Home  /  The Lab

The Agencie Lab

A frontier AI lab, on your own hardware.

Your choice of models, hosted privately. Autonomous agentic pipelines, full coding, vision, documents, slide decks, voice and image generation, and a browser for agents, through one governed endpoint, with a budget, a check and an audit record for every request, and runtime security from SILO.RED. It is what we use internally, now offered privately to the right partners.

Endpoint1every coding tool talks to one gateway
Tiers4simple, standard, complex, expert
Wind-down80%of a limit: finish the file, run the tests, commit
Open doors0without a key behind them

Overview

A frontier provider in miniature.

Coding agents are now how good teams ship. The catch is that they run on someone else’s models, read your code on someone else’s servers, and bill by the token with nothing to say what the money bought.

The Agencie Lab is two machines and three licensed modules. The Docker host runs AOS, the gateway and console, and Code Easy, which knows your repositories. The models host runs open models on a GPU, a DGX Spark included. Your people keep the tools they like: CloudCode in the terminal, VS Code with our extension, Continue or Cline, or any OpenAI-compatible client.

We supply the hardware, install the stack, register the repositories, set the budgets with you and hand over with the runbook. Your frontier subscriptions or keys go in on the day, and nothing of yours passes through us afterwards. The licence pays for the platform; your usage never leaves your lab.

What it does

Governance in the platform, not in a policy document.

01

One door for every tool

CloudCode in the terminal, VS Code with Continue or Cline, Code Easy, scripts and CI all call one gateway. It chooses the model, offers the tools, enforces the budget and keeps the record.

02

Local first, frontier by choice

Routine and standard work runs on open models on your own GPU. The hardest tasks go to a frontier agent as a whole, checked job, and only when you switch that on. Switch it off and nothing leaves the building.

03

Checked, as a provider checks itself

A coding turn ends only when the project’s own tests have run. A reviewer reads the change against the brief. Trust is earned from verified outcomes, never granted.

04

Nothing runs unaccounted

Every request reserves money before it starts and settles after. Limits per day, month and client; alerts at 80% and 100%; a monthly statement by team, repository and model for charge-back.

05

Autonomous builds

Code Easy knows every registered repository. AutoCode turns a specification into a build: one engine writes, another validates, a stuck task escalates. Close to a hundred specifications have run on our own products.

06

More than code

PDFs, Word, Excel and PowerPoint files are read, and made: documents, spreadsheets, PDFs and slide decks come back as links. Screenshots and photographs go to a vision model; pictures and voice-overs are made on the lab’s own servers, and short video with sound on request. All of it on your hardware, budgeted and recorded.

07

A browser for agents

Agents open web pages and work them as a person would: read, click, fill in a form, follow a link. Each page comes back as text the lab’s own models can read, so testing your sites becomes part of a build. Kept to the lab whenever you choose.

08

A mode for the work in hand

Isolated: no frontier model is sent anything. Max mode: the idle stacks stop and AOS has the machine. Studio mode: the Spark swaps its reasoning model for video and images. Each is a switch on the console, applied by the host and reported step by step.

09

The console, from anywhere

A live map of every model, tool, agent and host; spend to the penny; CloudCode itself in a browser tab, on a desk or a phone. One sign-in, roles for who may change what, and every key in an encrypted vault.

In use

Watch it think, from a desk or a phone.

The AOS console's live infrastructure map: AOS, the model servers, search, Code Easy, the safety classifier, the Word, Excel, PDF and deck tools, the coding agents and the hosts, with a dotted line to the internet
The console. The live map of the lab: AOS, the models, search, Code Easy, the document and deck tools, the agents and every host, and the line to the internet.
CloudCode starting in a terminal with the gateway as its provider
CloudCode. The terminal agent with one provider: the gateway.
The AOS extension in VS Code, with the Lab item in the status bar
VS Code. The AOS extension: the licence, today’s spend and the budget in the status bar.
Code Easy's view of a repository: each file sized and coloured by language, with codebase statistics, code quality, the activity feed, functions, API routes and the environment
Code Easy. Every registered repository at a glance: its files, its quality, its functions and routes, and what changed.
Code Easy's control centre with the work queue, engines and validation
AutoCode. A specification becomes a build, written by one engine and validated by another.

Who it is for

Teams that want the frontier, on their terms.

  • Engineering teams spending thousands a month on metered coding agents with no governance to show for it.
  • Regulated firms whose policy says code never reaches a frontier provider.
  • Groups with several teams or sites who need spend charged back by team and repository.
  • Anyone who wants the frontier way of working without handing over their code or their budget.

Ways to buy

Priced per lab, installed and supported.

Hardware passes through at cost. A quote follows a conversation.

  • The mini lab: the host, the stack installed, the governance on, a day of handover.
  • With the DGX Spark: a 120B reasoning model on the complex tier, on premises.
  • A hardware-ready kit: built and tested here, shipped, plugged in.
  • Deployed on your own machines or private cloud: software, installation and support.
  • Operated for you: your hardware, our engineers watching the console.
  • Institutional: your accelerators, isolation from day one, and the evidence for an auditor.
  • Video generation on the same hardware, for teams that need it: ask us.

Partnering is by conversation. An hour with the lab running, on work of yours.

Ask about partnering →