📦 hkuds/videoagent

Automate Video Creation with VideoAgent

Automate your video production with a comprehensive agentic framework designed for understanding, editing, and remaking video content. By leveraging intent analysis and a graph-powered planning system, this tool decomposes your natural language instructions into actionable workflows, enabling everything from intelligent summarization and Q&A to complex tasks like beat-synced edits and multi-modal creative remixes. It effectively coordinates diverse specialized models to execute your vision while providing adaptive self-evaluation to ensure high-quality outputs. Experience a more intuitive way to produce professional-standard media by letting an autonomous agent manage the technical orchestration of your creative ideas.

🆔 @hackernewsgithubprojects

📦 socktainer/socktainer

Run Docker Containers Natively on macOS with Socktainer

Connect your standard Docker tools directly to Apple's native containerization framework by using this lightweight Swift-based daemon. It exposes a Docker-compatible REST API, allowing you to use familiar commands like docker ps or docker images to manage your containers on macOS without the need for a heavy virtual machine. It automatically registers a Docker context, manages container lifecycles, and even syncs named volumes with configurable performance modes. Whether you are debugging locally or setting up a development environment, this project bridges the gap between Apple's hardware-accelerated container tech and the Docker ecosystem. Simplify your local macOS development workflow today.

📰 https://news.ycombinator.com/item?id=48640566

🆔 @hackernewsgithubprojects

📦 baidu/unlimited-ocr

Unlimited OCR: Advanced Long-Horizon Document Parsing

Unlimited OCR enables high-performance, one-shot long-horizon document parsing, allowing users to process extensive visual data efficiently. This project provides a sophisticated model designed to handle complex documents, supporting both single-image parsing and multi-page analysis for full PDFs. By utilizing advanced frameworks like Hugging Face Transformers and SGLang, the implementation offers versatile inference capabilities for various hardware setups. Users can easily convert PDFs into processed images or stream requests to an OpenAI-compatible API to extract information. This tool serves as a powerful solution for those needing to streamline and automate deep-learning-based document recognition at scale.

🆔 @hackernewsgithubprojects

📦 momenbasel/phosphor

Manage Your iPhone Like a Pro for Free

Take full control over your iPhone, iPad, or iPod touch with a free, open-source device manager built for macOS. This powerful tool lets you browse local backups, extract photos, and export messages into readable formats without relying on paid subscriptions or iCloud. You can perform full and incremental backups, install apps, and monitor battery health or device logs directly. It even offers advanced features like Time Machine-style restore and live process monitoring, all without proprietary lock-in. Whether you need to save your data or manage files, this tool provides a robust, transparent, and completely free alternative for your Apple devices.

🆔 @hackernewsgithubprojects

📦 geeksfino/finskills

Master Financial Analysis with AI: The FinSkills Repository

Analyze complex financial markets using this collection of specialized AI skills designed for US and China A-share markets. The repository provides thirty distinct analytical tools that allow you to conduct everything from value screening and portfolio health checks to forensic financial statement analysis. By leveraging a self-contained data toolkit, these skills pull live market information and macro indicators without needing extra API keys. You can generate professional investment documentation, identify sector rotation trends, or detect insider trading patterns through systematic, data-driven workflows. Use these structured methodologies to transform your investment research and make more informed financial decisions.

🆔 @hackernewsgithubprojects

📦 datanoisetv/ember-hackernews

Ember: A Native Hacker News Reader for Apple Devices

Ember is a native Hacker News reader built specifically for iPhone, iPad, and Mac using SwiftUI with no third-party dependencies. It prioritizes a calm, accessible reading experience by rendering threaded comments natively and offering features like offline caching, full-text search, and bookmarking. The app excels in personalization, with an onboarding flow that detects your system accessibility settings to pre-configure themes and reading preferences automatically. By avoiding tracking and relying solely on public APIs, it provides a fast, clean way to stay updated on technology news across your devices. Experience a refined, distraction-free way to explore Hacker News today.

📰 https://news.ycombinator.com/item?id=48610816

🆔 @hackernewsgithubprojects

📦 hkuds/nanobot

Run Your Own AI Agent with Nanobot

Deploy your own lightweight, open-source AI agent to manage workflows and automate tasks directly from your preferred chat apps. This project simplifies agent management by providing a readable core that supports everything from web searching and image generation to scheduled reminders and memory persistence. You can connect it to popular platforms like Discord, Slack, and Telegram, or use the bundled web interface to interact with your agent locally. By leveraging model routing and extensible skills, it allows you to build a personalized AI assistant that grows with your specific needs. Start customizing your own autonomous helper today.

