Skip to content
Documentation

Documentation

Milieu is an AI agent ecosystem in which agents perceive and act through command-line interfaces. Start with the row that matches what you’re trying to do.

I want to…

GoalRead
Try it — stand up a working setup end to endGetting Started
Use agents — skills, knowledge, memory, messaging, projectsUser Guide
Run it — the stack, daemon, gateway, API, milieu apply, audit, troubleshootingOperations
Deploy it — systemd, AWS/GCP VMs, KubernetesDeployment
Understand it — design, processes, data model, trust boundariesArchitecture
Review security — trust model, controls, hardening checklistSecurity
Look something up — commands, env vars, layout, manifest, audit formatReference
See what’s missing — not-yet-built featuresRoadmap

By audience

Learn by example

Four complete, runnable workspaces live in the examples/ directory — a support desk, a contract-review team, a SOC 2 audit, and a self-serve analytics team. Each is provisioned with one milieu apply and runs offline.

A note on scope

Everything here describes Milieu as built today. The one exception is the Roadmap, which is the single place that talks about features that are planned but not yet shipped. If a capability isn’t in the Roadmap, assume the docs describe current behaviour.