📦 bozhoudev/codex-orange-book

Mastering Codex with the Orange Book

A user scrolls through a detailed digital document that breaks down the entire process of installing and using the Codex platform from start to finish. This repository serves as a comprehensive guide that functions as an unofficial manual for those looking to master the technology through practical real world examples. By offering clear pathways from initial setup to hands on implementation, it demystifies complex workflows and provides a downloadable resource for developers. It is a valuable tool for anyone needing a structured reference to improve their technical proficiency. Grab this guide to streamline your learning and build projects more effectively.

🆔 @hackernewsgithubprojects

📦 jamesstringer90/appsandbox

Run Fully Sandboxed Virtual Machines on Windows and macOS

Build and run full desktop virtual machines like Windows, Ubuntu, and macOS using this high-performance, open-source tool. It offers an easy way to isolate your work by running programs or testing software inside clean, GPU-accelerated environments that remain completely separate from your host system. You can manage everything through a simple graphical interface or automate the entire VM lifecycle using a scriptable headless API and Python SDK. Whether you are testing drivers, running computer-use AI agents, or just need a secure sandbox for development, this project provides a flexible and powerful way to handle your virtualized tasks.

🆔 @hackernewsgithubprojects

📦 davideast/inbrowser-agent

Build AI Directly in the Browser

Developers can now run language models directly in the user's browser without needing a dedicated inference backend by utilizing the in-browser AI stack. This modular framework consists of four libraries that handle on-device model execution on the GPU, manage durable streaming jobs that survive page reloads, and provide a runtime for agents that can execute complex tool-based tasks. Whether you are building local AI tools or need to proxy cloud-based models while keeping API keys secure on the client, this project enables robust, persistent AI experiences that remain functional even when network connections drop or browser sessions are interrupted.

🆔 @hackernewsgithubprojects

📦 dmtrkovalenko/ffs

Search Your Disk Directly By Bypassing the Kernel

This command line tool performs file searches by bypassing the operating system kernel entirely and reading raw disk blocks directly. By avoiding the standard virtual file system and buffered read paths, it functions as a specialized file searcher that can scan detached volumes like disk images without mounting them. While it requires elevated permissions to access raw device nodes, this approach can outperform conventional tools on extremely large file sets by eliminating kernel overhead. It supports specific file system formats and utilizes multi-core processing to scan through massive data volumes, demonstrating that direct hardware interaction can sometimes offer significant performance advantages.

📰 https://news.ycombinator.com/item?id=48622433

🆔 @hackernewsgithubprojects

📦 juliensimon/canopy

Canopy: Parallel Claude Code Sessions for macOS

Canopy is a native macOS application that enables you to run multiple Claude Code sessions in parallel within a single interface. By leveraging git worktrees, it allows you to maintain independent coding contexts for different branches without the friction of stashing changes or juggling multiple terminal windows. The application includes a unified activity dashboard for monitoring token usage, a command palette for rapid navigation, and automated session management that persists your conversation state across restarts. Built with SwiftUI, it provides a high-performance alternative to managing disjointed AI workflows, offering a streamlined path to ship your projects faster while maintaining full control.

📰 https://news.ycombinator.com/item?id=48538315

🆔 @hackernewsgithubprojects

📦 kevinywu/hug

Generate Human Grasps from Stereo Images

Generate diverse human hand grasps for objects by simply clicking on an image captured from a stereo camera. This project provides an official implementation for Human Universal Grasping, a system trained on real-world data to predict precise grasp patterns in MANO form. It includes an interactive application that lets you visualize 3D hand poses and skeletons directly in your web browser. By processing RGB-D inputs, the model understands spatial geometry to create realistic grasping demonstrations. Explore this implementation to advance your work in hand-object interaction and robotics with a ready-to-use inference pipeline for your own captures.

🆔 @hackernewsgithubprojects

📦 stepfun-ai/gelab-zero

Build Your Own Local GUI Agent with GELab-Zero

Automate mobile tasks locally by deploying this open-source GUI agent solution that removes the need for cloud dependencies and complex infrastructure. Designed for both personal and enterprise use, it features a lightweight 4B model that runs on consumer hardware to maintain complete privacy. The repository includes a plug-and-play engineering pipeline to handle device management, task distribution, and interaction trajectories across various Android apps. By automating real-world tasks like shopping or navigation, this tool helps developers quickly test and deploy agent workflows. Download the project to regain control over your mobile automation tasks and experience fully local inference.

