📦 newjhez01/gdns

Build Your Own DNS Server with Go

Want to take control of your network privacy? This project is a custom DNS resolver built from scratch in Go, designed to run on a Raspberry Pi. It acts like your own personal traffic controller by parsing DNS requests at the bit level and blocking ads and trackers by routing them to NXDOMAIN. It uses a high-performance SQLite database for blocklists and Redis for lightning-fast response caching. By handling requests locally before forwarding legitimate traffic to Cloudflare, it gives you a powerful, self-hosted alternative to standard network filters. Try it out to see how deep network protocols really go.

🆔 @hackernewsgithubprojects

📦 tencent/hpc-ops

Supercharge Your AI Models with HPC-Ops

Are your large language models struggling with slow inference times? Meet the high-performance operator library from the Tencent Hunyuan AI Infra team. This project provides production-grade kernels specifically optimized for modern NVIDIA hardware to accelerate critical tasks like attention, MoE, and GEMM computations. By fusing complex operations—like combining AllReduce with RMSNorm or streamlining token sampling—it significantly reduces bottlenecks that typically drag down performance. Whether you need precision-sensitive computations or massive throughput for your AI workloads, these tools are built to help. Explore these advanced kernels to unlock faster, more efficient inference and take your deployments to the next level.

🆔 @hackernewsgithubprojects

📦 rawfilejson/awesome-osint-arsenal

Supercharge Your Recon with Awesome OSINT Arsenal

Are you struggling to manage dozens of scattered security tools? The Awesome OSINT Arsenal is a massive, curated collection of over seven hundred fifty powerful utilities designed to streamline your reconnaissance and security workflows. Whether you are performing network scans, diving into digital forensics, or conducting red team operations, this toolkit simplifies everything with one-command installers for major Linux distributions and even Termux. It effectively solves the problem of tedious manual setups by organizing tools into fifty specific categories, from web application testing to hardware analysis. Grab this ultimate library today and take your security research to the next level.

🆔 @hackernewsgithubprojects

📦 osu-nlp-group/quest

Meet QUEST: Powerful New Open-Source Deep Research Agents

Ever wish you had an AI that could handle complex, long-form research tasks just like a human expert? Meet QUEST, a new family of open-source models ranging from two to thirty-five billion parameters. These models are specifically designed to tackle deep research by mastering fact seeking, citation grounding, and detailed report synthesis. Whether you need to automate research workflows or improve your data generation pipelines, QUEST provides the necessary tools and model checkpoints to get the job done effectively. Dive into this repository to explore the future of automated research and see how these agents can transform your workflows today.

🆔 @hackernewsgithubprojects

📦 haru-lcy/voidpadding

Stop Model Failures with VoidPadding

Have you ever noticed your language model getting stuck or acting weird with padding tokens during complex tasks? Masked diffusion language models often struggle when empty padding gets confused with semantic endings, leading to annoying errors where the model overproduces tokens. VoidPadding is a clever new approach that solves this by introducing a dedicated void signal specifically for padding, while leaving the conventional ending token to handle true semantic termination. By clearly separating these two roles, this method improves model robustness, prevents overflow errors, and even enables smarter adaptive canvas expansion. It is a powerful way to make your model decoding more efficient.

🆔 @hackernewsgithubprojects

📦 opendfm/xcientist

Automate Your Research with AI Scientists

Ever wonder if AI could handle the heavy lifting of scientific research? Meet Xcientist, a powerful multi-agent workflow designed to turn any research topic into a complete scientific journey. This system automates everything from gathering paper surveys and generating structured research ideas to executing actual code experiments and drafting technical blog articles. By using specialized agents for tasks like MCTS-based ideation and workspace orchestration, Xcientist streamlines complex research cycles into a single, cohesive pipeline. Whether you are validating new theories or conducting experiments, this framework provides the harness you need to accelerate discovery. Try it out to supercharge your research workflow.

🆔 @hackernewsgithubprojects

📦 dregen-yor/recloop

Are AI Recommenders Creating Filter Bubbles?

Ever wonder if your personalized feed is trapping you in an information cocoon? The RecLoop project investigates this by using a clever closed-loop simulation where LLM-powered user agents interact with both traditional and generative recommender systems. By running periodic model retraining over fifteen feedback cycles, it helps researchers understand how different recommendation paradigms shape content diversity over time. This repository provides the essential framework for setting up these simulations, allowing you to compare how modern generative models stack up against classic algorithms. It is a vital tool for anyone studying the long-term impact of AI on our digital habits.

