A studio for physical-world AI

AI tools for engineers working between software and the physical world.

We build instruments — not platforms, not visions, not promises. Each one solves a specific problem for a specific kind of engineer. We ship them, charge for them, and improve them.

Founded
2026
Currently shipping
Code Sentinel
Team
A studio of one
Based
Remote · Asia

The frontier of AI is not a smarter chatbot. It's code that meets the world.

The past three years of AI tooling were built for a specific kind of person — a knowledge worker writing prose, code, or queries that live entirely inside a screen.

But the engineers who actually move the physical world — embedded developers, roboticists, IoT integrators, industrial control programmers — were never the audience. Their code runs on microcontrollers with 256KB of RAM. Their bugs surface only at 3 AM in a warehouse. Their tools were built before transformers existed.

The general-purpose AI tools of 2025 don't fit the engineers who keep the physical world running. PhyCyber is the studio that builds for them.

We don't try to be a platform. We don't try to be a model. We make precise, opinionated instruments — one at a time — for engineers whose problems the rest of the AI industry overlooks.

Three tools planned. One shipping.

Every PhyCyber tool is shaped by the same principle: do one thing for one kind of engineer, and do it better than any general-purpose AI can.

Available · v0.0.1 alpha

Code Sentinel

A local static analyzer for embedded C, FreeRTOS, and ISR-context mistakes.

  • 8 RTOS & memory-safety rules
  • Terminal, JSON, and HTML reports
  • FreeRTOS demo with 13 findings
  • Pure Python · local-first · no telemetry
Run the alpha → pip install git+https://github.com/lonrun/code-sentinel
In development · Q3 2026

Sensor Studio

Browser-based diagnostics for sensor data streams. Drift, noise, alignment — solved by an agent that understands signals.

  • Multi-sensor data ingestion
  • Drift & noise detection
  • Cross-modal alignment
  • Plain-language anomaly explanations
Notify me →
Research · 2027

Agent Layer

A protocol for AI agents to query and reason about physical devices — not just talk about them.

  • Device semantic translation
  • Sensor-aware agent primitives
  • Open-source SDK
  • Compatible with major LLMs
Read research note →
PCFounder · Studio of one

An odd career, by design.

I spent years moving between worlds most people pick one of. AI agents at Alibaba — writing code that fixed code. MEMS sensors and nanopore sequencing at Tsinghua — studying how physical signal becomes digital truth. Smart buildings, IoT firmware, warehouse pick-to-light — actual systems in actual factories, seven years ago, when none of this was fashionable.

PhyCyber is what that career converges on. The space between clean software abstractions and messy physical reality is where the next decade of AI tools needs to live. I'm building one tool at a time, for the engineers who already live there.

Industry
AI Agent Engineer, Alibaba
Research
MEMS, Tsinghua University
Education
MS Software Engineering, ZJU
Open Source
Static analysis · AI agents

Reading is part of the work.

Occasional essays on physical AI, engineering tools, and the strange overlap between sensor physics and software design. No build-in-public diaries. No daily updates. Just the things worth saying.