An agent platform where
nothing runs unwatched
Neutron is one agentic platform that many separate teams can run, each with their own AI agents. Its reason to exist is the part most agent tools skip: deciding, in advance and in writing, what an agent is allowed to do — and stopping it when it tries to do more.
A map of every element
The core, the development engine, the Revenue Engine, Projects, Goals, federation and orbits — what each is for and which gate governs it.
Governed autonomy
Every mutating action passes a gate before it runs. Three outcomes, not two: allowed, parked for a human, refused — and all three are recorded.
One image, many customers
A customer is a configuration file and a database, never a fork or a branch. Isolation is physical: its own pod, its own data.
You cannot approve yourself
Separation of duties is written into the permission policy as a subtraction, so the engine enforces it rather than etiquette.
Multi-harness
Codex, the Claude Agent SDK, and OpenCode sit behind one seam. No provider type is allowed to escape it.
Autonomy is a dial
An issue becomes a reviewable merge request. From there, policy decides: hold every merge for a human, or let review agents review, approve, and publish — governed and audited either way.
Federation
Neutron Cores federate with each other, and each core centrally controls one or more orbits — all over the same governed, audited interface.