AI-powered visual reasoning tools for broadcast, live streaming, and ProAV professionals. The Visual Reasoning Playground provides 17 ready-to-use tools demonstrating real-world applications of Vision Language Models (VLMs) using Moondream. From PTZ camera auto-tracking to multimodal audio+video automation, the tools offer functionalities like scene description, object detection, gesture control, smart counting, scene analysis, zone monitoring, color matching, multimodal fusion, smart photography, PTZ tracking, tracking comparison, scoreboard extraction, scoreboard OCR, framing assistance, PTZ color tuning, multimodal studio automation, voice triggers, and OBS plugin integration. The tools are designed to streamline tasks in live streaming, broadcast automation, camera control, content creation workflows, security monitoring, and more.

bumpgen is a tool designed to automatically upgrade TypeScript / TSX dependencies and make necessary code changes to handle any breaking issues that may arise. It uses an abstract syntax tree to analyze code relationships, type definitions for external methods, and a plan graph DAG to execute changes in the correct order. The tool is currently limited to TypeScript and TSX but plans to support other strongly typed languages in the future. It aims to simplify the process of upgrading dependencies and handling code changes caused by updates.

Detour is an autonomous collision-avoidance system designed to run on-board satellites using NVIDIA's Nemotron LLM on the ASUS Ascent GX10. It utilizes a multi-agent LangGraph pipeline to detect debris threats, assess risk, plan maneuvers, validate safety constraints, and execute avoidance burns locally with zero ground-station latency. The system consists of key components such as Agent Pipeline, Physics Engine, Satellite Model, Tool Wrappers, API, Frontend, and Ascent GX10 Setup. The tool aims to provide fast and autonomous decision-making capabilities to prevent collisions in Low Earth Orbit (LEO) by leveraging edge AI technology.

Lanhu MCP Server is a powerful Model Context Protocol (MCP) server designed for the AI programming era, perfectly supporting the Lanhu design collaboration platform. It offers features like intelligent requirement analysis, team knowledge base, UI design support, and performance optimization. The server is suitable for Cursor + Lanhu, Windsurf + Lanhu, Claude Code + Lanhu, Trae + Lanhu, and Cline + Lanhu integrations. It aims to break the isolation of AI IDEs and enable all AI assistants to share knowledge and context.

Chronicle is a self-hostable AI system that captures audio/video data from OMI devices and other sources to generate memories, action items, and contextual insights about conversations and daily interactions. It includes a mobile app for OMI devices, backend services with AI features, a web dashboard for conversation and memory management, and optional services like speaker recognition and offline ASR. The project aims to provide a system that records personal spoken context and visual context to generate memories, action items, and enable home automation.

AIO Coding Hub is a local AI CLI unified gateway that allows requests from Claude Code, Codex, and Gemini CLI to go through a single entry point. It solves the pain points of configuring base URLs and API keys for each CLI, provides intelligent failover in case of upstream instability, offers full observability with trace tracking and usage statistics, enables easy switching of providers with a single toggle, and ensures security and privacy through local data storage and encrypted API keys. The tool features a unified gateway proxy supporting multiple CLI tools, intelligent routing and fault tolerance, observability with request tracing and usage statistics, channel validation with multi-dimensional templates, and security and privacy measures like local data storage and encrypted API keys.

Auto Paper Digest (APD) is a tool designed to automatically fetch cutting-edge AI research papers, download PDFs, generate video explanations, and publish them on platforms like HuggingFace, Douyin, and portal websites. It provides functionalities such as fetching papers from Hugging Face, downloading PDFs from arXiv, generating videos using NotebookLM, automatic publishing to HuggingFace Dataset, automatic publishing to Douyin, and hosting videos on a Gradio portal website. The tool also supports resuming interrupted tasks, persistent login states for Google and Douyin, and a structured workflow divided into three phases: Upload, Download, and Publish.

Zen-AI-Pentest is a professional AI-powered penetration testing framework designed for security professionals, bug bounty hunters, and enterprise security teams. It combines cutting-edge language models with 20+ integrated security tools, offering comprehensive security assessments. The framework is security-first with multiple safety controls, extensible with a plugin system, cloud-native for deployment on AWS, Azure, or GCP, and production-ready with CI/CD, monitoring, and support. It features autonomous AI agents, risk analysis, exploit validation, benchmarking, CI/CD integration, AI persona system, subdomain scanning, and multi-cloud & virtualization support.

Observers is a lightweight library for AI observability that provides support for various generative AI APIs and storage backends. It allows users to track interactions with AI models and sync observations to different storage systems. The library supports OpenAI, Hugging Face transformers, AISuite, Litellm, and Docling for document parsing and export. Users can configure different stores such as Hugging Face Datasets, DuckDB, Argilla, and OpenTelemetry to manage and query their observations. Observers is designed to enhance AI model monitoring and observability in a user-friendly manner.

