ProtoModule ProtoModule
Back to home

From Box to Big Screen in Under Five Minutes

· 3min · ProtoModule
Three steps: plug in the stick, connect WiFi, watch your agent stream to the TV

The whole point of ProtoModule is that it disappears. You shouldn't have to think about it. You shouldn't have to read a manual. You plug it in, and a few minutes later your agent is streaming to the biggest screen in your home.

Here's how that happens, and what's actually inside the stick.

Six steps. Three you do. Three happen automatically. 1 Plug in HDMI + USB-C Physical install done 2 Connect WiFi Guided on-screen Enter password once Select network HomeWiFi_5G 3 Pair Bluetooth Headset or speaker One tap, done You're done 4 Open your agent Claude / Codex Launch as usual $ claude-code 5 Auto-discovers mDNS finds MCP No config needed 6 Visuals stream Charts, diffs, logs Real-time on TV MISSION BOARD 0:00 1:30 3:00 3:30 4:00 4:30 Target: under 5 minutes • Most people: well inside that
setup flow: plug in → connect WiFi → pair Bluetooth → open agent → auto-discover → stream

The five-minute setup

Six steps. Only the first three involve you touching anything.

  1. Plug in. The stick goes into an HDMI port on the back of your TV. Power comes from USB-C. That's the whole physical install.
  2. Connect WiFi. The TV shows a guided on-screen setup. Pick your network, enter the password once.
  3. Pair Bluetooth. One tap to pair your headset or speaker. Hands-free audio, done.
  4. Open your agent. Launch Claude or Codex on your laptop.
  5. It auto-discovers the stick. Your agent finds the MCP server on your WiFi on its own. No IP addresses, no config files, no hunting.
  6. Visuals stream. Charts, diffs, logs, and diagrams appear on the TV in real time.

From unboxed to first visual on the TV, the target is under five minutes. Most people land well inside that.

What's inside

The stick is a small computer that runs AI models locally. Voice, vision, and language all happen on the device, not in some distant cloud.

The services are written in Rust. That matters for two reasons: it's fast, and it's safe. Rust is the language you choose when you want things to not crash and not leak.

protomodule The whole product, in one hand. PROTOMODULE physical killswitches camera · microphone — power rails cut 360° status ring privacy · notifications · state HDMI passthrough TV keeps working, always 80mm × 40mm × 15mm · anodized aluminum · slate, silver, terracotta
protomodule device render

On your network, the stick runs an MCP server. It talks over WebSocket, and your agent finds it through mDNS discovery. The connection is encrypted, and every tool the agent can call has its own permission level. Nothing runs by default.

Then there's the rendering pipeline. This is the part that makes ProtoModule safe.

Reuses the screen you already own

ProtoModule is a stick, not a screen. It adds a job to the TV already on your wall, and doesn't ask for a new computer, a new desktop, or a new tablet to see your agent's work.

That choice is environmental before it's economic. Every new display is a new LCD panel: liquid-crystal chemicals, loosely sealed between polarizers, persistent in the environment, released at manufacturing, during use, and again at disposal. When it dies, it can't be recycled easily — no industrial-scale process exists, and over 60% of replaced TVs were still working when they were replaced, heading to a system that can't handle them. The greenest screen is the one already in your home. ProtoModule is built to keep it in service — not by building a better recycling process, but by giving it a reason to stay turned on. Repairable, long-lived, and one fewer display per use case.

The point of all of it

The stick is a small computer, but the goal is that you never think about the computer. You think about the work on the TV.

Plug it in. Connect WiFi. Pair Bluetooth. Open your agent. Watch it stream.

Under five minutes, and then it disappears.