Skip to content

hfsc2004/core-pcb

Repository files navigation

Core-PCB

Core-PCB Logo

Core-PCB is a stand-alone project derived from selected core-ce components, focused on AI-assisted schematic and PCB design workflows.

Primary target capability:

  • Run and orchestrate local models (including multimodal/vision-capable models) for electronics tasks, such as:
    • schematic interpretation
    • netlist reasoning
    • PCB placement/routing guidance
    • design rule and manufacturability review

Initial target model reference:

Runtime policy

  • Local-first and local-only by default.
  • Runtime scope for current architecture: llama.cpp only.
  • Frontier APIs are optional and not required for base operation.

Scope for this phase

  1. Stand-alone project structure inside this repository.
  2. Reuse strategy from core-ce for:
  • Hugging Face metadata/download flows
  • local runtime launching and model session management
  • optional deterministic tooling and RAG adaptation for EDA documents
  1. No modifications to existing core-ce files.

Integration status

  1. Option 1 (active): external app + file bridge.
  2. Option 2 (stub): external app + KiCad Python bridge.
  3. Option 3 (stub): KiCad Action Plugin.

See docs/ARCHITECTURE.md and docs/INTEGRATION_PATHS.md.

Quick Start (Current MVP)

Install dependencies once:

cd Core-PCB
npm install

Linux runtime bootstrap (recommended):

cd Core-PCB
./install/RUN_ONCE_LINUX.sh

Desktop app (Electron):

npm run desktop

Web app only:

npm start

Open http://localhost:4310.

Alternative launchers from the Core-PCB folder:

  • Linux desktop: ./start.sh
  • Linux web: ./start-web.sh
  • macOS web: ./start.command
  • Windows web: start.bat
  • macOS desktop: ./start-desktop.command
  • Windows desktop: start-desktop.bat

RUN_ONCE_LINUX.sh creates .venv, installs adapter runtime Python deps, and writes .env.local with CORE_PCB_PYTHON for launcher scripts.

Current UI supports:

  • optional Hugging Face token save
  • add model by Hugging Face URL (auto metadata scrape)
  • local catalog persistence
  • llama.cpp (llama-server) start/stop/status

For implementation status, see docs/MVP_STATUS.md.

About

Core-PCB is a local-first desktop app for schematic/PCB AI workflows. It imports Hugging Face models, auto-detects runtime/provider needs, caches models offline, and runs llama.cpp or Transformers+PEFT locally with runtime controls, diagnostics, GPU selection, and model cache management for KiCad-focused assistance.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors