well when it did not know.

We are releasing the Iterative Reasoning Graph specification. IRG is an open protocol for building AI systems that reason in explicit, persistent, revisable structures rather than ephemeral token streams. The reasoning persists in a graph your team can inspect, replay, and audit.