Start here

Getting started with PoisonZero

PoisonZero watches your AI agents’ memory and instruction files, scores every change, and reverts poisoned edits automatically. This page shows how that works in one picture, then walks you through protecting your first device in three steps.

How it protects, in one loop

Every time an agent writes to a watched file, the same loop runs on your device - in milliseconds, before the change is trusted.

01

Agent changes a file

An AI agent writes to a watched memory or instruction file.

02

Melira engine scores it

It scores a redacted diff of the change on your device, never your whole file.

03

A verdict is reached

Based on the score and your sensitivity, one of three things happens:

Revert

A dangerous change is rolled back automatically.

Ask

A borderline change waits for your confirmation.

Allow

A safe change passes through untouched.

Fail-closed by design: if the engine can’t run safely, changes are recorded and surfaced rather than trusted.

Every check runs on your device

The inference engine, the scoring, the verdict - all of it runs on your own machine, in both Cloud and Private mode. Your files are never uploaded anywhere to be analysed.

Your device

Your AI agent

Writes memory and instruction files as it works.

PoisonZero watcher

A privileged service that reads each change locally and prepares a redacted diff.

Melira engine

Scores the diff on your device and returns a verdict - in both modes. It never opens your files.

The engine is sandboxed: no network, read-only, and it spawns no processes.

Control panel

Incidents, audit and fleet settings for your whole team.

Only verdicts, signals and telemetry leave your device - never the contents of your files. Scoring runs locally in both Cloud and Private mode.

Cloud or Private - same local checks, different egress

You pick the mode when you install. Either way every check runs on your device; the mode only decides what (if anything) leaves it.

PrivateZero egress*
Your device
Your AI agent PoisonZero watcher Melira engine · local
Nothing but one signed licence check-in.

Model and console fully self-hosted.

Cloud
Your device
Your AI agent PoisonZero watcher Melira engine · local
Only verdicts, signals and telemetry - never your file contents.

Console, model updates and fleet management hosted by us.

* One signed licence check-in every 30 days to update.poisonzero.com. Your files and verdicts never leave the device.

Protect your first agent in three steps

  1. 1

    Create your account and pick a mode

    Sign up and pick a mode: Cloud (managed console and model updates) or Private (everything on your own infrastructure). Either way, scoring runs on your device.

  2. 2

    Install and enroll in one command

    Grab an enrollment code from the panel, then run a single install command that carries it. It installs the privileged service and enrolls the machine in one shot - on Linux, macOS or Windows, so a rogue agent can’t stop it.

  3. 3

    Watch it work

    Protection starts immediately. From the control panel you review what PoisonZero caught, under Incidents and Audit.

What happens next

From here, PoisonZero watches in the background and reverts poisoned changes on its own. You review what it caught in the control panel, under Incidents and Audit. Want the deeper picture? These are the best next reads:

Protect your first agent in minutes.

Free, for Linux, macOS and Windows.

Sign me up