ArgoBox is a private AI control plane that sits between OpenClaw and your infrastructure. The current public wedge is one hardened stack: ArgoBox, Hermes, OpenClaw, and Home Assistant. No raw shell trust. No vague autonomy story. One canonical path first.
Product story first: what the stack is, how to install it, and how the OpenClaw trust boundary works.
See the homelab-first product framing: ArgoBox as the approval and audit layer, Hermes as routing, OpenClaw as the hands.
Install the supported v1 stack first. One documented path, one operator flow, one place to start before broader framework claims.
Read the public trust story: approval boundaries, capability gating, auditability, and what ArgoBox still refuses to promise.
ArgoBox is optimizing for homelabbers first, while keeping a clear path for developers and AI operators after the hardened core is proven.
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 pathThis is the first wedge: a private AI control plane for Proxmox, Docker, Unraid, Home Assistant, and the rest of your self-hosted stack.
Start hereThe interesting question is not “can an agent act?” but “what controls survive hostile use?” ArgoBox leads with that trust boundary.
Review the model
The storage lessons that finally stuck: give each box a job, fix ownership before containers start, tune CIFS for the workload you actually have, and treat recovery like a process instead of a panic button.
The setup that finally stuck: use RustDesk for helping people, Tailscale for private network access, and Cloudflare Tunnels for public web apps. Here's how to wire it together without opening your firewall to the internet.
I spent 21 hours building a focus music engine with Web Audio API and FM synthesis. The singing bowls sound great. Everything else taught me why procedural generation isn't enough.
AI automation, home lab infrastructure, Linux systems, and DevOps workflows — explored in depth.
RAG pipelines over Obsidian vaults, knowledge graphs, AI agents, and automation that writes, publishes, and monitors itself.
Building a custom Gentoo-based distro from scratch. Portage, binary packages, Btrfs snapshots, and OpenRC — no systemd.
GitOps pipelines, Ansible automation, modular deployments, and infrastructure as code patterns — git push to deploy.
Multi-site network with Proxmox clusters, Tailscale mesh VPN, NAS arrays, and containerized services across two locations.
Knowledge graphs, Zettelkasten workflows, and an Obsidian vault that powers RAG search, content publishing, and AI context.
