Skip to main content
Chiplab is an intelligent platform built for AI-assisted embedded development. Connect your coding agent, Cursor, OpenCode, or Claude Code, once, and from then on you just describe what you want in plain language. Your agent handles uploading your binary, running it on a chip-accurate virtual board, and reporting back the results.

Introduction

Learn what Chiplab is, how it works, and what problems it solves for embedded firmware development.

Quickstart

Connect your AI coding agent to Chiplab and run your first virtual board simulation.

Tools

A conceptual overview of what your agent can do with Chiplab: ask and run, with more on the way.

Supported Hardware

Browse the full list of supported virtual boards, from STM32F4 Discovery to nRF52840 DK.

Connect Cursor

Step-by-step setup guides for Cursor, OpenCode, Claude Code, and others.

API Reference

Manage connected agents, API keys, and usage from your dashboard.

​
How it works

These steps take you from a fresh account to a running firmware simulation.
1

Sign in to Chiplab

Open the Chiplab dashboard and sign in with your account. Authentication uses OAuth 2.0 and completes in the browser, no manual API keys to copy.
2

Connect your coding agent

Navigate to API Keys → Connect agent in the dashboard. Select your agent (Cursor, OpenCode, or Claude Code) and follow the displayed configuration instructions. Your agent connects to Chiplab over HTTP.
3

Ask your agent to run a simulation

Once connected, you don’t need to call any tools yourself. Just tell your agent what you want, for example: “Test this firmware on Chiplab: /path/to/firmware.elf on an STM32F4 Discovery board.” Your agent uploads the binary, runs it on a chip-accurate virtual board, and reports back the console output.