A private, cross-platform AI voice transcription and note-taking app that uses OpenAI Whisper to provide offline speech-to-text capabilities.

A pipeline parallel training script that allows for the training of large-scale image and video diffusion models across multiple GPUs.

A high-performance, scalable LLM library written in JAX and Python for pre-training and post-training large models on Google Cloud TPUs and GPUs.

XNNPACK is a highly optimized library of low-level performance primitives used to accelerate neural network inference across ARM, x86, WebAssembly, and RISC-V platforms.

The official PHP SDK for the Model Context Protocol (MCP), enabling developers to build MCP servers and clients to expose PHP tools and resources to AI models.

A collection of specialized React Native knowledge bundles that can be installed into AI coding assistants to help them optimize, test, and migrate apps.

A reference implementation of the agentic registration protocol, enabling AI agents to authenticate with services on behalf of users via identity assertions and claim ceremonies.

An open source framework for the agile development of Chisel-based RISC-V systems-on-chip, integrating processor cores, accelerators, and VLSI tooling.

A self-hosted RSS reader and personal knowledge management tool that uses intelligent aggregation and vector databases to help users manage high-volume reading.

A collection of Claude Code skills designed to automate academic research workflows, including exhaustive literature retrieval, verified proposal writing, and high-fidelity slide generation.

A federated, domain-anchored specification for cataloging and discovering agentic resources like MCP servers, skills, and APIs across networks.

A JavaScript library that enables running pretrained machine learning models directly in the browser using ONNX Runtime, removing the need for a server.

DeepLabCut is a markerless pose estimation toolbox that allows researchers to track animals and objects in video without physical markers using deep learning.

A high-fidelity robot simulation platform combining Unreal Engine 5 and MuJoCo to provide realistic rendering, high-rate physics, and ROS 2-compatible data streaming.

A set of ready‑to‑use “agent skills” that expose ElevenLabs’ speech, voice‑changing, dubbing, and music generation APIs. Install with `npx skills add elevenlabs/skills`, configure an API key, and then any compatible AI coding assistant can call the skills (e.g., text‑to‑speech, speech‑to‑text, real‑time voice chat, voice‑changer, dubbing). The repo provides Python, JS/TS, and CLI SDKs, plus a test suite for trigger and functional validation. Licensed under MIT.

A multi-subscription extension for the pi coding agent that enables automatic rate-limit rotation and failover across multiple AI provider accounts.

A composable and auditable workflow for AI agents to research, plan, and grow Roblox game websites through a seven-stage evidence-based pipeline.

Firmware that turns an ESP32 into a WiFi NAT router with WireGuard VPN, WPA2-Enterprise support, and an AI-ready MCP bridge for network control.

An open-source hardware platform providing CAD files, BOMs, and assembly guides for building and customizing robotic arms.

A command-line tool for Xiaohongshu that enables keyword research, viral content analysis, and automated engagement management using browser cookie authentication.

A SillyTavern extension that converts chat history into structured lorebook entries to preserve long-term memory and narrative continuity.

A JavaScript library for voice activity detection that allows developers to run callbacks on audio segments containing user speech.

An open-source, 3D-printed tendon-driven robotic hand designed for affordable dexterous manipulation research and reinforcement learning.

A cross‑platform demo for the 4 B‑parameter Bonsai diffusion model, offering a web‑based studio and CLI for image generation on macOS (MLX) or NVIDIA GPUs (gemlite + HQQ).

Hibiki is a model for streaming speech-to-speech translation that generates natural target speech and text in real-time as the user speaks.

A ComfyUI custom node that provides an interactive 3D viewport for controlling camera angles and generating compatible prompts for the Qwen-Image-Edit-2511-Multiple-Angles-LoRA.

A collection of Model Context Protocol (MCP) servers that enable LLMs to query Neo4j databases, manage Aura cloud instances, and maintain persistent knowledge graph memory.

A Python package for extracting structured, ontology-grounded information from text using LLMs, preventing hallucinations by validating identifiers against real-world ontologies.

An AI-powered tool that transforms EPUB books into bilingual editions, preserving original formatting and structure while providing side-by-side translations.

An open-source toolkit for implementing and evaluating prompt injection attacks and defenses, featuring specialized tools for detection and localization of contaminated prompts.

A ComfyUI node that dynamically adjusts reserved VRAM in real-time to prevent OOM errors and optimize GPU memory usage.

A cross-harness configuration organizer for AI coding tools that provides a unified dashboard to manage memories, skills, and MCP servers while optimizing token usage and detecting tool poisoning.

An AI-powered penetration testing tool that uses a multi-agent architecture to simulate human security experts in discovering vulnerabilities across Web apps and APIs.

Track4World is a framework for dense 3D tracking of every pixel in monocular videos, providing world-centric 3D scene flow estimation in a feedforward manner.

Tmax is a framework for training and evaluating terminal-using AI agents, featuring a synthetic data generation pipeline and a specialized training recipe.

A high-performance shot boundary detection tool that uses a Shot-Query Transformer to identify cuts and transitions across diverse video sources.

A local multimodal AI application for generating and editing images, video, audio, and text using various open-source pipelines and GPU backends.

Noi is an interaction-first workspace and browser that streamlines AI chat workflows through prompt management, session isolation, and a built-in terminal.

A high-performance C++ audio inference framework based on ggml that enables fast, portable local execution of TTS, ASR, and voice cloning models across multiple hardware backends.

A curated library of 130+ JSON‑based visual‑style prompt templates for AI image generation. Each `style.json` defines a reusable layout (e.g., poster, collage, typographic art) with placeholders you fill before pasting the whole file into a multimodal LLM (ChatGPT‑4‑Vision, Gemini‑3‑Pro, etc.). The repo includes preview images, example values, a validation script, and a copy‑prompt shortcut, aiming to make AI‑generated graphics consistent and easy to iterate.

A Python-native agent harness for AI coding assistants that supports any LLM, including local models, providing a flexible and open-source alternative to proprietary tools.

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 hierarchical robot foundation model for long-horizon manipulation that uses a world-model-guided high-level policy for planning and a generalist low-level policy for execution.

A full-stack open-source framework for building action-conditioned video world models, providing a complete pipeline from data preparation to 4-step real-time inference.

An open-source durable execution platform for microservices and AI agents that turns complex workflow graphs into persisted, inspectable, and recoverable executions.

An AI agent workforce platform that allows a single operator to deploy, monitor, and coordinate hundreds of isolated AI agents across a fleet of self-hosted runners.

A lightweight, modular AI application framework for Java that provides unified abstractions for LLMs, RAG, and agents, with production-ready tooling for Spring Boot integration.

An enterprise search server built on OpenSearch that crawls and indexes content from websites, file systems, and various data stores for unified full-text search.