Yad Konrad

One-Hundred-Layers-Tiramisu. Keras Implementation of The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation by (Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero, Yoshua Bengio)

Study-Reinforcement-Learning. RL study guide — foundations through RLHF, DPO, GRPO, RLVR, agentic RL, and offline RL. Hand-written CS294 notes, 19 lecture drafts, 5 tested exercises, citations that resolve.

Nvidia-Autopilot-Keras. Keras Implementation of End to End Learning for Self-Driving Cars by (Baris Kayalibay, Grady Jensen, Patrick van der Smagt)

Keras-SegNet-Basic. SegNet-Basic with Keras

Deep-Learning-Summer-2015.

erdos-navigator. A toolkit for AI agents to explore and attempt Erdős's 1,179 unsolved mathematical problems

Mah-Paper-Notes. HTML

bourbaki. An autonomous agent for mathematical reasoning and proof

mycelium-theme. Digital garden theme for Astro + Obsidian. Wikilinks, graph view, 7 themes, 9 plugins.

SyntheaExplorations. Jupyter Notebook

StackUnderflow. StackUnderflow: the local observability for your coding agents. Search, replay, and analyse every session, all offline. Starts with Claude Code.

chimera. Open-source Python framework for building coding agents. Pick your provider, pick your tools, pick your loop. Chimera wires them together. Recreate SWE-Agent, Aider, Cline, Codex in a few lines, or design something entirely new.

CodeSearchNet. Datasets, tools, and benchmarks for representation learning of code.

openhost-vaultwarden. Vaultwarden (Bitwarden-compatible password manager) packaged for OpenHost — admin panel gated behind owner SSO