Stop Calling Agents Employees
The fastest way to build unsafe AI infrastructure is to pretend a model is a teammate with judgment. Treat it like an untrusted actuator with receipts.
Homelab-first v1 • approval-first agents
Run private AI operators on your homelab.
Run private AI operators on your homelab.
Approve every mutation.
ArgoBox is a private AI control plane that sits between AI tools and your infrastructure. The current public wedge is one hardened stack: ArgoBox, Hermes, Argonaut, and Home Assistant. No raw shell trust. No vague autonomy story. One canonical path first.
0 Canonical Stack
0 Core Roles
0 Raw Shell Trust
0 Your Infra
argo@argobox:~
argo@argobox:~$ docker ps --format 'table {{.Names}}\t{{.Status}}\t{{.Ports}}'
NAMES STATUS PORTS
traefik Up 47 days 80/tcp, 443/tcp
portainer Up 47 days 9443/tcp
uptime-kuma Up 47 days 3001/tcp
homepage Up 47 days 3000/tcp
grafana Up 12 days 3100/tcp
prometheus Up 12 days 9090/tcp
jellyfin Up 30 days 8096/tcp
arr-stack Up 30 days 7878/tcp, 8989/tcp
Start With the Hardened Core
Product story first: what the stack is, how to install it, and how the approval-first trust boundary works.
What ArgoBox Is
See the homelab-first product framing: ArgoBox as the approval and audit layer, Hermes as routing, and Argonaut as the operator-facing assistant.
Canonical Quickstart
Install the supported v1 stack first. One documented path, one operator flow, one place to start before broader framework claims.
Approval-First AI
Read the public assistant story: scoped context, capability boundaries, auditability, and what ArgoBox still refuses to promise.
Who Comes First?
ArgoBox is optimizing for homelabbers first, while keeping a clear path for developers and AI operators after the hardened core is proven.
Developers
The framework story is real, but it follows the hardened stack. Expect adapter seams, reference modules, and cleaner reuse after the core proves itself.
See the pathHomelabbers
This is the first wedge: a private AI control plane for Proxmox, Docker, Unraid, Home Assistant, and the rest of your self-hosted stack.
Start hereAI Operators
The interesting question is not “can an agent act?” but “what controls survive hostile use?” ArgoBox leads with that trust boundary.
Review the modelLatest Transmissions
View Archive 
Your Homelab Has a Blast Radius
Self-hosting stops being a toy the moment other people, backups, money, or legal records depend on it. That is when the lab needs production manners.
56 AGENTS, 1,500 VARIABLES, AND A LEAKY BRIDGE
A deep dive into the massive ArgoBox Design System merge. How 56 agents collaborated to re-point 1,500 CSS variables to a new organism design language with zero downtime.
Explore & Learn
AI automation, home lab infrastructure, Linux systems, and DevOps workflows — explored in depth.
AI & Knowledge Systems
RAG pipelines over Obsidian vaults, knowledge graphs, AI agents, and automation that writes, publishes, and monitors itself.
RAG Agents Obsidian Knowledge Graphs
Explore → Linux & Gentoo
Building a custom Gentoo-based distro from scratch. Portage, binary packages, Btrfs snapshots, and OpenRC — no systemd.
Argo OS Portage Btrfs
Explore → DevOps & Automation
GitOps pipelines, Ansible automation, modular deployments, and infrastructure as code patterns — git push to deploy.
GitOps Ansible Modules
Explore → Home Lab Infrastructure
Multi-site network with Proxmox clusters, Tailscale mesh VPN, NAS arrays, and containerized services across two locations.
Proxmox Tailscale Docker
Explore → Digital Gardens & Obsidian
Knowledge graphs, Zettelkasten workflows, and an Obsidian vault that powers RAG search, content publishing, and AI context.
Obsidian Zettelkasten PKM
Explore →