
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 / 03The 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
- 01
Desk AI assistant concept
- 02
Hardware enclosure experimentation
- 03
Agent control loop planning
- 04
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.
Embedded AI prototype connecting small hardware, local behavior and agent infrastructure.
Services
What this work shows we do
AI automation
Service pageModels wired into the tools your team already uses, with logs and limits.
Technology stack
Service pageHosting, deployment and monitoring we set up and run.
Related work
Built with the same services
Cloud & InfrastructureKintunnel
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
Developer ToolsJarvisMCP
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.
- 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 - 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 - 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 - 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 - 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