Sohyeon Park

Hey DevHunt! I am Sohyeon here, Co-founder and CPO at Veecle 👋 Chiplab is an MCP server that lets AI coding agents build, run, and test embedded firmware on a virtual copy of the real chip. No physical board required. [Why we built it] Years ago, we spent hours in a car flipping through a several-hundred-page datasheet just to find one signal. Then we ordered a board and lost weeks waiting for it to ship before we could even start. And when it finally arrived, we still had to wait our turn for the single setup the team shared. Every new AI coding tool seem built for apps or websites. We wanted embedded developers to move just as fast, to spend their time on real engineering, not on datasheets and waiting. [What it does] Helps your agent develop correct embedded code from day one by using datasheets, manuals, and results from all runs. - Runs your code on a virtual instance of the real chip. - Reads crashes for you, and gets better with every run. - Runs across all boards at once, instead of one at a time. - No custom hardware or tooling required. Connect your agent, and it’s ready. [Who it's for] Embedded engineers and teams who want their AI agent to carry the work all the way through, not just write the code. [What's supported today] - Chips: STM32 (F1, F4, F7, H7, L0, WBA) and Nordic (nRF52). - OS/Framework: Bare-metal, Embassy-Rust, Zephyr, FreeRTOS, Eclipse ThreadX. - Languages: C/C++, Rust. We're in beta and improving fast. Peripheral support and CI/CD integration are coming next week, so you can wire this into your GitHub and write real test scenarios. It's free to use while we're in beta. Excited to keep shipping :) Try it at: chiplab.veecle.ai Veecle website: veecle.ai Or leave a star on our public repo: github.com/veecle/chiplab Would love to hear what you'd want us to support next. We'll be in the comments all day.