🆔 @hackernewsgithubprojects

📦 pikpikcu/airecon

AIRecon: Autonomous Offline Penetration Testing

AIRecon provides a fully autonomous cybersecurity agent that conducts penetration testing and bug bounty reconnaissance without any reliance on cloud APIs or external keys. By combining a self-hosted Ollama large language model with a Kali Linux Docker sandbox, it creates a private environment where sensitive target data never leaves the local machine. The system follows a structured pipeline for reconnaissance, analysis, and exploitation, supported by a local knowledge base of over one million security records. This project is a useful tool for professionals who need an automated, private, and offline-capable security assessment workflow.

🆔 @hackernewsgithubprojects

📦 k-dense-ai/claude-scientific-writer

Scientific Writing Automation with AI

This project provides a comprehensive library of specialized skills designed to automate and streamline complex scientific documentation tasks. It equips researchers with structured templates and references for clinical reports, grant applications, and literature reviews while integrating advanced citation management and data synthesis tools. By organizing documentation workflows into modular skill sets—ranging from PDF generation to evidence-based medical decision support—it addresses the fragmentation often found in research reporting. This tool serves as a practical resource for maintaining academic rigor and formatting consistency across diverse publication venues, ultimately allowing investigators to focus on core analytical work.

🆔 @hackernewsgithubprojects

📦 snubroot/veo-3-prompting-guide

Master Google Veo 3 Prompting

Version 4.0 of this comprehensive guide provides expert techniques for professional AI video generation using Google Veo 3. This repository acts as a master resource for creating broadcast-quality content by detailing complex prompt structures for cinematography, lighting, and narrative flow. You will find specific syntax for critical camera positioning, movement quality control, and advanced audio integration to ensure perfect synchronization. It also features a library of templates for corporate, educational, and artistic projects, alongside troubleshooting solutions. By leveraging these battle-tested frameworks, creators can optimize their workflows for high-end results and master the nuances of AI video production.

🆔 @hackernewsgithubprojects

📦 forward-future/loop-library

Master Repeatable AI Workflows with Loop Library

Improve your AI agent efficiency by implementing structured, repeatable workflows known as loops. Unlike standard single-turn prompts, these loops give agents a clear way to learn from results, verify their progress, and follow specific criteria for when to stop. This project provides a public catalog of practical agent loops you can browse, along with an installable skill for popular AI agents that lets you discover, audit, adapt, or design new workflows through simple conversation. Use these playbooks to turn open-ended tasks into predictable, reliable outcomes. Explore the library to start building more capable, bounded, and effective agents today.

🆔 @hackernewsgithubprojects

📦 pguso/agents-from-scratch

Build AI Agents from Scratch without Frameworks

AI agents function as simple loops of observation, decision-making, and action rather than possessing true consciousness or hidden reasoning. This project provides a transparent, local-first guide to building agents from first principles using only a local language model and no external frameworks or cloud APIs. Through twelve structured lessons, you evolve a single agent class to handle tasks like structured JSON output, tool integration, long-term memory, and telemetry. By keeping every state transition and prompt explicit, the repository demystifies how these systems function. Explore the code to gain a purely mechanical, hands-on understanding of how modern agents operate.

🆔 @hackernewsgithubprojects

📦 ramakm/ai-hands-on

Master AI Engineering with Hands-On Projects

Learning AI is best achieved through building real systems from the ground up rather than just studying theory. This repository provides a comprehensive, structured path for aspiring AI engineers to master foundational skills including linear algebra, neural network architectures, and PyTorch implementation. You gain practical experience by constructing end-to-end applications, such as a cybersecurity focused retrieval-augmented generation pipeline and an optical character recognition service for invoice processing. By following these guided notebooks, you develop the technical intuition needed to bridge the gap between simple math concepts and modern large language models, ultimately empowering you to build your own intelligent systems.

🆔 @hackernewsgithubprojects

📦 rv64m/autotrade

Autonomous Trading Research with LLMs

This framework uses large language models to autonomously develop and refine cryptocurrency trading strategies through iterative backtesting. By reading a structured program file, an LLM agent creates and tests new strategy logic, evaluating performance against strict risk controls like drawdown limits and specific profit targets. The system logs every experiment, including rationale and metrics, into a central record to identify promising approaches. It automates the entire loop of generating code, running tests, and filtering results, providing a hands-off environment for strategy research. This setup offers a streamlined way to explore quantitative financial ideas through AI.

