A GitHub‑only tool that daily crawls selected arXiv categories, uses a Large Language Model (default DeepSeek) to generate Chinese summaries, and publishes the results as a static site on GitHub Pages. It requires only a fork, a few secrets/variables, and runs via GitHub Actions—no servers needed.

A persistent, animated ASCII companion for Claude Code, Pi, and Oh My Pi that uses MCP to ensure the companion survives software updates.

An extension for the pi agent that allows prompt templates to define their own model, skill, and thinking level, enabling the creation of specialized slash commands for different AI tasks.

A data platform for AI/ML that abstracts data computation and serving, ensuring point-in-time consistency between offline training data and online real-time feature serving.

A model-mediated harness for coding agents that ensures reliable software development by placing a validated domain model and typed contracts between business requirements and final code.

A collection of example programs and libraries for MLX Swift, demonstrating how to build LLM, VLM, and image generation apps on iOS and macOS.

A tool for optimizing LLM serving configurations, helping users find the best GPU distribution and parallelism settings to maximize throughput under SLA constraints.

A collection of agent skills and plugins that enable AI agents like Claude, ChatGPT, and Cursor to manage Railway cloud infrastructure.

A TypeScript framework that simplifies building Model Context Protocol (MCP) servers by removing boilerplate and providing high-level APIs for tools and resources.

A collection of Docker Compose demos for deploying and orchestrating AI agents, supporting multiple frameworks and local or remote model execution.

A Python library for creating tabular synthetic data using machine learning to emulate real-world patterns while maintaining privacy.

A comprehensive ComfyUI toolkit for training, analyzing, and selectively loading LoRAs across multiple model architectures, featuring granular block-level and sub-component control.

An Angular-native node editor library for building production workflow builders, AI pipelines, and AI low-code tools with built-in drag-and-drop and state management.

An AI governance platform that helps businesses manage AI compliance, risk, and security through on-premises hosting and support for frameworks like the EU AI Act.

A lightweight Go-based gateway that transforms existing APIs and MCP servers into MCP-compliant endpoints via configuration without requiring code changes.

The official W3C repository for the WebGPU API and WebGPU Shading Language (WGSL) specifications, enabling high-performance GPU acceleration for web applications.

An unofficial Go client library that simplifies integration with the OpenAI API for text generation, image creation, audio processing, and more.

A minimal, GPU-accelerated terminal for macOS designed for AI coding, featuring one-click agent launchers, workspace management, and integrated SSH/Git worktree support.

A Python-based programming language for NVIDIA GPUs that allows developers to write high-performance kernels using Tile IR.

A JAX-powered library for solving optimal transport problems at scale, providing tools to efficiently match point clouds using discrete solvers and neural network approaches.

A local protocol-compatibility proxy that unifies multiple AI providers like GitHub Copilot and xAI Grok into a single OpenAI or Anthropic compatible API.

A lightweight, automated runner for RWKV models that provides an OpenAI-compatible API and a user-friendly interface for chat, completion, and music composition.

A library of hardware-accelerated, batchable, and differentiable optimizers built for JAX.

AppWorld is a high-fidelity execution environment simulating 9 everyday apps and ~100 simulated people, with 457 APIs, used to benchmark interactive coding and function-calling agents on complex real-world tasks. It provides task worlds, evaluation, and leaderboards for agent developers.

A lightweight native runtime for running JavaScript/TypeScript games natively with WebGPU, providing a browser-less alternative to Electron for game development.

An A2C-based reinforcement learning agent that learns to optimize the capture of crackable WPA WiFi handshakes and key material from its environment.

WaterCrawl is an open-source web crawling and data extraction platform that enables users to scrape web content and integrate it into AI and automation workflows.

A collection of optimized recommender system models and GPU libraries for large-scale training and inference, featuring automated agent-driven performance optimization.

An automation tool for Kubernetes that manages the installation and lifecycle of NVIDIA GPU drivers, runtimes, and monitoring tools as containers.

A training framework for Stable Baselines3 that provides scripts for training, evaluating, and tuning RL agents, along with a collection of pre-tuned hyperparameters for common environments.

A visual workbench for AI coding agents that replaces linear chat with a tree-structured interface for managing context, inspecting model transactions, and controlling agents remotely.

An open-source, self-hosted AI app builder engine that uses coding agents to create and host real applications in isolated Docker sandboxes on your own server.

An AST-based semantic code search tool that enables AI coding agents and developers to find code by meaning and structure, reducing token usage by up to 70%.

A native desktop environment for agentic development that organizes terminals, code, and context files on an infinite spatial canvas to reduce context switching.

A tool that centralizes AI coding assistant instructions into a single source of truth and automatically distributes them to various AI agent configuration files.

KubeSphere is a distributed operating system for cloud-native application management that simplifies Kubernetes management across multi-cloud, edge, and datacenter environments.

A reliable benchmarking suite for time-series anomaly detection that provides curated datasets, a reliable evaluation metric (VUS-PR), and a unified framework to compare 40 different detection algorithms.

An MCP server that connects AI coding agents to a running Next.js dev server to provide live runtime errors, logs, and route information.

An open-source deployment platform featuring an autonomous AI agent that handles app deployment, configuration generation, and self-healing fixes.

An open-source production-level Quantum Monte Carlo code for computing the electronic structure of atoms, molecules, and solid-state materials.

A scraper for Perplexity AI that allows developers to send prompts and collect AI-generated responses and structured metadata in formats like JSON and Markdown.

A maintained fork of gym-retro that turns classic video games into Gymnasium environments for reinforcement learning training and evaluation.

A library of communication-efficient orthonormal optimizers, including Dion and Muon, designed to accelerate convergence in distributed ML training.

A macOS desktop hub for managing multiple AI coding agent sessions (Claude Code and Codex) with integrated terminal, GitHub support, and live previews.

A concise and feature-rich Transformer library that implements a variety of experimental architectural optimizations and research-backed features for text and vision models.

SeekStorm is an open‑source Rust search engine offering native lexical (BM25, faceting, typo‑tolerance) and vector (ANN, quantisation, hybrid) indexes. It can be used as an in‑process library or as a multi‑tenant REST server, with client SDKs for Rust, Python, TypeScript, C# and Java. Designed for sub‑millisecond latency on a single commodity machine, it supports real‑time incremental indexing, sharded billion‑scale indexes, and a web UI for ad‑hoc queries.

A tool to mount Hugging Face Hub repositories and Buckets as local filesystems, enabling lazy loading of models and datasets without full downloads.

An open-source observability and self-improving layer for AI agents that detects production failures, root-causes them to source code, and opens verified fix PRs.