JarvisNano
Pocket AI agent hardware prototype
C/C++ / ESP32-S3 / Embedded AI / Lua / MCP / OpenSCAD / Kotlin (Android companion)
Source codeInside the project
01 / 04Cockpit dashboard showing the project command surface.
The brief
The problem
Most AI assistant demos run in a chat window. JarvisNano explores what changes when a small physical device needs camera input, local controls, model-aware behavior, and a practical path to supervised agent workflows.
Our approach
Built a public hardware and firmware prototype around ESP32-S3 with a shared C/C++ firmware tree, on-device Lua skills that load without a reflash, an MCP server and client over LAN, OpenSCAD design notes, and lightweight integration patterns that can inform robotics, kiosks, voice assistants, and edge AI experiments.
Features
What it does
- 01
Pocket AI assistant concept
- 02
Camera-capable microcontroller target
- 03
Hardware enclosure experimentation
- 04
Agent control loop planning
- 05
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
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.
Working on something similar?
Tell us what you are building or fixing.