Some parts of this page need JavaScript.

Skip to main content

Analytics only if you accept. Privacy

All work

AI & Machine Learning / Case study

JarvisNano

Desk AI assistant hardware prototype

JarvisNano running
In development · JarvisNano

In short

JarvisNano is a public embedded AI prototype: ESP32-S3 firmware for a desk assistant on the Waveshare 1.75C that calls tools through the JarvisMCP gateway.

Status
In development
Visibility
Public GitHub
Focus
Embedded AI
Proof
Hardware plus agent tooling
Built with
C/C++ / ESP32-S3 / Embedded AI / MCP / OpenSCAD / Kotlin (Android companion)

Inside the project

01 / 03

The Orbit Console, served by the device itself: the voice loop, the panel and touch state.

JarvisNano1 / 3

JarvisNano Orbit Console with a listening voice core, voice lifecycle counters, diagnostics buttons and a mirror of the 466 by 466 watch face

The Orbit Console, served by the device itself: the voice loop, the panel and touch state.

The brief

The problem

Most AI assistant demos run in a chat window. JarvisNano explores what changes when a small physical device needs local controls, model-aware behavior, and a practical path to supervised agent workflows.

What we did

Our approach

Built a public hardware and firmware prototype around the Waveshare ESP32-S3 Touch AMOLED 1.75C with a shared C/C++ firmware tree that calls tools through the JarvisMCP gateway, OpenSCAD design notes, and lightweight integration patterns that can inform robotics, kiosks, voice assistants, and edge AI experiments.

Features

What it does

  • Desk AI assistant concept

  • Hardware enclosure experimentation

  • Agent control loop planning

  • Open-source project documentation

Results

What happened

  • Public GitHub project with active 2026 development
  • Combines embedded hardware, AI agent patterns, and physical prototyping
  • Working reference for voice, device and local assistant builds
  • Documents the path from prototype hardware to a usable device

Architecture

Under the hood

Embedded AI prototype connecting small hardware, local behavior and agent infrastructure.

frontend
backend
service
external
ai
Sensor and control loopAgent actionsPhysical prototypeDocumented patterns
ESP32-S3 Device
Waveshare 1.75C board
Device Logic
Controls and local behavior
Agent Layer
Assistant planning and tool interface
Hardware Design
OpenSCAD enclosure concepts
Public Repo
Versioned releases and documentation

Embedded AI prototype connecting small hardware, local behavior and agent infrastructure.

Services

What this work shows we do

  • AI automation

    Models wired into the tools your team already uses, with logs and limits.

    Service page
  • Technology stack

    Hosting, deployment and monitoring we set up and run.

    Service page

Related work

Built with the same services

Other work of ours that shares this project's services.
  • Kintunnel, running
    Cloud & Infrastructure

    Kintunnel

    A public infrastructure project that manages VPN access for families and small teams. WireGuard networking and Docker-native deployment, designed to be self-hosted with Docker Compose.

    Read the case study
  • JarvisMCP, running
    Developer Tools

    JarvisMCP

    JarvisMCP gives AI agents one governed door into our company systems: CRM, search intelligence, infrastructure, memory and coordination. Agents find the capability they need, act through it, and leave a record. They never hold the keys.

    Read the case study

How we work

How a change reaches production

The same five gates for our own products and for yours. Nothing reaches your customers on the strength of a demo.

  1. 01 · Isolate

    Its own branch and workspace

    Every change starts in a separate copy of the code, so work in progress never touches what is live.

    git worktree add .worktrees/your-change
  2. 02 · Build

    Engineers with AI agents

    Agents write and test code beside us. They hold no passwords: every call they make goes through our gateway, which checks it and logs it.

    agent → gateway → policy · audit · call
  3. 03 · Prove

    Evidence, then review

    Tests, before-and-after screenshots of the running app, then independent reviewers. It does not move on until no serious finding is left.

    review: 0 high · 0 medium → pass
  4. 04 · Ship

    Deployed and checked live

    The pipeline builds and deploys. Then we check the running service itself, not just a green build.

    replicas 1/1 · image sha matches · health 200
  5. 05 · Watch

    Checked every night

    Each integration we run is tested against its provider every night, so a changed API is caught before your team notices.

    nightly: each integration vs its provider

Want something built like this?

Tell us what your team does by hand and the tools involved. AI automation is where most projects like this start.