📰 https://news.ycombinator.com/item?id=48657446

🆔 @hackernewsgithubprojects

📦 xiangchenyin/holo-world

Holo-World: Controllable Video Generation from a Single Image

Holo-World is a unified video world model that enables precise camera, object, and weather control starting from just a single input image. Traditional models often struggle to manage these elements independently or rely on pre-existing source video structure, but this project introduces a specialized dataset called HoloStateData and a Unified Scene Adapter to resolve these limitations. By factorizing world preservation and environmental changes into distinct parameter subspaces, the model maintains scene structure while rendering specific weather effects and particle motion. This approach provides a robust framework for controllable video generation, offering a sophisticated tool for modern visual AI research.

🆔 @hackernewsgithubprojects

📦 shumaione/shumai

Shumai: The Open-Source Alternative for Creative Media Management

Shumai functions as a comprehensive, self-hosted platform designed to streamline creative workflows by providing tools for media storage, project collaboration, and automated asset management. It allows teams to securely store assets using local or S3-compatible cloud storage while enabling precise, frame-specific annotations and timestamped comments on video and image files. Beyond standard review features, the platform integrates an AI agent capable of semantic search, automatic metadata generation, and secure script execution within an isolated sandbox. With its distributed transcoding and granular role-based access controls, Shumai offers a flexible, open-source environment for managing complex production pipelines from start to finish.

📰 https://news.ycombinator.com/item?id=48642686

🆔 @hackernewsgithubprojects

📦 furiosa-ai/efficientrollout

Speed Up RL Training with EfficientRollout

This repository provides a system-aware framework designed to accelerate reinforcement learning rollout generation for large language models. Rollout latency is often a major bottleneck, but this project addresses it using self-speculative decoding, where a quantized version of the target model serves as a drafter. By coordinating a system-aware toggle policy and adapting draft lengths, the framework dynamically switches to speculative decoding only when it is computationally beneficial. This approach reduces overall latency by up to nineteen percent, helping developers optimize training performance without sacrificing model quality, and includes tools to calibrate these settings for specific hardware environments.

🆔 @hackernewsgithubprojects

📦 andreknieriem/headunit-revived

Turn Any Android Tablet Into an Android Auto Headunit

Headunit Revived is the specialized Android application that transforms your existing tablet or phone into a functional Android Auto receiver. By handling complex projection protocols, video decoding, and audio mixing, this project allows you to mirror your smartphone experience directly onto a secondary screen. It supports versatile connection methods, including wired USB configurations for direct data transfer and wireless helper modes for seamless network pairing. Whether you are building a custom car dashboard or repurposing older hardware, this tool provides the necessary connectivity and configuration settings to bring the full Android Auto interface to your device.

🆔 @hackernewsgithubprojects

📦 wshobson/agents

The Ultimate Multi-Harness Agentic Plugin Marketplace

The agents repository is the multi-harness plugin marketplace that synchronizes eighty-four specialized building blocks across five major developer tools from a single source of truth. It solves the fragmentation of agentic workflows by allowing you to maintain one set of plugins while natively supporting Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot. You gain access to nearly two hundred expert agents, over one hundred commands, and modular skills, all managed through an automated adapter framework that ensures native performance on every platform. Use this repository to standardize your automated development toolkit and ship agentic capabilities anywhere.

🆔 @hackernewsgithubprojects

📦 microsoft/webwright

Webwright: A Coding Agent Approach to Web Automation

Webwright is a lightweight browser agent framework that allows language models to solve complex, long-horizon web tasks by treating the browser as a tool to be programmed rather than a stateful session to manage. Instead of predicting individual clicks and keystrokes, the agent writes and executes Python scripts to interact with web elements, which makes the entire process repeatable, debuggable, and significantly more robust. By prioritizing the local workspace over the browser state, this tool delivers performance on web-based benchmarks. It can also function as a pluggable skill for existing developer agents, turning them into capable web browsers.

🆔 @hackernewsgithubprojects

📦 nv-tlabs/pid

Boost Image Resolution with PiD

PiD is the high-performance pixel decoder that replaces standard VAE models to generate high-resolution images in a single pass. By reformulating latent-to-pixel decoding as a conditional diffusion process, it intelligently unifies the tasks of decoding and upsampling. This approach allows users to transform low-resolution latent representations directly into detailed, super-resolved outputs for various popular diffusion backbones like Flux, SD3, and Stable Diffusion XL. Whether you are scaling up images to 4K or refining fine details with advanced distillation checkpoints, this tool provides a powerful, drop-in solution to elevate your generative image quality and streamline your creative workflow.

