AI Toolkit
A modular repository of specialized engineering tools, automation workflows, and helper utilities designed for AI agents and human developers.
Toolkits & Modules
| Module | Description | Quick Links |
|---|---|---|
| CAD Toolkit | Hardware-accelerated 3D CAD viewer, procedural & parametric modeling engine, CSG operations, Signed Distance Fields (SDF), 3D printability analysis, and AI Agent CollabBridge HTTP/CLI. | Documentation • Interactive Viewer • AI Bridge |
Highlights: 3D CAD Toolkit (cad/)
The CAD Toolkit provides a complete 3D modeling and visualization suite built for autonomous AI agents and pair-programming workflows:
- Interactive 3D Viewport: Fast, cross-platform UI with Dear PyGui and hardware-accelerated OpenGL offscreen rendering with CPU fallback.
- AI Agent CollabBridge: HTTP JSON API & CLI on port
8765enabling external AI agents to query scene state, inspect geometry, command camera views, adjust live parameters, and export models. - Procedural Modeling: Parametric primitives, CSG booleans (union, difference, intersection, chamfer, fillet) powered by Manifold3D, assemblies, and exploded views.
- Signed Distance Fields (SDF): Smooth mathematical CSG blending and high-resolution Marching Cubes meshing.
- 3D Print Preparation: Overhang detection, support volume estimation, bed boundary checks (Bambu, Prusa, Ender, Voron), and automatic print orientation optimization.
- Automated Testing & CI: Comprehensive 222-test suite enforcing >=90% code coverage across Linux, Windows, and macOS.
For full setup instructions, CLI parameters, and developer guides, refer to the CAD Toolkit Documentation.
Repository Structure
ai-toolkit/
├── .github/
│ └── workflows/
│ └── cad.yml # Cross-platform GitHub Actions CI for CAD
├── cad/ # 3D Computer-Aided Design & Procedural Modeling Tool
│ ├── README.md # In-depth CAD documentation & CLI reference
│ ├── view.py # Interactive 3D CAD viewer
│ ├── save.py # Headless scene exporter & snapshot generator
│ ├── bridge.py # AI Agent CollabBridge client
│ ├── core/ # Modeling, rendering, SDF, and geometry engine
│ ├── scenes/ # Demo procedural scenes
│ ├── scripts/ # Cross-platform environment & setup helpers
│ ├── ci/ # Tool-specific CI composite action
│ └── tests/ # 222 unit and integration tests (95% coverage)
└── LICENSE # Repository license
Contributing & Development
- Clone the repository:
git clone https://github.com/sanchousf/ai-toolkit.git cd ai-toolkit
- Navigate to the tool directory (e.g.
cd cad) and run the setup script:- Linux / macOS / Termux:
./setup_dev.sh - Windows:
setup_dev.bat
- Linux / macOS / Termux:
- Run tests with coverage:
- Linux / macOS / Termux:
./run_tests.sh - Windows:
run_tests.bat
- Linux / macOS / Termux:
Metadata
Release files for sanchousf-ai-toolkit 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| sanchousf_ai_toolkit-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Release files / sanchousf_ai_toolkit-0.1.0-py3-none-any.whl
| Download URL | sanchousf_ai_toolkit-0.1.0-py3-none-any.whl |
|---|---|
| Size | 259.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3da92012fe80a7d1df765225ea402acc358b4097a8e7d5d5e33a1eb1bc53e4a3
|
|
BLAKE2b-256 checksum How to use checksums |
7078d42bb35534442fbbcc1bffabe5b9fe3e425a81c6110a2d81a95f188ebb27
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 18, 2026.
Transparency log