A Python package for balancing biased data samples using weighting methods to ensure a sample accurately represents a target population.

A desktop app that uses AI to generate macOS app icons in the .icns format, allowing users to describe their desired design and iteratively refine the result.

A research project and evaluation framework that analyzes whether Reinforcement Learning with Verifiable Rewards (RLVR) expands an LLM's reasoning capacity or merely optimizes its sampling efficiency.

A tool that translates EEG and biometric data from biosensors into OSC parameters for VRChat, enabling brain-controlled avatar animations and effects.

A tool that streams client-side browser logs to the development terminal or an MCP server, enabling AI coding assistants to see runtime errors and logs.

An agent-native video director skill that turns text prompts into reproducible video projects by automating asset sourcing, shot planning, and ffmpeg rendering.

A Vim and Neovim plugin that integrates GitHub Copilot to provide AI-powered coding suggestions based on natural language prompts.

A PyTorch implementation of RLHF on the PaLM architecture, providing tools to train a base model, a reward model, and align them using a reinforcement learning trainer.

A web-based user interface for Stable Diffusion that provides tools for image generation, upscaling, and prompt engineering with optimizations for low-VRAM GPUs.

A lightweight and powerful PyTorch baseline for object and person re-identification, providing a comprehensive set of architectures and loss functions for cross-camera object retrieval.

Elyra is a collection of JupyterLab extensions that add AI‑focused features such as a visual pipeline editor, batch‑job execution for notebooks/Python/R scripts, reusable code snippets, LLM‑powered code assistance, hybrid runtime support via Jupyter Enterprise Gateway, and Git integration. Installable via pip or conda (or via Docker), it lets data‑science teams build, run, and version‑control AI pipelines without leaving the notebook environment.

An AI writing companion for Obsidian that enables chatting with AI directly in notes and referencing other vault notes via wiki links.

AugMix is a data processing technique that mixes augmented images and enforces consistent embeddings to improve the robustness and and uncertainty calibration of image classification models.

A BERT-based relation extraction model for Chinese text that identifies semantic relationships between entities, achieving over 95% accuracy on the Baidu DuIE dataset.

A local-first terminal coding agent powered by Ollama that can read, edit files and run commands while keeping all data on the host machine.

A collection of Unreal Engine 5 examples demonstrating high-performance AI and crowd simulation using the Mass ECS framework.

A plugin for the LLM CLI tool that enables interaction with models hosted on local, remote, or cloud-based Ollama servers.

An AI-powered technical analysis tool for the A-share market that combines historical data and technical indicators with Deepseek LLM to generate professional HTML investment reports.

A PyTorch-based image classification pipeline for detecting crop diseases, featuring a ResNet50 backbone and modern PyTorch 2.x optimizations.

An autonomous security agent that performs automated penetration testing, LLM red-teaming, and provides a cryptographic identity standard for AI agents via the Agent Trust Protocol.

A declarative YAML-based language for creating reliable, composable LLM prompts and integrating them into software systems with support for control flow and code execution.

A set of performance optimizations for Qwen3.5-122B-A10B on NVIDIA DGX Spark, increasing inference speed from 28.3 to 52 tokens per second using hybrid quantization and speculative decoding.

An AI-native terminal emulator that integrates project-aware AI assistance to predict commands, resolve errors, and execute tasks autonomously.

A PyTorch implementation of Google Research's MetNet models for short-term and global precipitation forecasting using satellite and atmospheric data.

A modern, highly customizable interface framework for Stable Diffusion WebUI that improves the workflow and visual experience of AI image generation.

An open-source framework for training and deploying robot world models to evaluate robot policies through controllable video generation.

An open-source AI coding agent for VS Code that supports local-first execution via llama.cpp and Ollama, featuring semantic codebase search and integrated developer tools.

An AI-native SRE control plane for Kubernetes that automates the incident lifecycle from diagnosis to verified recovery using a guarded agentic loop.

A self-hosted framework that turns an AI coding agent into a persistent Slack teammate that executes tasks on a user-controlled local machine.

A comprehensive C++ framework for background subtraction in computer vision that provides over 40 algorithms to detect moving objects in video streams.

A Keras implementation of Temporal Convolutional Networks (TCN) that provides a more stable and parallelizable alternative to LSTMs and GRUs for long sequence modeling.

Claude Night Market is a plugin marketplace that extends Anthropic’s Claude Code IDE with 23 safety‑guarded plugins for git workflows, test‑driven development, spec‑driven development, autonomous agents, and many domain‑specific utilities. Install the marketplace, pick the plugins you need, and run high‑level commands like `/attune:mission` to manage the full feature lifecycle inside Claude Code.

An archived experimental operations platform for OpenClaw designed to orchestrate and operate AI agents.

A browser extension that allows users to save prompts and responses from multiple LLMs like ChatGPT, Claude, and Mistral directly into Notion databases.

A Python package and CLI that computes eight standard image‑similarity metrics (RMSE, PSNR, SSIM, FSIM, ISSM, SRE, SAM, UIQ) for two images. Install via pip, optionally add speed‑ups, and use either the `image-similarity-measures` command or the `evaluation` function in code. Useful for quantitatively assessing image‑processing or AI models, especially in remote‑sensing contexts.

Neighbor is a Rails gem that adds vector‑based nearest‑neighbor search to ActiveRecord models. It supports PostgreSQL (pgvector or cube), MariaDB, MySQL (HeatWave), SQLite, Redis, and S3, offering many distance metrics, multiple vector types, and both exact and approximate indexing. Use it to build semantic search, recommendations, or hybrid retrieval directly inside a Rails app.

An open-source AI market agent that researches assets, forms investment theses, and executes trades across onchain and traditional financial markets.

An AI-powered code exploration platform that helps developers understand GitHub repositories through an interactive dashboard and a codebase-aware AI chat assistant.

A family of large-scale autoregressive vision encoders that provide high-performance backbones for multimodal understanding and image recognition.

A PyTorch implementation of the SASRec model for sequential recommendation, providing a self-attentive approach to predict user item interactions.

Fuji-Web is an AI-powered browser extension that autonomously navigates websites and executes tasks based on user intent, providing step-by-step explanations of its actions.

A set of tools and models for inspecting sparse circuit models, featuring a Streamlit dashboard for visualizing task-specific circuits found through pruning.

A sketch extractor that uses deep learning to convert illustrations, anime art, and manga into clean line art and sketches.

A Streamlit component that adds an interactive sketching canvas using Fabric.js, enabling users to draw shapes and annotations and return the data to Streamlit.

A Go kernel for Jupyter and nteract that allows users to run Go code interactively in a browser-based notebook for data science and documentation.

A collection of n-dimensional RRT-based motion planning algorithms, including RRT* and RRT-Connect, optimized with R-trees for efficient pathfinding.

A Rust‑based, step‑by‑step course that guides you to implement an in‑memory vector database, covering Arrow tables, DataFusion integration, and several ANN indexes (IVFFlat, NSW, HNSW, IVF‑PQ), with SQL support and benchmark tools.

A platform for persistent AI companions with their own isolated Linux runtimes, enabling them to execute code, manage files, and run background automations.