🆔 @hackernewsgithubprojects

📦 krispinwandel/vit-up

ViT-Up: Dense Feature Upsampling for Vision Transformers

ViT-Up provides an implicit feature upsampler that predicts backbone-aligned features at any continuous image coordinate for Vision Transformers. By leveraging self-supervised feature distillation across over one million images, this project enables downstream models to work directly with dense features from DINOv3 architectures. It solves the challenge of extracting fine-grained, high-resolution information from transformers, making it useful for tasks like dense prediction and semantic correspondence. The repository includes specialized toolkits for evaluation, probing, and even experimental video encoding, allowing you to project features into visual formats easily. This framework effectively bridges the gap between transformer backbones and detailed spatial analysis.

🆔 @hackernewsgithubprojects

📦 nilskikonjizdunava/fprm

Understanding Fixed-Point Reasoners in Looped Transformers

Enhance neural network reasoning by utilizing fixed-point convergence as a dynamic halting mechanism within looped Transformer architectures. This project provides an implementation of models that address signal propagation challenges common in deep recurrent systems by incorporating pre-norm layers and specialized residual scaling. By decoupling parameter counts from effective computational depth, this approach allows models to naturally adapt their compute usage based on the specific difficulty of a task. These optimizations eliminate the need for complex, manual halting strategies, providing a more stable and efficient way for systems to solve demanding reasoning benchmarks like Sudoku and maze navigation tasks.

🆔 @hackernewsgithubprojects

📦 aigeeksgroup/motionvla

MotionVLA: Generating Realistic Humanoid Motion with Dual-Stream AI

MotionVLA is an autoregressive model that generates realistic humanoid motion from scene images and text instructions by leveraging a specialized Dual-Stream Frequency-domain Tokenizer. By splitting motion data into a Base stream for pose semantics and a Phys stream for physical dynamics, the model effectively decouples low-frequency information from high-frequency velocity components, solving the common issue where shared codebooks cause geometric drift. This approach uses a Qwen3.5 backbone to arrange these streams into a unified, phase-aware sequence, significantly improving motion consistency and diversity. It is a powerful tool for researchers and developers looking to enhance animation and robotic humanoid control.

🆔 @hackernewsgithubprojects

📦 oweixx/gast

Geometry-Aware Style Transfer in 3D Gaussian Splatting

Geometry-aware style transfer allows for the artistic transformation of 3D Gaussian Splatting scenes while preserving their underlying spatial structure. This project introduces a batch pipeline that applies reference styles to pre-trained 3D Gaussian models, enabling the creation of stylized animations. By utilizing a specific training script to process point clouds and style images, users can generate depth-aware, visually consistent results across different scenes and artistic styles. This tool is particularly useful for researchers or developers looking to integrate creative aesthetics into 3D environments without compromising the integrity of the scene geometry. It offers a structured approach for rendering stylized video outputs.

🆔 @hackernewsgithubprojects

📦 furiosa-ai/async-opd

AsyncOPD: Speeding Up Large Language Model Training

AsyncOPD is the multi-process training pipeline that finally keeps your GPUs fully utilized during complex language model distillation and reinforcement learning. By decoupling rollout generation from learner updates, it allows simultaneous processing for on-policy distillation, GRPO, and supervised fine-tuning. The framework integrates vLLM for rollout, FSDP or Megatron for training, and NCCL for efficient weight synchronization, offering configurable staleness to balance throughput against training accuracy. With curated examples for various research workloads, this project provides a robust, asynchronous architecture that lets you scale large model training jobs efficiently. Adopt AsyncOPD to keep your expensive hardware productive today.

🆔 @hackernewsgithubprojects

📦 ai-builder-club/skills

Build Compounding AI Agents with this Plugin

Automate your codebase by implementing compounding agent loops that handle work independently. This plugin marketplace provides the necessary scaffolding to transform a standard repository into an agent-ready environment. You can deploy an isolated cloud development box for each agent, generate one-command local launchers for your stack, and build robust end-to-end test gates that verify features before shipping code. By utilizing shared file-based memory and specialized plugins, your agents can investigate issues, test their own changes, and log results to create a self-improving system. Leverage these tools to design smarter workflows that save you from constant manual prompting.

🆔 @hackernewsgithubprojects