Forge-GPU – 55 C lessons for SDL's GPU API, built with Claude Code
Open-source tutorial series teaching real-time graphics programming with SDL's GPU API. Covers everything from Hello Window to SSAO, with math lessons, engine lessons, and a UI track building font rendering from scratch. Every lesson is a standalone C program with commented code explaining why, not just what. The whole project was built with Claude Code. Each lesson also distills into a reusable Claude Code skill — copy them into your own project and build games with AI that actually understands the GPU patterns.
Does the same job
all alternatives →
- G2GPT-2 implemented using graphics shaders2025 · github.com · ▲228
Back in the old days, people used to do general-purpose GPU programming by using shaders like GLSL. This is what inspired NVIDIA (and other companies) to eventually create CUDA (and friends). This is an implementation of GPT-2 using WebGL and shaders. Enjoy!
- CCCode Claude Code2025 · github.com · ▲117
In the nature of Open Source, I am releasing something I'm actively working on but is insanely simple and will likely be made anyways. It is an SDK for scripting Claude Code. It's a lightweight (155 lines) and free wrapper around claude code This is a big deal because it seems that using claude code and cursor has become largly repitive. My workflow typically goes like this: Plan out my task into a file, then have claude code implement the plan into my code. I'm actively building a product with this, but still wanted to make it OSS! Use it now with `pip install codesys`
- IBI built a tensor library from scratch in C++/CUDA2025 · github.com · ▲119
Hi HN, Over the past few months, I've been building `dsc`, a tensor library from scratch in C++/CUDA. My main focus has been on getting the basics right, prioritizing a clean API, simplicity, and clear observability for running small LLMs locally. The key features are: - C++ core with CUDA support written from scratch. - A familiar, PyTorch-like Python API. - Runs real models: it's complete enough to load a model like Qwen from HuggingFace and run inference on both CUDA and CPU with a single line change[1]. - Simple, built-in observability for both Python and C++. Next on the roadmap is…
- IWI wrote a C++ ray tracer from scratch without AIJun 2026 · github.com · ▲155
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