🆔 @hackernewsgithubprojects

📦 dataexpert-io/ai-engineer-handbook

Master AI Engineering: The Ultimate Resource Handbook

Are you struggling to keep pace with the rapidly evolving world of AI? The AI Engineering Handbook is a comprehensive, open-source treasure trove designed to help you master the field from the ground up. This repository eliminates information overload by curating over five hundred essential resources, including high-quality books, active communities, and expert-led newsletters. Whether you are diving into prompt engineering, exploring large language models, or preparing for technical interviews, this handbook provides the structured roadmap you need. Start your journey today, tap into these expert resources, and gain the clarity required to build the next generation of AI-driven applications.

🆔 @hackernewsgithubprojects

📦 mims-harvard/autoscientists

AI Agents Working Together to Solve Complex Science Problems

Imagine a team of AI scientists that never sleep and constantly learn from each other to solve complex research challenges. This project introduces a decentralized system where AI agents self-organize into specialized teams to tackle long-running computational experiments. Instead of working alone, these agents critique each other's proposals and share both successes and failures to accelerate discovery. It has already achieved impressive results across biomedical benchmarks, protein engineering, and training optimizations. By automating the coordination of these digital researchers, this system pushes the boundaries of autonomous scientific exploration and discovery. Check it out to see how decentralized AI is changing science.

🆔 @hackernewsgithubprojects

📦 shawn0728/opensearch-vl

Build Your Own Multimodal Search Agent with OpenSearch-VL

Ever wondered how to build your own advanced AI research agent that can see, search, and reason? Meet OpenSearch-VL, a completely open-source toolkit designed to train multimodal agents that operate in a closed loop. Unlike standard models, these agents inspect images, use web search tools, and gather evidence before answering. This repository provides the full recipe, including specialized training datasets and a fatal-aware reinforcement learning algorithm to handle tool errors effectively. Whether you are interested in agentic supervised fine-tuning or scaling up with deep reinforcement learning, this project gives you the complete blueprint to create your own powerful search agent.

🆔 @hackernewsgithubprojects

📦 andyhuo520/aetherviz-master

Turn Any Subject Into an Interactive 3D Lesson

Ever wish complex topics were easier to visualize? AetherViz Master is an innovative educational tool that transforms abstract concepts into immersive 3D interactive webpages. Whether you are studying physics, chemistry, or mathematics, this project uses Three.js and SVG rendering to create dynamic visual simulations based on your input. It automatically identifies your chosen subject and generates high-quality, responsive 3D environments with embedded UI controls for a hands-on learning experience. By bridging the gap between static text and interactive models, it makes learning intuitive and engaging. Dive into the repository to start building your own custom visualizations today.

🆔 @hackernewsgithubprojects

📦 strands-agents/shell

Give Your AI Agent a Shell Without Risking Your Machine

Want to give your AI agents the power of a shell without compromising your system security? Meet Strands Shell, a lightning-fast, Bourne-compatible shell built to run entirely in-process. It solves the risk of giving agents machine access by providing an isolated, sandbox-ready environment. With over 50 built-in commands like grep, curl, and jq, it executes instantly without the overhead of containers or system calls. You define exactly what files and URLs your agent can reach, ensuring total control and security. Start sandboxing your agent loops today and keep your machine keys safely tucked away for complete peace of mind.

📰 https://news.ycombinator.com/item?id=48572485

🆔 @hackernewsgithubprojects

📦 yongaifadian1/nvmos

Is Your AI Speech Sounding Natural? Meet NVMOS

Have you ever wondered if your synthetic speech sounds truly human? Evaluating non-verbal vocalizations like coughs, laughs, or sighs is notoriously difficult for standard AI. That is where NVMOS comes in. It provides an automated way to predict the perceptual quality of these specific vocal events in your audio files. By using advanced cross-attention modeling, this tool assigns a quality score from zero to five, helping you identify if your AI-generated sounds feel natural or robotic. It is a powerful way to refine your audio projects, ensuring your synthetic voices sound more lifelike and authentic than ever before.

