Sathvik VK

B55

A software prototype of a small device you talk to. It runs a local model, uses tools, and asks before it changes anything.

Status
Prototype. Runs as a simulator on a Mac. No hardware has been built
My role
Solo. Architecture, daemon, interface and test harness.
When
Nov 2026
Capabilities
LLM apps, Agents, Memory, Voice, Desktop, Integrations
Three states of the B55 interface: a greeting with suggested requests, an approval card asking to save a note, and a verified result.
Greeting, approval, verified result. Interface states from the Mac simulator.Screenshot

What it is

B55 explores what a personal device looks like when the main interface is a request rather than an app grid. You type or speak; an agent decides which tools to use; the screen shows what it wants to do and waits.

It is a simulator. The interface and the agent are real and run on a Mac, with a path to a Raspberry Pi drafted but not built.

What I built

Two processes that talk over a local Unix socket using newline-delimited JSON.

  • The daemon: an asyncio agent loop, a tool registry, a policy gate, connectors, voice input and a SQLite memory.
  • The shell: a Qt QML interface with its own on-screen keyboard, onboarding, and the approval and result cards.
  • Connectors: GitHub works end to end. Gmail is implemented and tested offline but the consent flow is not finished. Drive has its scope declared and nothing more.
  • A rehearsal runner that replays a demo request against the local model.

Decisions

Policy lives in code, not in the prompt. Any tool that is not read-only requires approval, and no answer within two minutes counts as no. After a write, the daemon reads the value back, and the interface shows Verified only if that check passed.

I wrote a small agent loop instead of adopting a framework. It is about a hundred lines, which makes it possible to reason about exactly when a tool can run.

The interface never holds secrets and never calls a model. Only the daemon does, through one adapter that can point at Ollama, llama.cpp or a hosted model.

Qt QML was chosen over a web view because it renders straight to the display with little memory, which matters on a small board.

What the testing showed

The first working slice shipped with five daemon tests; the suite later grew to 141. A scripted rehearsal of the core demo request passed 20 times out of 20 on the local Qwen3 model.

That rehearsal is a harness that answers the approval prompts itself, on a simulator. It shows the loop is repeatable. It is not user testing and says nothing about hardware.

How it fits together

Shell
Qt QML interface
typed or spoken request, cards, keyboard
Socket
Unix socket
newline-delimited JSON
Daemon
Agent loop
local model through one adapter
Policy gate
not read-only means ask first
Memory
SQLite
Tools
Notes and device
GitHub
working
Gmail
built, consent pending
Drive
scoped only
The shell draws and collects input. The daemon decides, checks policy and runs tools. Simplified diagram drawn for this page, not a product screenshot.

Built with

PythonasyncioPySide6Qt 6 QMLOllamaQwen3whisper.cppSQLiteOAuth 2 with PKCEpytest

Screens

Next case studyOr press the right arrow keyGibbleA CRM for music teachers: student onboarding, scheduling, tasks and lesson history, on React Native and Spring Boot.