ruv.sgit.airUv + sgit

For consultancies and product companies · business

Add governed agent swarms to what you already sell.

Your clients are asking what you do with agents. Answer with something you can show: a hive of agents with a written mandate per role, an encrypted vault per run, and a ledger with the numbers. Start by reselling runs; end with your own deployment.

Built on rUv's tools: Ruflo (MIT, by rUv / ruvnet), an agent meta-harness for Claude Code and Codex with a queen-led hive-mind and a policy engine that runs in legacy, observe or enforce mode and writes a hash-chained receipt for every decision. We build on it; we do not sell or own it. Ours: sgit vaults and Agent Behaviour Policies (Apache-2.0).

Who this is for

  • Consultanciesthat want a delivery practice built on agent swarms, with evidence a client's risk team will accept.
  • Product companiesthat want agent runs inside their product, under their brand.

The problem, in your words

"We need an agent offering this year. We cannot hand client data to a black box, and we cannot sell something we do not control."

The continuum

Start where it is cheap to learn. Move along as the demand is proven. Each step uses the same runner, the same behaviour policies, the same vaults.

  1. Resell runs

    Buy task runs on shared infrastructure and sell them on, with your expertise around them. Nothing to deploy.

  2. White label

    Your brand on the offering and the deliverables. We run the hives behind you; you hand your clients their run vaults.

  3. Your own deployment

    Dedicated compute, one machine per task, with the vault created inside that environment (designed, not built yet). Then the maintained repository: the code that runs this, kept current, with your UI, branding and setup, on Claude Code, on AWS, or anywhere you choose.

Not automated end to end yet. A person on our side starts each run and watches it to the end. The runs on this site used a local vault server on the machine that ran the hive, so their timings are local numbers; the workers were Claude Code subagents, with Ruflo holding the queen, the roles, the tasks and the broadcasts. Dedicated compute and the materials sandbox for customer uploads are not built yet, and SG Compute is not connected to runs: when we reply to an order we say what we can do today.

What stays with you

Your clients

The relationship and the conversation are yours. We are behind you, not beside you.

Your brand

White label or your own deployment: the offering, the pages and the delivered vaults carry your name.

Your keys

Vault keys stay in your secret store. They are never printed, logged or committed. The vault server holds ciphertext only: across the ledger, no probed text from the delivered files was found in any byte it stored.

data/vaults.json

What you get

  • A Ruflo hive per run: a queen and workers in parallel, one role per piece of work.
  • A written mandate per role, compiled into Ruflo's policy engine in enforce mode, with a hash-chained receipt for every decision.
  • One encrypted vault per run: a branch per worker, every delivery committed and merged, measured at close, then delivered and deleted.
  • A business model you can copy: the plan, the structure and the architecture. Anybody who implements it implements sgit vaults and Agent Behaviour Policies.

Offers that fit

Prices are in the shop. Mix and match: put what fits in the cart and send it; there is no payment step, the order comes to us by email and we reply.

The whole map

The four offers on one map: from shared runs to your own deployment. Read the map with the business model.

Talk to us

agent@riskmandate.ai

A live agent answers; a person follows up. Every contact and every order from the shop goes to this address.