A programming language embedded in C++ and Python designed for writing high-performance image and array processing code across diverse hardware architectures.

A desktop tray app that reduces token costs for AI coding agents by routing requests through a local optimization pipeline that compresses prompt bloat.

A governance and engineering system that transforms rough workflows and prompts into reusable, cross-platform AI agent skill packages with built-in evaluation and release gates.

A Kubernetes operator that simplifies the deployment, autoscaling, and management of Ray clusters for distributed AI workloads like LLM training and inference.

A production-ready project generator that scaffolds full-stack AI agent applications using FastAPI and Next.js, featuring built-in RAG, authentication, and enterprise integrations.

An open-source reference app for building and running background coding agents on Vercel, featuring a decoupled agent runtime and isolated sandbox environments.

A GUI for managing WSL on Windows and native VMs on macOS, featuring an MCP server and AI assistant that can actively operate and configure your Linux environments.

A Claude Code skill that teaches the AI concrete, mechanical design rules from the book Refactoring UI to create professional-looking user interfaces.

A collection of portable knowledge packs that teach AI coding agents Home Assistant best practices to prevent common configuration errors.

VeOmni is a versatile framework for scaling the pre-training and post-training of single- and multi-modal models across various hardware accelerators using a modular, trainer-free design.

A lightweight, end-to-end OCR vision-language model that unifies document parsing and text extraction with speculative decoding for faster inference.

An open-source, expressive robot platform for AI builders featuring Python/JS SDKs and an app store integrated with Hugging Face Spaces.

A local AI search engine that automatically indexes folders to provide agents with precise code and document retrieval, reducing token costs and improving coding efficiency.

An open-source, local-first AI autocomplete tool for macOS that provides system-wide inline text suggestions using on-device models.

An MCP server that enables AI assistants to perform trading operations and retrieve market data for stocks, options, and crypto via the Alpaca Trading API.

A generative 3D world engine that converts text and images into simulation-ready 3D assets and environments for embodied AI, deployable across multiple robotics simulators.

An all-atom biomolecular foundation model that uses co-folding for structure prediction, design, and optimization in drug discovery.

An AI-powered research workspace for annotating and understanding scientific papers with verifiable citations and cross-paper synthesis.

A CLI tool for defining and running deterministic, version-controlled multi-agent workflows using YAML configurations and the GitHub Copilot SDK.

A local CLI tool that converts plain English requests into shell commands using a fine-tuned Qwen2.5-Coder model, featuring a built-in safety checker for dangerous operations.

A set of agent skills that enable AI agents to trade stocks, crypto, and forex and manage wallets across multiple blockchains using natural language.

A comprehensive training suite for diffusion models that provides tools for dataset preparation, fine-tuning, and model conversion through a GUI or CLI.

A collection of sample apps and tutorials for deploying and optimizing machine learning models on Qualcomm Snapdragon devices across Android, Windows, and Ubuntu.

An open-source auto-aiming and fire-control system for combat robots that uses neural network detection and trajectory planning to maximize hit rates and minimize kill times.

An experimental framework from AMD Research that enables fast, scalable inference of quantized neural networks on FPGAs by generating customized dataflow architectures.

An efficient and scalable reinforcement learning training framework that extends support to vision language models and multiple RL algorithms like GRPO.

A toolkit for training neural networks to model the behavior of guitar amplifiers and audio equipment, exporting them for real-time use.

A local-first audio and video transcription tool that converts recordings into structured Markdown notes and enables AI-powered Q&A over the content.

Live Avatar is a research‑grade system that turns spoken audio (plus an optional reference image or text prompt) into a continuous, real‑time video of a talking avatar. Built on a 14 B diffusion backbone (WanS2V‑14B) with a LoRA fine‑tune, the authors achieve ~45 FPS streaming on multi‑GPU H800 hardware and can generate videos longer than 10 000 seconds via block‑wise autoregressive processing. The repo provides Conda‑based installation, multi‑GPU and single‑GPU inference scripts, optional FP8 quantisation and JIT compilation for speed, and a Gradio UI. Model weights are hosted on Hugging Face under Apache 2.0.

A sudoless Apple Silicon system monitor providing deep visibility into the Neural Engine, Media Engine, and memory bandwidth for AI and media workloads.

A Neo4j-compatible graph database that integrates vector retrieval and historical versioning in one engine for AI agent memory and Graph-RAG.

A pytest-native safety and security testing framework designed for red teaming and risk assessment of agentic AI applications.

Writing‑Agent is a Windows‑compatible, Claude‑Code‑driven tool that turns article creation into a multi‑stage, reproducible pipeline with evidence tracking, fact‑checking, and AI‑tone removal. It works via CLI, a plugin, or a preview desktop app and supports low‑cost Anthropic‑compatible models such as deepseek‑v4‑flash.

A cross-platform desktop application for AI-assisted video masking, segmentation, and object removal using models like SAM2 and MatAnyone.

A collection of fast, end-to-end text-to-speech models supporting a wide variety of languages, designed for efficient execution on CPU and GPU.

An all-in-one AI framework for semantic search, LLM orchestration, and language model workflows, featuring a built-in embeddings database for RAG and autonomous agents.

A curated registry of AI agents that implement the Agent Client Protocol (ACP) and support user authentication, providing a discovery mechanism for client applications.

A structural code navigation tool and MCP server that helps AI agents read codebases more efficiently by providing outlines, definition-first search, and call-chain tracing.

An agentic code research platform that provides AI agents and developers with token-efficient, evidence-based context from local and GitHub repositories using a Rust-powered engine.

A production-grade Sanskrit chant text-to-speech system that generates traditional melodic recitation instead of flat read-aloud speech.

A PotPlayer subtitle translation plugin that uses OpenAI-compatible AI APIs to provide real-time, context-aware translations of subtitles.

Copper is a Rust runtime for building static, zero‑allocation robot task graphs that can run on anything from Linux to bare‑metal MCUs. It records execution into a replayable log, offers ROS 2 interop, and provides tooling (project templates, visualisation, replay) for deterministic, real‑time robot software.

A linter for AI agent configurations that validates files like CLAUDE.md and .cursorrules to prevent AI tools from silently ignoring custom instructions.

A platform for hybrid quantum-classical computing that integrates QPUs, GPUs, and CPUs into a single programmable system.

A lightweight, single-binary coding agent harness written in Go that provides a unified interface for 30+ AI providers and built-in tools for filesystem and shell interaction.

An evidence-bound resume toolkit for AI internship seekers that polishes resumes, tailors them to JDs, and generates interview prep based on verifiable technical evidence.

SDAR is a self-distilled agentic reinforcement learning framework that unifies Agentic RL with on-policy self-distillation to improve LLM agent performance in interactive environments.

Tavily MCP is a Model Context Protocol server that exposes four web‑knowledge tools—search, extract, map, and crawl—so LLM‑based agents (Claude Code, Cursor, etc.) can fetch up‑to‑date web data, pull page content, generate site maps, or bulk‑crawl sites. It can be used via Tavily’s hosted endpoint or run locally with a single `npx` command, authenticating with an API key or optional OAuth. Configuration is done through environment variables (`TAVILY_API_KEY`, `DEFAULT_PARAMETERS`, `TAVILY_HUMAN_ID`). The server enables real‑time web access for AI assistants, RAG pipelines, and productivity tools without custom scraping code.