Praecise
Menu
Products · 04Cloud

Praecise Silo

A microVM for every agent: its own kernel, its own disk, and no network.

Each silo is a Firecracker microVM started for one agent on a machine Praecise owns, with Python, Node, Git and a compiler ready inside. The agent runs commands and moves files in and out through the API or as MCP tools, and every run returns a receipt of what ran and what came back. Nothing one silo does is visible to another, and nothing survives its deletion. Built on Silo in Furcate, and part of Praecise Cloud.

Contact
Category
Cloud
Layer
03 · Cloud

01

Where it sits in the stack

Praecise Silo is in layer 03, cloud. Each layer is built on the one below it.
  1. 05

    Work

    Businesses and teams

    Invoices, orders, customer answers, reporting.

  2. 04

    Automation

    Ipnops · Praecise Inbox · Skerry

    Agentic automation, messaging and payments.

  3. 03

    Cloud

    Praecise Cloud · Praecise Silo

    Apps, agents, models, data and machines, and a microVM for every agent.

  4. 02

    Operating system

    Furcate

    Open source and Linux-based, for machines, edge cells and data centers.

  5. 01

    Metal

    Praecise Metal

    Owned machines: placement, power, thermal.

All products

02

What a silo is(5)

One agent, one VM. The boundary is a kernel, not a container.
  1. 01

    Its own kernel

    Firecracker microVM

    Every silo boots its own Linux kernel under KVM, so the line between one agent and the next, and between an agent and the machine, is a hypervisor boundary.
  2. 02

    Its own disk

    Overlay on a shared image

    The tools come from one read-only image; everything a silo writes goes to a disk of its own and is removed with it. The agent runs as root inside, and nowhere else.
  3. 03

    No network

    vsock only

    A silo has no network interface. The one channel is a socket to the agent inside, so code an agent wrote cannot reach anything the owner did not hand it. A controlled way out through the host is coming.
  4. 04

    A receipt for every run

    Digests of input and output

    Each command returns its exit code and output with a receipt: the kernel and image it ran on, a digest of the request and of each output stream.
  5. 05

    API and MCP

    Create · run · files · pause · delete

    Agents call it as six MCP tools or through the API with a Furcate agent token, and see only the silos they created. Each silo has a term and is removed when it ends. Snapshots are coming.

03

Place your first workload on Praecise.

Say what you run and where it runs today, and we reply with what it takes to place it.

contact@praecise.com