Tell your home what to do. In plain language.
AIRobot is a household robot you command by voice or text. An AI brain plans the physical steps a chore needs, picks the right robot from the fleet, and runs the job — with a hard STOP always one button away.
A practical helper that earns its keep around the house — not a one-trick toy
The goal is a household utility robot that handles the everyday chores people would rather not do themselves, starting with the toilet. You give it a high-level goal in natural language; it plans the sequence of physical actions and carries them out using onboard sensors. Interchangeable end-effectors let one platform handle many chores instead of being locked to a single task.
Straight talk: today's robots have drive, arm, and sensors — but no cleaning end-effectors yet. Chore commands currently run as motion choreography (“mimed”). Real scrubbing needs a Phase-2 tool: a brush, mop, and fluid system. This site shows what works on the bench today and what's honestly still ahead.
From a spoken sentence to coordinated robot motion
The real pipeline running on Prototype #1 today — voice in, plan, dispatch, act, report — with safety gates at every stage.
You speak — no app, no robot name
Say "robot", it answers "Yes?", and your next sentence is the command. Speech is transcribed on-device with offline Whisper — no cloud, no API key for the voice step.
Claude plans & picks the rig
The transcript goes to Claude via the Anthropic API. It reads a live capability manifest of every connected robot — battery, sensors, arm, skills, reachable rooms — then chooses the right rig and emits a step-by-step plan.
Dispatcher translates to primitives
Each step expands into controller commands — a drive uses calibrated ticksPerFoot, a skill unfolds its choreography, a navigate plays back a taught room route.
The robot acts
Commands travel laptop → COM port → wireless XBee link (or wired serial) → the on-bot Serializer controller → motors, servos, and sensors.
Sensors report back
Telemetry returns over the same path; the AI confirms the robot actually stopped, reports completion, and can auto-return the robot home by reversing the route.
Safety wins, always
Every motion is gated by an ARM check, a STOP ALL button always overrides, motions use a confirmed-stop, and robots respect a physical tether limit.
One brain, many bodies
The Cockpit console coordinates 1..N robots at once, each defined by a simple JSON file. Two rigs run on the bench today; three more are designed and gated behind a commit checklist before any hardware is bought.
4WD Mecanum chassis with a 6-DOF arm and full sensor suite. Drive, encoders, sensors, sonar, compass, arm, and servo power all validated.
A second 4WD robot on a wired serial link, drive-validated end-to-end through the Cockpit. Intended long-term host: a vintage 80386 laptop running the custom MarkKOS OS.
Bringing the 6-DOF arm fully online through P1's existing servo channels. Parts in hand; software pattern underway.
More capable platforms for real cleaning — Linux SBC, depth camera + LiDAR, cobot arm, and a fluid system. Gated behind a 6-milestone commit checklist before spend.
Built like real software, not a demo reel
The hard part isn't any single robot — it's the layer that understands intent and coordinates the fleet reliably. That's the core of AIRobot.
AI brain — Claude
Anthropic Claude (Opus) via the Anthropic API, using the Agent SDK pattern. The same robot tools are exposed over MCP so any Claude client can drive the fleet.
Capability-driven HAL
App code targets abstract interfaces (IRig, IMotor, ICompass, IServo…), so one brain runs different robots by swapping only the driver layer.
Skills are data, not code
A skill like clean the toilet is a JSON motion file. Drop in a file and any robot with the required capabilities is offered it — no code change.
Offline voice
OpenAI Whisper (tiny.en) runs locally on the laptop CPU — hands-free wake-word control with no cloud dependency for transcription.
Safety & supervision
ARM gate, STOP-ALL override, confirmed-stop, and tether limits — plus a structured event log, hang-detector, and per-rig health roll-up.
MarkKOS — a 386 OS
A from-scratch protected-mode OS for the Intel 80386 (~1,850 lines of C and assembly). A long-term "modern AI on a 386" demonstration — deliberately off the critical path.
An honest snapshot
This is an early-stage, single-builder hardware R&D project with working bench prototypes — not a shipping product or a funded company. Here's exactly what's real.
Two robots drive-validated end-to-end
P1 (full 4WD + sensors + arm) and MarkKOS (in commission), both controlled through one Cockpit process.
Cockpit console at v0.21.0
Multi-rig observation, AI Conversation tab where Claude picks the rig and plans, calibrations with audit trail, hands-free offline voice, and auto-return-home.
Multi-rig smoke test green
Two rigs driven in one process with supervision logging — the first two milestones of the build-commit gate passed.
Arm-on-bot + central MCP coordinator
Making the AI the commander and the Cockpit the observer, with the arm fully integrated on P1.
Real chore execution
Toilet cleaning needs Phase-2 hardware (brush + fluid system) on a more capable platform — gated behind the commit checklist before any spend.
Working hardware. A capability-driven brain.
The honest early innings.
AIRobot is a credible engineering bet on the household-robotics era: a fleet-agnostic AI control layer with two robots already running on the bench. If you back early-stage hardware-plus-AI and want to talk about what it takes to reach the first real cleaning chore, let's connect.