How it works
Turn a component datasheet into a SPICE model that’s been checked. What Auto EE does, what it’s built with, and how far along it is.
The premise
Auto EE is a desktop app that reads a component datasheet PDF and builds an LTspice model for it. It figures out what kind of part it is, pulls the parameters and test conditions out of the tables, and digitizes the graphs. Then it fits a model, simulates it in LTspice, and scores the result against the datasheet’s own curves.
If the score is too low, a numeric optimizer takes a pass, followed by a repair loop using Claude Code or Codex on your own machine, so there are no API keys to manage. The agents can only suggest changes; the Rust code writes the model files. Seven kinds of parts are supported so far. Simple parts like diodes pass today, and power transistors don’t yet.
What’s included
Checks its own work by simulating the model against the datasheet’s curves
A graph digitizer that finds the axes, reads the ticks and traces each curve
The same inputs always produce the same model file
Jobs can be stopped and resumed, with every step logged
How it’s built
Auto EE is built on Rust, Tauri 2, React, TypeScript, LTspice, Claude Code and Codex.
It carries 487 commits since Sep 2026, most recently changed in Sep 2026.
How the work is done
Every project here starts as a written spec, and the spec stays the source of truth once there’s code. The repository keeps a build plan with current status, an append-only decision log of where the code departed from the plan, and a handoff document that describes where things stand, including the unfinished parts.
That’s how one person keeps this many projects moving, and it’s what this page is written from.
Current state
Prototype. Works, but isn’t finished.
The source is private, so the way to check what this page says is to use the product.
Next
Put Auto EE in your pipeline
Ask about hooking it up to the repositories and agents you already run.