A Navidrome plugin that integrates AI-powered song and artist similarity features from AudioMuse-AI into the Navidrome music server frontend.

A curriculum-aligned knowledge graph and dataset for STEM subjects, designed to benchmark and train LLMs to understand the structured prerequisites and relationships of K-12 education.

An MCP server that enables LLMs to inspect MySQL schemas and execute SQL queries, featuring built-in PII redaction and secure remote access.

Paper‑Agent is an open‑source AI research assistant that automates literature review creation. It uses a LangGraph‑driven workflow of specialized agents (search, read, analyse, outline, write) that call LLMs (OpenAI/Anthropic compatible) to retrieve papers from arXiv, OpenAlex, and Semantic Scholar, download PDFs, convert them to markdown, chunk and embed the text in ChromaDB, analyse sub‑topics, generate a structured outline, and write each section of a review. A FastAPI backend streams real‑time progress via SSE, persisting sessions in SQLite + files, while a Vue 3 front‑end lets users configure model providers, monitor token usage, and resume work after refresh. Installation uses the `uv` Python package manager and npm for the UI; configuration is done via `config/model.json`. The project is fully open source and invites contributions via tests and PRs.

VLA-JEPA is a Vision-Language-Action model that integrates a latent world model to enhance robotic task performance and environment understanding.

A benchmark that measures the ability of CLI agents to autonomously post-train pre-trained LLMs to improve their performance on specific benchmarks.

Skills for Copilot Studio is a plugin (for Claude Code, GitHub Copilot CLI, and VS Code) that lets you create, edit, sync, test, and get design advice on Microsoft Copilot Studio “standard” agents using YAML files—all from your terminal or editor.

An OpenTelemetry-native evaluation framework for AI agents and RAG apps that uses LLM judges to trace and score application performance, cost, and quality.

An offline, real-time translation app for Android that uses on-device AI models like Whisper and NLLB to enable private, internet-free conversations.

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

A structured, reusable prompt design framework that treats prompt engineering as a programming language to create high-quality, scalable AI personas.

An AI-powered manga translation and management suite that automates text detection, OCR, translation, and image inpainting, featuring a RAG-based story analysis engine.

A highly efficient gradient boosting framework that uses tree-based learning algorithms to handle large-scale data with high speed and low memory usage.

An AI-powered tool for the automatic segmentation of most major anatomical structures in CT and MR images, based on the nnU-Net framework.

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

A Godot Engine plugin that implements the Model Context Protocol (MCP), enabling AI assistants to read and modify scenes, scripts, and resources directly via natural language.

An OCR engine that extracts either raw text or structured JSON data from receipt images using Tesseract and LLMs.

A unified ComfyUI node that simplifies the MiniMax H3 video pipeline by consolidating text-to-video, image-to-video, and advanced editing tools into a single interface.

An open-source C++ and Python library for audio analysis and music information retrieval, providing a wide array of signal processing algorithms and music descriptors.

A one-stop creation suite for CS2 that automates demo analysis, highlight recording via OBS, and video editing, featuring AI-generated commentary on gameplay.

An open skills marketplace that provides AI agents with native, natural-language access to centralized and decentralized crypto services, including trading and wallet tracking.

An automated pipeline that transforms a topic into a professional 4K video podcast by integrating AI research, TTS audio, and Remotion-based video rendering.

A PyTorch library that enables accessible large language models through 4-bit and 8-bit quantization for both inference and training.

Darkbloom (d‑inference) is an open‑source, decentralized inference platform that lets owners of Apple‑silicon Macs rent out idle GPU resources as an OpenAI‑compatible backend. A Go coordinator runs in a GCP Confidential VM, handling authentication, billing, and routing, while a hardened Swift CLI on each Mac runs models in‑process via MLX. Every request is end‑to‑end encrypted (NaCl Box) and the provider process is locked down with the Hardened Runtime, SIP, and kernel‑level debugger denial, ensuring the Mac’s owner cannot read prompts or responses. Consumers use the standard OpenAI/Anthropic API by pointing their SDKs to `https://api.darkbloom.dev/v1`. Providers install the CLI with a one‑liner, link their account, and earn per‑token revenue; self‑route and direct modes enable free, private inference on one’s own machine. Pricing is roughly half of major hosted APIs, and the system is currently in public alpha.

