AI coding rolled out, not smuggled in

For organisations adopting AI coding across many developers and many repositories, where a pile of personal accounts and no visibility is the current state. Runix Code, in development, is being built so every change lands as a reviewable diff, with seats, per-key limits and attribution by developer. Runix Router gives the model calls one policy and one bill.

One of six solution pages. Statuses are literal: the products named below are in early access or in development, as marked.

The stack for engineering organisations

Runix Code
An independent coding agent, reviewable in your repository · in development
Runix Router
One compliant endpoint for every model · early access

02 · Situation

The situation

Three things this team is usually dealing with when it calls.

Personal accounts, no visibility

Developers sign up for assistants on their own, expense them or pay with their own cards, and paste code into tools nobody reviewed. The organisation cannot say who uses what, on which repositories, or what it costs. Turning that off loses the productivity; leaving it on loses the audit.

Agents that write without a reviewer

An agent that edits files silently is faster until the first bad change ships. Review habits were built around diffs, and tools that bypass the diff bypass the review. Trust has to be earned per change, not granted per tool.

One provider key for the whole organisation

A single shared key means one runaway job empties the budget for everyone, and revoking it means a redeploy. Which model serves which repository is decided by whoever wrote the config last.

03 · Stack

The products, and the role each plays

Each one works on its own; together they are one path through the stack.

Runix CodeLayer 05 · AgentsIn development
An AI coding agent being built for teams: grounded in your repository, with multi-file implement, refactor and test from one instruction, and every change landing as a reviewable diff, never a silent write. Seats, per-key limits and usage attribution by developer are part of the product, not an add-on; it is in development, with the waitlist open.
Runix RouterLayer 04 · GatewayEarly access
Optional in front of the agent's model calls, and useful on its own: one OpenAI-compatible endpoint with per-key quotas, rate limits and allowed models, revocable without a redeploy. Usage is billed in USD and itemised, so attribution survives the invoice.

04 · Start

How it starts

A person on the other end at every step; nothing here is self-serve.

01Join the waitlist

Tell us the team size, the repositories and what you want an agent to take off the team's plate. Cohorts are invited in order, and we reply within one business day with where the product is.

02Set up seats and policies

Seats, per-key limits and review gates are configured with you. The team plans are set out on the Code plans page.

03Put Router in front, if you want one bill

Runix Router accounts are set up after a short intake, with evaluation credits issued on request. Each key carries its quota, limits and allowed models, so the agent's model calls are governed the same way as every other call in the organisation.

05 · In writing

What is in writing

The parts a review asks for, stated once and linked to the page that holds them.

Data terms

Content sent through Runix Router is processed to serve the request and never used for training; operational metadata is kept for billing and support. Put Router in front of the agent and its model calls are covered by the same terms.

Contracting and billing

You contract with Runix AI Inc; an MSA and a DPA are available on request. Router billing is usage-based in USD, itemised, on a prepaid balance or by invoice; Code has team plans, set out on the Code plans page.

Statuses, literally

Runix Code is in development and not generally available; its page describes what is being built, and waitlist cohorts are invited in order. Runix Router is in early access and running traffic, with no published SLA.

07 · Questions

Common questions

Can developers use Runix Code today?

No. It is in development and not generally available; the waitlist is open and cohorts are invited in order. The product page describes what is being built, not a shipped product.

Does the agent commit code on its own?

It is designed so that every change lands as a reviewable diff, never a silent write. Your review process stays where it is.

How do we attribute cost to a team?

Runix Code is designed with seats, per-key limits and usage attribution by developer. Runix Router meters per key, with itemised usage-based billing in USD, so a team's model spend is attached to its key at call time.

Get your team into an early cohort

Tell us what you run today and what you are trying to change. We reply within one business day with a concrete plan, and we say which parts we would not do.

Talk to sales