Chiplab
Test firmware on a virtual chip with no hardware needed
What it does
Chiplab lets AI coding agents build, run, and test embedded software on a virtual copy of the real chip. No physical board required. Just connect it over MCP to any AI coding agent (Cursor, Claude Code, VS Code, and more), and skip hardware entirely. Chiplab compiles, runs, and debugs your firmware, and tells you exactly what broke. Works today on STM32 and Nordic chips, with more on the way. Currently in beta and we'd love your feedback.
Agents call Chiplab to run firmware on a virtual instance of the real target chip. Every run deposits what happened into a shared corpus.
A virtual instance of the actual target chip — not a generic CPU emulation. Same binary, same peripherals, same interrupt timing as the physical board. Cross-compilation, peripheral simulation, sensor IO, and chip-by-chip plumbing — exposed through one endpoint. Corpus lookup, build, simulate, test, bench, composed behind a single verb. Verdict, trace, fix — back to the agent in seconds. The corpus learns. Query the collective embedded corpus. Every chip-specific gotcha, validated fix, and architecture decision — searchable in milliseconds. Execute firmware on a virtual chip. No hardware required. Virtual simulation returns verdict, trace, and register state in seconds. Compile against any…from veecle.ai
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com