We write your reusable computer vision tools. 💜

Generate 16:9 & 9:16 videos with your HeyGen avatar, animated backgrounds (HyperFrames), music, SFX and Hormozi captions — then publish them to every social network. Reusable skill.

LyteNyte Grid monorepo: Build powerful data tables with a lightning-fast, zero-dependency React data grid (~40 KB). Headless or pre-styled. Declarative API. 150+ enterprise-grade features. Supporte…

A repository containing many free shaders to use with ghostty (the terminal)

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

A portfolio website for projects I worked on in the past.

🦀 Small exercises to get you used to reading and writing Rust code!

Replace complex Borg Backup terminal commands with a beautiful web UI. Create, schedule, and restore backups with just a few clicks.

A macOS menu bar app that shows your real-time Claude.ai usage

Codebase pattern detection for AI agents. Scans your code, learns conventions, feeds context to Claude/Cursor or any IDE MCP. Also works fully offline with CLI

Autonomous engineering teams for Claude Code. Point Zeroshot at a GitHub issue, walk away, and return to feature complete and production-grade code

Lets you post to Twitter, Threads and BlueSky simultaneously.

Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models l…

A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.

The official Roboflow Python package. Manage your datasets, models, and deployments. Roboflow has everything you need to build a computer vision application.

Convert JSON annotations into YOLO format.

[Medium] Lane line detection using classical computer vision.

[Large] Advanced lane line detection in videos, taken from a vehicle. Thresholding, several outlier removal techniques, clustering, perspective transformation curve fitting.

NumPy aware dynamic Python compiler using LLVM

[Small] PID control and PID parameter calibration using Twiddle algorithm for a simulated vehicle.

[Large] A path planner that can navigate safely on a virtual highway, keeping to speed limit, changing lanes and avoiding other vehicle. Robust to simulator errors.

[Medium] Particle filter localisation of a simulated vehicle.

[Medium] Cloning of driving data for a vehicle in a simulation, using deep learning. Data gathering and processing.

[Small] Extended Kalman Filter state estimation for a simulated vehicle.

[Small] Traffic sign classification using Tensorflow and LeNet.