Agentic ADK is an Agent application development framework launched by Alibaba International AI Business, based on Google-ADK and Ali-LangEngine. It is used for developing, constructing, evaluating, and deploying powerful, flexible, and controllable complex AI Agents. ADK aims to make Agent development simpler and more user-friendly, enabling developers to more easily build, deploy, and orchestrate various Agent applications ranging from simple tasks to complex collaborations.

Autopilot Notes is an open-source knowledge base for systematically learning autonomous driving technology. It covers basic theory, hardware, algorithms, tools, and practical engineering practices across 10+ chapters. The repository provides daily updates on industry trends, in-depth analysis of mainstream solutions like Tesla, Baidu Apollo, and Openpilot, and hands-on content including simulation, deployment, and optimization. Contributors are welcome to submit pull requests to improve the documentation.

PaiAgent is an enterprise-level AI workflow visualization orchestration platform that simplifies the combination and scheduling of AI capabilities. It allows developers and business users to quickly build complex AI processing flows through an intuitive drag-and-drop interface, without the need to write code, enabling collaboration of various large models.

Claude Emporium is a Roman-themed plugin marketplace for Claude Code, offering six plugins that wrap standalone MCP servers with automation hooks, commands, and skills. The plugins include Praetorian for context guard, Historian for session memory, Oracle for tool discovery, Gladiator for continuous learning, Vigil for file recovery, and Orator for prompt rhetoric. Each plugin self-configures on install, and the MCP servers handle the actual work. The plugins coordinate automatically when multiple are installed, enhancing behaviors and synergy. The tool is designed with zero overhead, no external API calls, no background processes, and no databases, making it efficient and lightweight for users.

KWeaver is an open-source ecosystem for building, deploying, and running decision intelligence AI applications. It adopts ontology as the core methodology for business knowledge networks, with DIP as the core platform, aiming to provide elastic, agile, and reliable enterprise-grade decision intelligence to further unleash productivity. The DIP platform includes key subsystems such as ADP, Decision Agent, DIP Studio, and AI Store.

AIO Homematic (hahomematic) is a lightweight Python 3 library for controlling and monitoring HomeMatic and HomematicIP devices, with support for third-party devices/gateways. It automatically creates entities for device parameters, offers custom entity classes for complex behavior, and includes features like caching paramsets for faster restarts. Designed to integrate with Home Assistant, it requires specific firmware versions for HomematicIP devices. The public API is defined in modules like central, client, model, exceptions, and const, with example usage provided. Useful links include changelog, data point definitions, troubleshooting, and developer resources for architecture, data flow, model extension, and Home Assistant lifecycle.

HUF is an AI-native engine designed to centralize intelligence and execution into a single engine, enabling AI to operate inside real business systems. It offers multi-provider AI connectivity, intelligent tools, knowledge grounding, event-driven execution, visual workflow builder, full auditability, and cost control. HUF can be used as AI infrastructure for products, internal intelligence platform, automation & orchestration engine, embedded AI layer for SaaS, and enterprise AI control plane. Core capabilities include agent system, knowledge management, trigger system, visual flow builder, and observability. The tech stack includes Frappe Framework, Python 3.10+, LiteLLM, SQLite FTS5, React 18, TypeScript, Tailwind CSS, and MariaDB.

This repository supports the YOLO series models and provides an AI auto-aiming tool based on YOLO-TensorRT for the game CrossFire. Users can refer to the provided link for compilation and running instructions. The tool includes functionalities for screenshot + inference, mouse movement, and smooth mouse movement. The next goal is to automatically set the optimal PID parameters on the local machine. Developers are welcome to contribute to the improvement of this tool.

DL3DV-10K is a large-scale dataset of real-world scene-level videos with annotations, covering diverse scenes with different levels of reflection, transparency, and lighting. It includes 10,510 multi-view scenes with 51.2 million frames at 4k resolution, and offers benchmark videos for novel view synthesis (NVS) methods. The dataset is designed to facilitate research in deep learning-based 3D vision and provides valuable insights for future research in NVS and 3D representation learning.

AliceVision is a photogrammetric computer vision framework which provides a 3D reconstruction pipeline. It is designed to process images from different viewpoints and create detailed 3D models of objects or scenes. The framework includes various algorithms for feature detection, matching, and structure from motion. AliceVision is suitable for researchers, developers, and enthusiasts interested in computer vision, photogrammetry, and 3D modeling. It can be used for applications such as creating 3D models of buildings, archaeological sites, or objects for virtual reality and augmented reality experiences.

AI-powered visual reasoning tools for broadcast, live streaming, and ProAV professionals. The Visual Reasoning Playground provides 17 ready-to-use tools demonstrating real-world applications of Vision Language Models (VLMs) using Moondream. From PTZ camera auto-tracking to multimodal audio+video automation, the tools offer functionalities like scene description, object detection, gesture control, smart counting, scene analysis, zone monitoring, color matching, multimodal fusion, smart photography, PTZ tracking, tracking comparison, scoreboard extraction, scoreboard OCR, framing assistance, PTZ color tuning, multimodal studio automation, voice triggers, and OBS plugin integration. The tools are designed to streamline tasks in live streaming, broadcast automation, camera control, content creation workflows, security monitoring, and more.

