Highlights
Lists (5)
Starred repositories
Agent skills for Obsidian. Teach your agent to use Markdown, Bases, JSON Canvas, and use the CLI.
Enable Claude Code to learn in real-time, update it's knowledge, and grow with you, using supermemory.
Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.
PyTorch code and models for VJEPA2 self-supervised learning from video.
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …
A world model that replaces attention and recurrence with reaction-diffusion PDEs. Latent states evolve through Laplacian diffusion and learned reaction terms on a 2D spatial grid, giving the model…
Automated vulnerable machine deployer for penetration testing training and CTF challenges. Deploys Docker containers with multiple configurable attack surfaces over SSH, managed through a web UI wi…
A offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.
graphzero: High performance C++ backed python library for graphs
A visual-based graph node editor for training computer vision models.
Machine learning robot with Arduino Uno, LIDAR and ORP chassis
infinition / lerobot
Forked from huggingface/lerobot🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
ArXiv Studio is a paper layout editor for academic content, built with one shared codebase for:
BeamForge is an experimental text generation engine coded in Rust from scratch. Unlike modern LLMs that use extremely demanding deep neural networks, BeamForge relies on a stochastic semantic graph…
LSTN is an experimental text generation engine that models language not as static probabilities, but as a dynamic and "liquid" neural network. Each trigram (3-character sequence) acts as an individ…
ERLM is a hybrid language model architecture that combines a global probabilistic base model (n-gram) with an advanced episodic memory system via Contextual RAG (Retrieval-Augmented Generation).
Branchez le boîtier LaRuche sur votre réseau, et l'IA devient disponible pour tout appareil connecté. Zéro configuration, zéro cloud, zéro compromis sur la vie privée.
A lightweight, local-first protocol for automatic discovery and communication between AI nodes on a local network.
FluidVLA is Transformer-free Vision-Language-Action model for real-time edge robotics. - Replacing O(N²) self-attention with Reaction-Diffusion PDEs.
LiquidBrain is an experimental language modeling engine written entirely in Rust. Rather than encoding language as static weight matrices (as in Transformers or classical n-gram models), it builds …
FluidLM is a Transformer-free language model replacing O(N²) self-attention with reaction-diffusion PDEs - achieving O(N) scaling, adaptive computation, and no KV-cache.
LAN Orchestrated Key Infiltrator - Autonomous network recon payload for the Hak5 WiFi Pineapple Pager — inspired by Bjorn/Ragnar, rebuilt with themes, web UI, and expanded functionality.
Desktop app for managing Hytale dedicated servers. Dashboard, console, updates, backups, mods, config, port forwarding.
An application written in C++ to modify the Windows 11 Taskbar.
BinaryManager, allows you to install (copy) your individual scripts, or programs in a folder (for more complex apps), into your /bin for global use.
An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.
Gnome Extension to bring macOS's Spotlight functionality