An open-source framework for automatically building, evaluating, and evolving LLM-based agentic workflows through iterative feedback loops.

A DOCX-native document engine that allows for browser-based editing and programmatic automation via a unified API, specifically designed to be agent-ready.

An automated research workflow that searches, recommends, and analyzes academic papers from arXiv and Semantic Scholar, integrating the results directly into Obsidian notes.

A collection of ComfyUI custom nodes featuring an AI Video Builder for scene-by-scene production, video enhancement, and LoRA training for AI video and music video creation.

A complete X/Twitter automation toolkit providing scrapers, a CLI, and an MCP server for AI agents, allowing full platform interaction without requiring official API keys.

An AI-powered card note-taking application that uses RAG to enable natural language retrieval of self-hosted notes.

A CLI tool for WeChat Official Account creation and publishing that provides Agent-ready interfaces for automating Markdown conversion, layout rendering, and multi-platform draft synchronization.

A Codex plugin that enables an AI agent to draw scientific figures live inside the desktop draw.io editor by calling draw.io’s graph API via a local MCP server. It provides tools for launching draw.io, adding shapes/edges, inspecting the canvas, saving the diagram, and exporting to PNG/SVG/PDF. The repo is legacy; active development has moved to the `scientific-illustrator` project.

An observability and automated fixing platform that helps developers make AI agents self-healing by capturing traces, grouping failures, and dispatching coding agents to implement fixes.

A library for mechanistic interpretability that allows researchers to reverse engineer generative language models by accessing and manipulating their internal activations.

A speculative inference engine optimized for heterogeneous consumer GPUs and APUs, providing high-throughput local LLM execution via custom kernels and hardware-tuned optimizations.

A ComfyUI pipeline for creating consistent character sprites, allowing users to manage appearance, poses, clothing, and emotions across multiple images.

A quota and token tracking tool for OpenCode that provides real-time visibility into AI model usage and usage limits across multiple providers.

A browser-native, local-first slide editor that uses Web AI and WebGPU to provide AI-powered slide generation, translation, and presentation tools without a backend.

A programming paradigm and meta-framework called Cordis that enables spatiotemporal composability, allowing software components to be dynamically added, removed, and reverted without side effects.

A Rust implementation of the Free Spaced Repetition Scheduler (FSRS) that provides tools for scheduling, parameter optimization, and simulation for memory retention apps.

A performance and correctness testing suite for the NVIDIA Collective Communications Library (NCCL) used to benchmark multi-GPU and multi-node communication.

A Rust and Python implementation of Behavior Trees for creating modular and reactive AI and robotics control systems.

An MCP server that integrates SonarQube Server or Cloud with AI agents, enabling them to access code quality and security analysis directly.

director is an AI‑agent skill that guides a language model through the full video‑production pipeline—script, visual style, characters, voice, shot‑by‑shot prompts—and uses LibTV or 即梦 CLI tools to generate ready‑to‑edit video clips. It supports three modes (Animated Explainer, Storytime Animation, Cinematic Drama) and is installed as a skill directory for agents like Codex.

A local-first AI agent workbench that enables AI to plan, execute, and verify software development and content creation tasks across a shared GUI and TUI runtime.

An opinionated Agent Skill that prevents AI-generated UIs from looking like generic templates by providing a visual direction selection process and strict professional design standards.

A fully local, uncensored AI companion system that integrates LLMs, TTS, image generation, and Live2D animations to create private, character-driven virtual partners.

CCB (Claude‑Codex‑Bridge) is a cross‑platform terminal UI that lets you run many LLM‑backed CLI agents (Codex, Claude, Gemini, etc.) together in visible panes, define collaboration graphs, share a project‑wide memory file, and even control the workspace from an Android app. Install via npm, configure with a built‑in UI, and manage providers, roles, and rich‑media terminals from the command line.