A standards-style pattern language for turning complex engineering and research work into explicit, reviewable reasoning to maintain coherence across teams and AI agents.

An open-source AI portal that allows users to quickly build and operate a production-grade hub for AI agents, prompts, and tools by integrating with existing AI platforms.

A high-performance streaming Markdown renderer for Vue 3 and other frameworks, designed to eliminate flicker and layout shifts in AI chat interfaces.

An automation platform for building and running agentic workflows across multiple channels using YAML, MCP, and RAG.

A collaborative platform that gives local AI coding agents persistent identities and shared rooms, allowing teams to interact with them as if they were team members.

A Node.js library that provides pre-built bindings for llama.cpp, enabling developers to run LLMs locally with automatic hardware acceleration and TypeScript support.

A software stack for physics-based simulation and Reinforcement Learning environments powered by the MuJoCo physics engine.

A Python library for user-friendly time series forecasting and anomaly detection, offering a unified API for models ranging from classic statistical methods to deep neural networks.

A platform for building AI agents featuring a no-code visual builder and a TypeScript SDK with full two-way synchronization for collaborative agent management.

Chorus is a management harness for AI coding agents that implements the AI-DLC workflow, allowing teams to orchestrate multiple agents and ensure human verification of AI-proposed code.

An interactive AI portfolio featuring a voice-enabled chatbot with agentic RAG, a 6-layer prompt injection defense, and a comprehensive LLMOps dashboard for monitoring and automated evaluations.

A reference solution for building enterprise RAG pipelines using NVIDIA NIM microservices, supporting multimodal data extraction and agentic multi-hop retrieval.

Ping Island is an open‑source macOS menu‑bar/notch app that monitors a wide range of AI coding assistants (Claude, Codex, Gemini CLI, Hermes, Pi, Qwen, Kimi, OpenClaw, Cursor, Qoder, Copilot, etc.). When an assistant needs approval, a question, or shows a completion, the app expands from the notch, displays the context, and lets you approve/answer or jump back to the originating terminal/IDE with one click. It supports remote Linux hosts via a lightweight `PingIslandBridge`, offers three visual themes, custom sound packs, per‑client mascots, and can auto‑approve Claude sessions. Installation is via Homebrew Cask or a downloadable DMG; the source builds with Xcode/Swift 6.1. The project is licensed under Apache 2.0 and includes a test suite and documentation for extending support to new AI clients.

Dust is a custom AI agent platform that allows users to create specialized AI agents to speed up their professional work.

A resilient, HTTP-based data streaming protocol designed for AI agents and collaborative apps to ensure ordered, replayable, and resumable data delivery across devices.

A React component library built on shadcn/ui that provides pre-built UI elements like waveforms and orbs for building audio and AI agent applications.

An efficient, portable GPU communication library that provides high-performance collectives, P2P transfers, and expert-parallel communication across heterogeneous GPU and NIC hardware.

A decentralized P2P network where autonomous AI agents collaboratively conduct ML research, pool compute for distributed training and inference, and share discoveries via a global leaderboard.

A cross-platform SDK that enables developers to run LLMs, vision, speech, and image generation models locally on phones, browsers, and desktops using a unified API.

A planning-and-execution layer for AI coding agents that turns high-level requests into structured plans and parallelized PRs through a rigorous design-and-review workflow.

Xybrid is an open‑source, cross‑platform SDK that runs LLMs, speech‑to‑text and text‑to‑speech models locally on devices (mobile, desktop, Unity). It provides native bindings for Flutter, Swift, Kotlin, Unity, Rust and Python, supports many popular open‑source models, and lets you chain them together in a multi‑model pipeline—all without requiring cloud services.

exxperts is a cross‑platform desktop/CLI app that runs AI agents locally with opt‑in, auditable memory. Rooms act as persistent workspaces; after each chat the agent proposes facts to remember, which you must approve. All data stays on your machine, supports any OpenAI‑compatible model, includes built‑in DuckDuckGo search, and is released under Apache 2.0.

A curated set of ~64 ultra‑compact (≈100‑line) implementations of influential machine‑learning papers, spanning from early deep‑learning milestones to the latest neural rendering and diffusion models. Designed as a learning and prototyping resource, the repo provides minimal, runnable code for each paper under an MIT license.

NVIDIA Transformer Engine is a GPU‑focused library that provides FP8/MXFP8/NVFP4 mixed‑precision support, fused kernels and a simple autocast API for PyTorch and JAX, enabling faster, lower‑memory training and inference of large language and MoE models.

A containerized development environment that isolates Claude Code with bypassPermissions enabled, providing a secure sandbox for security audits and untrusted code exploration.

A collection of musculoskeletal simulation environments using MuJoCo and the OpenAI Gym API to enable machine learning for bio-mechanic control problems.

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 CLI code search tool that uses structural awareness and cyclomatic complexity to rank results by relevance without requiring an index.

An AI-native CLI and TUI for the Longbridge trading platform that provides real-time market data, portfolio management, and trading capabilities.

A Rust‑based CLI (also packaged for Homebrew, npm, and binaries) that rewrites Codex’s SQLite state DB and rollout JSONL logs so that chat threads remain visible after you change the `model_provider`. It offers one‑off sync, continuous watch mode, and optional background‑service installation for macOS, Linux, and Windows.

A web-based UI for Claude Code and Codex CLIs that provides a visual chat interface, project management, and multi-provider AI agent coordination.

A real-time screen translation tool for Windows games that uses OCR and LLMs to translate on-screen text and audio into the user's language.

A collection of open-source Three.js experiences demonstrating interactive 3D showrooms, games, and data visualizations built with the Mint asset pipeline.

A toolkit for training and running inference on audio generation models, supporting various model types including diffusion and autoencoders.

An open-source standalone MCP host that enables developers to build and deploy AI agents by connecting LLMs with MCP servers.

An open-source Playwright library for AI-powered browser regression testing that uses natural language steps and multi-model consensus assertions to prevent test fragility.

An AI-powered subtitle editor that automates transcription, translation, and millisecond-precise timeline alignment using Gemini and Whisper.

A Python client library for the Groq REST API that provides typed, synchronous and asynchronous access to low-latency LLM services.

A collection of ComfyUI nodes that enhance image inpainting and outpainting using Fooocus SDXL models, LaMa, MAT, and advanced mask pre-processing tools.

An open-source AI programming assistant that enables multi-agent collaboration and full-cycle code development via a self-hosted browser interface.

An MCP memory layer for AI agents that provides persistent, structured graph storage with semantic retrieval and LLM-powered deduplication.

A personalized diet management platform that uses LLMs, RAG, and multimodal AI to provide intelligent meal planning, nutritional tracking, and recipe recommendations.

A PyTorch-based library that combines deep perceptual models with physics-based optimization for robot learning, providing tools for Lie groups, filtering, and second-order optimization.

VAGEN is a reinforcement learning framework for training multi-turn VLM agents that improves performance by reinforcing their internal world model through explicit visual state reasoning.

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

Vendor‑neutral Claude Fable 5 system prompt adapted for use across multiple frontier LLMs.

A suite of C++/Python utilities for processing and analyzing sensor and machine perception data from Project Aria AR glasses to support AI and machine perception research.

An AI-powered AstrBot plugin that analyzes group chat activity to generate visual reports and creative comics across QQ, Telegram, and Discord.