Junkz3

Junkz3 / wrench-board

Public

A senior microsoldering technician, available to every repair shop — from the seasoned pro to the apprentice. Powered by Claude Opus 4.7.

agentic-ai agents ai-safety anthropic boardview
27
12
100% credibility
Found Apr 30, 2026 at 27 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Wrench Board is an open-source AI diagnostic workbench that ingests schematics and boardviews to guide electronics repair technicians in identifying and fixing board-level faults.

How It Works

1
🔍 Discover Wrench Board

You find this helpful tool while searching for ways to diagnose tricky electronics faults on dead circuit boards.

2
💻 Set it up on your workbench computer

Download and launch the app easily, connecting your AI helper so it can start thinking about repairs.

3
📁 Upload your board's schematic and layout files

Drop in the PDF schematic and boardview file for the broken device you're fixing.

4
🧠 Watch the AI build a custom knowledge guide

In minutes, it creates a personalized repair manual with components, rules, and diagrams just for your board.

5
💬 Chat with your diagnostic teammate

Describe the symptoms, and get step-by-step guidance, highlights on the board, and smart suggestions.

6
🔧 Follow the plan to pinpoint the fault

The assistant highlights suspects, simulates failures, and guides your probes until you find the bad part.

✅ Fix the board and save it from the trash

With the precise diagnosis, you repair the device confidently, reducing e-waste one board at a time.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 27 to 27 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is wrench-board?

Wrench-board turns your browser into a AI-powered diagnostic bench for microsoldering repairs on PCBs. Upload a schematic PDF and boardview file—like KiCad, OpenBoardView, or Altium formats—and a Claude Opus 4.7 agent analyzes the board, highlights suspect components, traces nets, simulates boot failures, and guides probes via chat. Built in Python with FastAPI and WebSockets, it runs locally, ingesting files to build a knowledge pack for precise, hallucination-free advice.

Why is it gaining traction?

It bridges the gap between pro microsoldering know-how and AI, acting as a tireless senior tech who explains boot sequences or pinouts without fabricating refdes—tools enforce verified lookups only. Standouts include deterministic simulators for rail failures, live camera integration for macro shots, and self-evolving benchmarks that ship improvements automatically. The board wrench visualization—arrows for power flow, dim unrelated parts—makes causal chains visual, not verbal.

Who should use this?

Microsoldering techs in repair shops handling dead phones, laptops, or mainboards—from apprentices learning rail chasing to pros needing a second pair of eyes on tricky PMICs. Ideal for right-to-repair enthusiasts prototyping board bow wrench tools or paddle board wrench organizers, or anyone debugging custom hardware like MNT Reform boards.

Verdict

Promising alpha for niche electronics repair (27 stars, solid Makefile quickstart, 1400+ tests), but 1.0% credibility score flags early maturity—expect rough edges in edge-case boardviews. Try it if you're a github senior software engineer salary hunting side projects; skip for production shops until more field reports accumulate.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.