🆔 @hackernewsgithubprojects

📦 knostic/openant

Automate Security with OpenAnt

Tired of dealing with endless false positives in your security scans? Meet OpenAnt, an open source, LLM-based vulnerability discovery tool designed to help developers find and verify real security flaws. By using a clever two-stage pipeline, it first detects potential issues and then launches automated attacks to confirm which vulnerabilities are actually exploitable. This approach helps you focus on what truly matters by separating real risks from noise. Whether you use Go, Python, JavaScript, or C, OpenAnt provides a configurable way to secure your code. Take control of your security pipeline and start proactively defending your projects today.

🆔 @hackernewsgithubprojects

📦 zlab-princeton/ceobench-src

Can AI Agents Run a Startup for 500 Days?

Ever wonder if an AI can master the long game of running a business? CEO-Bench is a challenging simulation that puts AI agents in the driver seat of a startup for 500 days. The agents must navigate a complex, evolving market, manage company resources, and handle competitors to maximize their ending cash. It provides a realistic environment where agents use a programmable interface to make strategic decisions, providing a unique look at how AI handles long-term planning and business logic. It is a fascinating test of true agent autonomy and strategy. See if your favorite model can survive the business grind.

🆔 @hackernewsgithubprojects

📦 zleap-ai/sag-benchmark

Reproduce SAG Benchmark Results with Ease

Want to see how your retrieval systems truly stack up against the latest paper benchmarks? This repository provides the official reproduction code for the SAG benchmark, allowing you to replicate performance scores across datasets like HotpotQA and MuSiQue. It streamlines the evaluation process by providing tools for dataset uploads, index initialization, and running multi-strategy searches, including atomic entity-first expansion. By using containerized services for data management and tracking, it ensures your testing remains consistent and professional. Check out this project to validate your own RAG performance and push your retrieval accuracy to the next level.

🆔 @hackernewsgithubprojects

📦 epicgames/lore

Lore: The Next-Gen Version Control System Explained

Ever wonder how to handle massive projects that combine complex code with huge binary assets without slowing down? Meet Lore, an open-source, next-generation revision control system built by Epic Games. Designed for incredible scale, Lore uses a centralized, content-addressed architecture powered by Merkle trees and immutable revision chains. It optimizes performance for large teams by utilizing chunked storage and on-demand data hydration, meaning you only download what you actually need. Whether you are a developer or an artist, Lore provides a reliable, high-performance source of truth for your creative work. Dive into this growing ecosystem and start versioning smarter.

🆔 @hackernewsgithubprojects

📦 nashsu/llm_wiki

Build Your Own Automated Personal Knowledge Wiki

Imagine having a personal knowledge base that builds and organizes itself automatically. This desktop application turns your documents into an interlinked wiki, moving beyond basic search by using intelligent agents to process your files into a persistent, searchable network. It features a powerful knowledge graph, automated community detection, and two-step reasoning to ensure your information stays connected and current. Whether you are managing research or personal notes, it keeps your data structured without the constant manual effort of traditional systems. Start building a smarter digital brain today and watch your collective knowledge grow as your library expands.

🆔 @hackernewsgithubprojects

📦 thetom/llama-cpp-turboquant

Supercharge Your LLM Inference with TurboQuant

Want to run large language models more efficiently on your own hardware? This repository is a specialized fork of the popular engine for C and C plus plus, designed to push the boundaries of inference performance. It integrates an advanced codec stack that uses clever techniques like rotated polar quantization to significantly compress your KV cache and model weights. Whether you are using Apple Silicon, NVIDIA, or AMD hardware, this tool helps you reclaim VRAM and speed up your workflow. It is a powerful way to handle long contexts and complex models without sacrificing the quality of your output.

🆔 @hackernewsgithubprojects

📦 botchetdig/workout-gate

Stop Procrastinating: The AI Coding Tool That Forces You To Work Out

Are you tired of sitting at your desk for hours while your AI does all the heavy lifting? Meet Workout Gate, a clever tool for Claude Code that literally blocks your prompts until you complete a physical challenge. Using your webcam and pose detection technology, it forces you to perform push-ups or squats before your code will execute. You cannot simply skip it, as session-persistent debt ensures your reps are tracked until you finish. With customizable modes, streak tracking, and a built-in dashboard, it is time to make sure that you are working just as hard as your AI.

📰 https://news.ycombinator.com/item?id=48558998

🆔 @hackernewsgithubprojects