MME-RealWorld is a benchmark designed to address real-world applications with practical relevance, featuring 13,366 high-resolution images and 29,429 annotations across 43 tasks. It aims to provide substantial recognition challenges and overcome common barriers in existing Multimodal Large Language Model benchmarks, such as small data scale, restricted data quality, and insufficient task difficulty. The dataset offers advantages in data scale, data quality, task difficulty, and real-world utility compared to existing benchmarks. It also includes a Chinese version with additional images and QA pairs focused on Chinese scenarios.

VisionLLM is a series of large language models designed for vision-centric tasks. The latest version, VisionLLM v2, is a generalist multimodal model that supports hundreds of vision-language tasks, including visual understanding, perception, and generation.

AiTreasureBox is a versatile AI tool that provides a collection of pre-trained models and algorithms for various machine learning tasks. It simplifies the process of implementing AI solutions by offering ready-to-use components that can be easily integrated into projects. With AiTreasureBox, users can quickly prototype and deploy AI applications without the need for extensive knowledge in machine learning or deep learning. The tool covers a wide range of tasks such as image classification, text generation, sentiment analysis, object detection, and more. It is designed to be user-friendly and accessible to both beginners and experienced developers, making AI development more efficient and accessible to a wider audience.

VisionCamera is a powerful, high-performance Camera library for React Native. It features Photo and Video capture, QR/Barcode scanner, Customizable devices and multi-cameras ("fish-eye" zoom), Customizable resolutions and aspect-ratios (4k/8k images), Customizable FPS (30..240 FPS), Frame Processors (JS worklets to run facial recognition, AI object detection, realtime video chats, ...), Smooth zooming (Reanimated), Fast pause and resume, HDR & Night modes, Custom C++/GPU accelerated video pipeline (OpenGL).

AI-powered visual reasoning tools for broadcast, live streaming, and ProAV professionals. The Visual Reasoning Playground provides 17 ready-to-use tools demonstrating real-world applications of Vision Language Models (VLMs) using Moondream. From PTZ camera auto-tracking to multimodal audio+video automation, the tools offer functionalities like scene description, object detection, gesture control, smart counting, scene analysis, zone monitoring, color matching, multimodal fusion, smart photography, PTZ tracking, tracking comparison, scoreboard extraction, scoreboard OCR, framing assistance, PTZ color tuning, multimodal studio automation, voice triggers, and OBS plugin integration. The tools are designed to streamline tasks in live streaming, broadcast automation, camera control, content creation workflows, security monitoring, and more.

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

Daily Chinese ancient poetry and AI-generated images powered by Bing DALL-E-3. GitHub Action triggers the process automatically. Poetry is provided by Today's Poem API. The website is built with Astro.

EXIF Photo Blog is a full-stack photo blog application built with Next.js, Vercel, and Postgres. It features built-in authentication, photo upload with EXIF extraction, photo organization by tag, infinite scroll, light/dark mode, automatic OG image generation, a CMD-K menu with photo search, experimental support for AI-generated descriptions, and support for Fujifilm simulations. The application is easy to deploy to Vercel with just a few clicks and can be customized with a variety of environment variables.

SillyTavern is a user interface you can install on your computer (and Android phones) that allows you to interact with text generation AIs and chat/roleplay with characters you or the community create. SillyTavern is a fork of TavernAI 1.2.8 which is under more active development and has added many major features. At this point, they can be thought of as completely independent programs.

This project enables you to fetch liked tweets from Twitter (using Selenium), save it to JSON and Excel files, and perform initial data analysis and image captions. This is part of the initial steps for a larger personal project involving Large Language Models (LLMs).

Aila Desktop Application is a powerful tool that integrates multiple leading AI models into a single desktop application. It allows users to interact with various AI models simultaneously, providing diverse responses and insights to their inquiries. With its user-friendly interface and customizable features, Aila empowers users to engage with AI seamlessly and efficiently. Whether you're a researcher, student, or professional, Aila can enhance your AI interactions and streamline your workflow.

This project is an intelligent dialogue customer service tool based on a large model, which supports access to platforms such as WeChat, Qianniu, Bilibili, Douyin Enterprise, Douyin, Doudian, Weibo chat, Xiaohongshu professional account operation, Xiaohongshu, Zhihu, etc. You can choose GPT3.5/GPT4.0/ Lazy Treasure Box (more platforms will be supported in the future), which can process text, voice and pictures, and access external resources such as operating systems and the Internet through plug-ins, and support enterprise AI applications customized based on their own knowledge base.