A ComfyUI plugin that provides a UI‑driven “director” node for multi‑segment video generation with MiniMax‑H3 models, supporting text, image, reference, and video‑to‑video tasks, audio generation, motion continuity, second‑pass refinement, and import/export of project packs.

A plugin that connects MCP-compatible AI assistants to the Godot editor, allowing agents to build scenes, edit nodes, and configure game environments in real-time.

An open-source, DIY robot vacuum cleaner built with Raspberry Pi and ROS2 that uses 2D LiDAR for autonomous local navigation without cloud dependence.

An Agent Skill that guides AI agents to generate simple, cute, and commercially viable IP mascot characters with consistent composition and style.

WeMM‑Embedding is Tencent’s open‑source multimodal embedding suite (2B/4B/9B parameters) that converts text, images, video, and visual documents into a single L2‑normalised vector. It supports a range of output dimensions via “Matryoshka” truncation, offers ready‑made inference scripts for 🤗 Transformers and Sentence‑Transformers, and includes serving wrappers for vLLM and SGLang. Benchmarks (MMEB‑v2/v3) show state‑of‑the‑art scores across image, video, document, text, and agent tasks. Models are hosted on Hugging Face and released under Apache 2.0.

A free set of Claude‑compatible “skills” that let the Claude LLM audit, optimize and create marketing assets (Google/Meta ads, SEO, email, etc.) by connecting to live ad data through Ryze’s MCP connector.

A terminal emulator designed for running multiple AI coding agents simultaneously, featuring integrated Git diffs, token cost tracking, and multi-session management.

A remote control system for AI agents that lets users dispatch tasks to agents running on their PC via a wearable voice-interface device and an iOS app.

An open-source git extension that provides line-level attribution for AI-generated code, linking every line to the agent, model, and prompt that created it.

A Codex Skill that transforms text into a structured director's proposal and a set of optimized prompts for Gemini Omni Flash to create consistent one-minute stickman animations.

An agent-driven video editing pipeline that allows coding agents to transcribe, design, and render MP4 videos based on natural language descriptions.

An optimized LLM inference server for Apple Silicon Macs featuring tiered KV caching, continuous batching, and a native macOS menu bar management app.

An autonomous LLM-based research system for public markets that uses specialized agents to find, debate, and audit trading opportunities using a strict evidence-first pipeline.

A tool that converts websites and browser sessions into a CLI, enabling humans and AI agents to automate web interactions using logged-in Chrome profiles.

A resource-efficient, Rust-based headless browser for AI agents that prioritizes page structure over visual rendering to reduce CPU and memory overhead.

A web browser that runs inside the terminal using the kitty graphics protocol, enabling developers and AI agents to interact with the web without leaving the command line.

An AI agent skill that converts scripts and voiceovers into professional talking-head videos with character-level audio sync and automated motion graphics via Remotion.

EverOS is a Python library that provides local‑first, Markdown‑backed memory for LLM agents. It stores conversations and knowledge as editable `.md` files, syncs them with SQLite and LanceDB indexes, and offers keyword or hybrid vector search via a simple HTTP API.

A tool that converts natural language, source code, and infrastructure configurations into professional, editable .drawio architecture diagrams with automated layout and synchronization.

A local-first multi-agent desktop app where a central Commander agent coordinates a team of specialized AI agents to complete complex, multi-step goals.

A harness-neutral implementation of the AI-Driven Development Life Cycle (AI-DLC) that turns AI agents into a structured, gated, and verifiable software engineering workflow across multiple AI IDEs and CLIs.

An open-source AI assistant framework that proactively plans tasks, manages long-term memory and knowledge, and controls computers across multiple messaging platforms.

A graphical desktop management tool for CLIProxyAPI that aggregates multiple AI API providers and simplifies agent client configuration.

An enterprise-grade reinforcement learning framework for large-scale model post-training that integrates SGLang for rollouts and Megatron-LM for scalable training.

A terminal-native AI coding assistant that uses persistent memory and a multi-agent system to manage complex software development tasks across sessions.

A centralized manager for AI agent skills that allows users to install, organize, and sync capabilities across multiple AI coding tools and devices.

DataFlow is an open‑source Python framework that lets you build, run, and share low‑code pipelines for generating, cleaning, and evaluating LLM training data. It provides a library of reusable operators, a visual WebUI, an AI‑assistant for auto‑creating pipelines, and a Ray‑based distributed execution layer.

An open-source 7DOF humanoid arm and standardized environment designed for physical AI research, imitation learning, and safe human-robot interaction.