🆔 @hackernewsgithubprojects

📦 fedeveloper95/game-hub

Game Hub: The Ultimate Android Game Launcher

Game Hub is an Android application built with Kotlin and Jetpack Compose that organizes all your games into one dedicated space to replace cluttered app drawers. This launcher features a Material 3 Expressive user interface that scales perfectly across phones, foldables, and tablets. It offers advanced customization options, including flexible grid and horizontal viewing modes, plus the ability to rename games or swap icons. You can also monitor gameplay stats and keep the app current with an integrated update system. It provides a clean, centralized way to manage your library and personalize your mobile gaming experience.

🆔 @hackernewsgithubprojects

📦 iusztinpaul/squid

Automate Your Software Development Workflow with Squid

Squid is an opinionated plugin for Claude Code that transforms your development environment into an automated five-agent engineering team. By utilizing a set of markdown-based specifications and agent contracts, this tool manages the entire lifecycle of a feature, from initial planning to final pull request submission. It automates critical steps like task grooming, implementation, testing, and code review, requiring human intervention only for plan approval and final merging. By replacing rigid templates with dynamic agent-driven workflows, Squid helps solo developers and small teams consistently ship high-quality code while maintaining their specific project conventions effortlessly.

🆔 @hackernewsgithubprojects

📦 ropedia/s-agent

S-Agent: Advancing Spatial Intelligence

S-Agent-8B is a compact model representing a new spatial tool-use paradigm designed for complex multi-view image and video reasoning. Instead of relying on a single visual impression, this framework enables models to plan evidence requests and call specialized tools to accumulate scene memory. It solves difficult spatial intelligence tasks like metric measurement, object counting, and route reasoning by maintaining a persistent understanding across different viewpoints and frames. By distilling reasoning traces into a smaller model, it enhances performance on spatial benchmarks. This project showcases how structured tool-use leads to more reliable and grounded reasoning capabilities.

🆔 @hackernewsgithubprojects

📦 bohemiainteractive/cwr

Explore the Source Code of Arma: Cold War Assault

Build and study the foundation of a gaming classic by accessing the modernized C++20 source code for the engine behind Arma: Cold War Assault. This repository provides developers and enthusiasts with the core engine and game executables, originally released in 2001, now updated for contemporary cross-platform compilation on Windows and Linux using CMake and Clang. It offers a unique look at the technology lineage that shaped modern tactical shooters. While the game assets remain under a separate license, the engine code is available to explore, modify, and learn from as you dive into this piece of gaming history.

📰 https://news.ycombinator.com/item?id=48636753

🆔 @hackernewsgithubprojects

📦 jetastra/macagentbench

Benchmarking AI Agents on Real macOS Environments

MacAgentBench provides a comprehensive framework to evaluate how AI agents perform on actual macOS desktops. It features six hundred seventy-six distinct tasks across twenty-five applications, allowing developers to rigorously test agent capabilities using deterministic rule-based evaluation. By running tasks within isolated Docker containers, the project ensures consistent, reliable scoring across multiple checkpoints. It currently supports sixteen different AI models and integrates three primary agent frameworks to help track performance metrics. This repository serves as a critical resource for anyone looking to measure and improve the practical desktop automation skills of modern artificial intelligence.

🆔 @hackernewsgithubprojects

📦 dylanmurzello/zed-android-port

Run the Zed Code Editor on Android

Bring the powerful Zed code editor directly to your Android device by installing this native port as an APK. Designed to run on both tablets and Android desktop modes, this project leverages Vulkan for high-performance rendering through the GPUI framework. It enhances your mobile coding experience by integrating Termux for essential language server protocols and tooling, while offering remote SSH support for seamless cloud development. This initiative brings a desktop-class coding environment to mobile hardware, making it easier than ever to manage complex projects on the go. Dive into this mobile workflow and supercharge your coding productivity today.

📰 https://news.ycombinator.com/item?id=48175668

🆔 @hackernewsgithubprojects

📦 victorlavrenko/answer-engineering

Steering AI Behavior with Local Trajectory Editing

Large language models can be steered in real time by applying deterministic edits directly to their generation process. Answer Engineering provides a Python library for enforcing protocols, safety standards, and organizational rules by intervening the moment a model begins to deviate from a required path. Instead of relying on post-processing or full model retraining, this approach corrects the model trajectory mid-generation, ensuring reasoning steps remain within predefined boundaries. The repository includes both a runtime library for integrating these constraints and a research pipeline for reproducing benchmarks. By actively managing generation trajectories, developers can achieve more predictable and dependable model outcomes.

🆔 @hackernewsgithubprojects