An MCP server that integrates Google Calendar with AI assistants, enabling them to manage schedules, detect cross-account conflicts, and create events from images or PDFs.

A ROS 2 wrapper for Ultralytics YOLO models that enables object detection, tracking, instance segmentation, and 3D object localization for robots.

A toolbox for holistic 3D mapping and structure from motion that jointly optimizes points, lines, planes, and parametric primitives for more accurate 3D reconstructions.

An AI-powered assistant for Home Assistant that analyzes your smart home devices and setup to suggest tailored, ready-to-paste YAML automations.

A secure, scalable standard and Python implementation for defining and interacting with tools across multiple communication protocols like HTTP, CLI, and MCP.

An interactive diffusion pipeline for real-time streaming video generation that optimizes throughput and latency across single and multi-GPU setups.

ainovel‑cli is a Go‑based terminal UI that uses a multi‑agent LLM pipeline (Coordinator, Architect, Writer, Editor, Arbiter) to automatically draft long‑form novels. It offers a fully Vietnamese‑localized interface, supports Vietnamese or Chinese output, works offline with local Ollama models or with cloud APIs, and provides rich slash‑command controls for planning, editing, style simulation, import/export, and real‑time steering. The project includes checkpoint recovery, rolling two‑tier planning, and 4‑level context compression to handle very long stories.

FPO++ Code Release provides reproducible RL experiments for robot locomotion (Isaac Lab) and dexterous manipulation (LeRobot/robosuite). It includes setup scripts, training commands, and expected results for the Flow Policy Optimization algorithm, with all dependencies managed via per‑experiment conda environments.

A single-node launcher for DeepSeek V4 Flash on NVIDIA DGX Spark, enabling high-throughput serving with speculative decoding and context windows up to 384k tokens.

A tool to export and run SAM, SAM 2, SAM 3, MobileSAM, and EfficientSAM models in ONNX Runtime for portable and efficient deployment.

Surflo is a 3D surface flow model that turns a handful of unposed RGB views into detailed 3D meshes using a global state and flow matching.

A Claude Code skill that automatically turns long-form talking-head videos into short, social-ready clips with automated reframing and subtitles.

A Windows AI upscaler that enhances, upscales, and de-noises images and videos locally using DirectX12 compatible GPUs.

A nested U-Net architecture for medical image segmentation that improves upon the original U-Net by redesigning skip connections and allowing for flexible network depth.

A high-performance toolkit and 3-trillion-token open dataset for curating and cleaning large-scale corpora for language model pre-training.

PhiZero is a world model that predicts future physical dynamics by reasoning in a discrete Physical Language before rendering the results as video.

A productivity kit for solo entrepreneurs featuring 26 AI-agent-ready skills to automate marketing, content creation, and business operations, specifically optimized for the Korean digital ecosystem.

A lightweight, zero-dependency monitoring tool for NVIDIA GPU systems that provides a TUI, CSV logging, and a Prometheus exporter for tracking CPU, GPU, and memory metrics.

An AI Chief of Staff that extends Claude Code to provide session continuity, goal tracking, and integrations with productivity tools like Google Workspace and Slack.

An open-source expressive robot lamp featuring 5-axis movement, computer vision, and audio interaction for interactive physical presence.

RustFinance Terminal (Rust‑Forge) is an open‑source, Rust‑only trading platform that combines real‑time market‑data ingestion (direct exchange binary feeds, broker APIs, crypto WebSockets), a full‑screen terminal UI, Claude‑powered AI commentary, a library of micro‑structure indicators, risk models, and execution algorithms (TWAP, VWAP, Almgren‑Chriss, etc.). It offers native Nasdaq/NYSE connectivity, a modular crate architecture, and research‑grade documentation, targeting quant researchers, low‑latency developers, and AI‑enthusiasts.

A toolkit for extracting chat history, code context, and diffs from AI coding assistants to create datasets for machine learning training.

cco is a sandboxing wrapper for AI coding agents (Claude Code, Codex, etc.) that runs them in an isolated environment to protect your system from prompt injections and accidental damage, while preserving a seamless terminal experience.

A lightweight macOS menubar app that tracks Claude Code usage limits and provides notifications when AI agent sessions need user attention.

A tool to detect fake citations in academic papers by extracting references from PDFs and validating them against multiple academic databases.

An AI-driven CLI that tests Android and iOS apps using natural language specifications, utilizing multimodal models to interact with the UI and generate test reports.

A bundled multi-agent orchestration harness for OpenCode V1 that provides a curated set of agents, plugins, and MCP servers for AI-driven software development.

Kalshi Trading Bot CLI is a Bun‑based command‑line tool that uses Octagon AI probability estimates to find edges on Kalshi prediction markets, size trades with half‑Kelly, enforce a five‑gate risk engine, and support basket building, backtesting, paper‑trading, and a learning loop (calibration, reflection, hypotheses). Install via `bunx kalshi-trading-bot-cli@latest`, run the setup wizard for API keys, then use commands like `search`, `analyze`, `buy`, `basket build`, and `portfolio` to trade or simulate strategies.

A reinforcement learning framework based on NVIDIA Isaac Lab for training humanoid loco-manipulation policies with validated sim-to-real transfer capabilities.

A fast, scalable machine learning system focused on online learning and reinforcement learning that uses the hashing trick to maintain a bounded memory footprint.

A comprehensive machine learning toolkit for Rust, similar to scikit-learn, providing classical ML algorithms and preprocessing tools.

A multi-modal geospatial machine learning framework for agriculture and sustainability that fuses satellite imagery, weather data, and elevation maps to generate robust agricultural insights.

A suite of tools for managing and monitoring NVIDIA data-center GPUs in cluster environments, providing health monitoring, diagnostics, and governance policies.

An AI agent system that automates the end-to-end mathematical modeling process, from problem analysis and model selection to code execution and academic report generation.

A reinforced cognitive framework for end-to-end autonomous driving that combines a Vision-Language Model with a diffusion planner to generate safe, continuous trajectories.

A local-first desktop companion powered by MiniCPM that provides a chat interface and visual reactions to the activity of coding agents.

A LangGraph-based general-purpose AI agent framework that implements a secure two-phase skill execution protocol and sub-agent delegation for observable and extensible workflows.

A collection of reference GPU kernels and problem specifications used to evaluate and benchmark custom kernel implementations in GPU Mode competitions.

A lightweight training environment with a Web UI for performing LoRA fine-tuning on the Anima model.

A plugin for the DeepSeek Harness web interface that enables workspace path references via an @-mention system, allowing users to easily point AI agents to specific files and directories.

A research-paper learning plugin for AI agents that transforms PDFs into interactive study environments with automated summaries, code demonstrations, and a web viewer.

A self-hosted web API that provides free, unlimited access to various LLM providers through a single HTTP interface, eliminating the need for paid API keys.

A collection of high-performance, custom-written GPU kernels for H100 and GB300 that optimize matrix multiplication and sum reduction operations.

A family of large-scale time series foundation models, including univariate and multivariate versions, for efficient and accurate forecasting.

A Discord bot that transforms servers into collaborative LLM frontends, using Discord's reply chains to manage conversation history without a database.

A from-scratch x86_64 operating system where the only interface is natural language, allowing an LLM to manage hardware, write drivers, and create apps via 64 kernel syscalls.

A ComfyUI extension that enables distributed and parallel processing across multiple GPUs and machines to accelerate image and video generation and upscaling.

A minimal PyTorch re-implementation of Qwen 3.8 that provides a readable codebase and int4 quantization support for easier model deployment.