Skip to content

Hardware Design Space Explorer

Hardware Design Space Explorer is an AI hardware architect that turns a plain-English system requirement into three complete, verified system designs — each optimized for a different SWAP-C (Size,Weight and Power, Cost)

Code Demo Video Cerebral Valley

Core trick

A deterministic verifier checks each generated hardware design against power, thermal, and mass constraints, and human picks become ranking preferences.

Tags

robotics/hardwareagents

Description

Hardware Design Space Explorer is an AI hardware architect that turns a plain-English system requirement into three complete, verified system designs — each optimized for a different SWAP-C (Size,Weight and Power, Cost) trade-off (Efficiency: lowest power/longest runtime; Compact: smallest/lightest; Value: cheapest/fastest to source) — then ranks them and learns which one you actually pick. The problem: specifying hardware means balancing Size, Weight, Power and Cost against dozens of hard constraints, and there is rarely one right answer — there are trade-offs that depend on engineering judgment. Tools that emit a single answer hide that judgment. What makes this application different: a deterministic verifier — not the LLM — checks every design against every hard constraint (power budgets, P=I·V rails, endurance, thermal, mass, packing, compute, sensing, comms, actuation, connectors, IP rating), so results are trustworthy. A human picks the winner; the system distills that choice into preferences that reshape the next run's ranking, so its #1 converges on the human's taste (agreement rate trends up). Every backend step streams live, and a growing library, full run history, model-comparison view and Learned Insights round it out. Opus clearly beats Sonnet. Waiting to check Fable !
navanee4u/hardware-system-explorer★ 00 forksTypeScriptCreated Jun 13, 2026 · last push Jun 14, 2026

README excerpt

# Hardware System Explorer

> Give it a hardware requirement. Get **three complete, verified designs** — each tuned to a different trade-off — ranked, with the work shown live. Pick a winner, and the system **learns your taste** for next time.

### ▶ Live demo — **https://hardware-system-explorer.vercel.app**

![Hardware Design Space Explorer — a system requirement flows into the learning AI app and out as a SWAP-C optimized hardware design.](docs/hero.jpg)

![The two loops: a deterministic verifier gates every design; a human choice teaches the system over time.](docs/architecture-loops.png)

---

## The problem

Specifying hardware means balancing **SWAP-C** — **S**ize, **W**eight, **P**ower, **C**ost — against dozens of hard constraints. There is rarely one right answer; there are *trade-offs*, and the right one depends on engineering judgment. Tools that emit a single answer hide that judgment. This one surfaces it: **choice, with evidence — then it learns from the choice.**

## What it does

1. Turns a plain-English requirement into a **machine-checkable rubric**.
2. Generates **three complete designs**, each optimized for a different SWAP-C profile:
   - **Efficiency** — lowest power, longest runtime
   - **Compact** — smallest, lightest
   - **Value** — cheapest, fastest to source
3. **Gates every design with a deterministic verifier** — *never the LLM* — against every hard constraint, then ranks the three with a transparent scorecard.
4. A **human picks the winner** (

Team