governed-runtime

Turns repeatable, domain-agnostic workflows into graph-driven loops.

Make AI coding agents safe to scale autonomously: assign work, cap spend, enforce policy, verify output, roll back failures, learn from loops, and prove ROI across every repo.

Runtime evidence layer for agentic AI — signed audit chain, deterministic gate verdicts with record-bound audit replay. pip install phionyx-core.

Agent Gate Incident Replay is a browser-runnable blackbox replay runtime for Agent incidents. It restores a real VM state in the browser with [v86](https://github.com/copy/v86), mounts an incident module, and replays the agent's actions against real runtime boundaries and real Agent Gate verdicts.

GAP (Governed Agentic Programming) main repository | The native instruction language of AEP (Agent Element Protocol) | Fully deterministically programmed AI agents. | Paid version GAP runtime will be available on the NLA website soon.

Hamiltonian Programming Language: scheduler-governed execution, typed refusal, deterministic evidence and cryptographic anchoring.