An MCP-compatible server for stealthy browser automation that allows AI agents to bypass anti-bot checks and Cloudflare challenges using real Chrome instances.

SenseNova‑Skills is an open‑source collection of Agent‑Skills that add office‑automation functions (image generation, infographic creation, Excel analysis, deep research, and PowerPoint generation) to SenseNova LLMs. Drop the skill folders into an OpenClaw or hermes‑agent runtime, configure the SenseNova API, and the agent can turn a simple natural‑language request into polished data‑driven reports and decks.

A task generator that creates new, distribution-matched ARC-AGI-1 style tasks to evaluate AI models on unseen problems and prevent benchmark contamination.

Harbor is a Python framework for running and scaling benchmarks of AI agents and language models. Installable via `pip`/`uv`, it provides a CLI (`harbor run`) that lets you specify a dataset (e.g., Terminal‑Bench‑2.0), an agent (Claude‑Code, OpenHands, etc.), and a model, then executes the benchmark locally or on cloud providers (Daytona, Modal, etc.) with configurable parallelism. It also supports creating custom benchmarks and generating RL roll‑outs.

A modular Agentic RAG framework using LangGraph that implements hierarchical indexing, multi-agent parallel retrieval, and human-in-the-loop query clarification.

Y2A‑Auto is an open‑source, Docker‑ready pipeline that downloads YouTube videos, optionally runs Whisper/Voxtral ASR, translates and quality‑checks subtitles, generates titles/tags via OpenAI, encodes the video (CPU or GPU), and uploads it to AcFun and/or bilibili. It includes a Flask web UI, YouTube monitoring, CookieCloud sync, content‑moderation, and multi‑channel notification support, all configurable through a JSON file and protected by password/lockout features.

A DeepSeek Harness plugin that turns a single session into a coordinated multi-agent team with task scheduling, dependency management, and a live activity UI.

A self-hosted MCP server that gives ChatGPT secure access to your local files and terminal to read, edit, and run code directly in your projects.

A local-first, self-hosted workflow engine that turns existing scripts and containers into observable DAGs using a single binary and YAML configuration.

A standardized, open format for packaging specialized knowledge and workflows into portable folders that AI agents can load on demand to gain domain expertise.

A collection of reference implementations for the Model Context Protocol (MCP), providing examples of how to give LLMs secure access to tools and data sources.

A completion discipline for AI agents that uses runnable shell gates and evidence-backed ledgers to ensure substantial software work is fully completed and verified.

CyberStrikeAI is an open‑source Go‑based platform that lets security professionals drive over 100 pentesting tools through natural‑language prompts. An LLM‑powered “Eino” agent translates intent into reproducible, auditable workflows, stores evidence in SQLite, and provides a web UI for task, asset, and vulnerability management. It includes RBAC, human‑in‑the‑loop approvals, C2/WebShell capabilities (for authorized use), and plugins for Burp Suite and browsers. Deployment is a one‑command script; AI channel configuration is required before use. Licensed under Apache 2.0.

avoid‑ai‑writing is a portable skill for Claude, OpenClaw, Cursor, Hermes, and other AI‑agent platforms. It audits text for 74 AI‑writing patterns, can rewrite the prose (with optional voice profiles), detect only, or edit files in‑place, and returns a structured report. Installation is a simple clone or copy‑paste of the provided `dist/avoid‑ai‑writing.md` file, and the skill works across many agents via their standard skill/plugin mechanisms.

A shared workspace for team collaboration with coding agents, allowing teams to dispatch work and track agent progress across desktop, mobile, and CLI.

A Claude Code skill that rewrites dense English into Simplified Technical English (ASD-STE100) to prevent AI agents from misinterpreting tool descriptions, error messages, and inter-agent instructions.

Muesli is a native macOS app that provides on‑device speech‑to‑text dictation and meeting transcription. It uses Apple‑silicon‑optimized models (Parakeet, Whisper, Nemotron, etc.) for low‑latency transcription, with optional hosted ASR via OpenAI/OpenRouter. Features include hold‑to‑talk dictation, voice‑driven editing (Quill), VAD‑driven chunking, speaker diarization, AI‑generated meeting notes, iCloud text sync, Siri/Shortcuts integration, and a JSON‑first CLI for agent automation.

A terminal-based AI coding agent that understands codebases, edits files, and executes shell commands via a TUI or headless mode.

A self-deployable, multi-tenant knowledge agent platform that integrates RAG, knowledge graphs, and multi-agent orchestration for secure team collaboration.

A CLI and library for evaluating and red-teaming LLM applications to replace trial-and-error prompt engineering with data-driven testing and security scanning.