📦 alekk89/llama-cpp-windows-manager

llama-cpp-windows-manager

The llama-cpp-windows-manager is the desktop console that finally makes running local AI models on Windows painless. Instead of wrestling with complex command-line arguments and manual environment setups, this slick desktop application coordinates everything for you right on your PC. It lets you download models directly from Hugging Face, manage different runtimes, and spin them up with customized launch profiles in a couple of clicks. The coolest part is how it integrates with both native Windows and WSL, giving you a smooth way to build, run, and monitor your local model APIs for coding workflows without any of the usual headache. Give it a spin and see how easy local AI...

🆔 @hackernewsgithubprojects

📦 christopherarter/superpowers-reasonix

Superpowers Reasonix

Superpowers-reasonix is the coding-agent plugin that finally brings rigorous, human-grade engineering discipline to your AI workspace. Instead of letting your AI model rush ahead to write messy code, this clever harness forces it to stop, plan, and think first. It ports a set of eleven essential software disciplines to the Reasonix platform, teaching the AI to write tests before implementing features, trace root causes before debugging, and run thorough verifications before claiming a task is done. It even includes a complete benchmarking suite to verify the model actually obeys these instructions. It is the ultimate way to turn a fast but sloppy AI assistant into a careful, reliable peer.

🆔 @hackernewsgithubprojects

📦 heymrun/heym

Heym AI Native Workflows

Build and run complex AI agents on a visual canvas without writing a single line of code. Heym changes how we automate tasks by putting language models at the very center of the execution rather than just plugging them in as an afterthought. You can visually wire together smart agents, web scrapers, and data tables to build workflows that actually talk to each other. The coolest part is that you can build these entire automated systems using just your voice or plain text prompts, and the visual editor automatically handles the wiring. It runs entirely on your own hardware, so your data stays private and secure.

🆔 @hackernewsgithubprojects

📦 hkuds/paper2slides

Paper2Slides

Turn dry research papers, PDFs, and Word documents into fully designed, professional presentation slides and academic posters with a single command. It uses an intelligent four-stage pipeline that parses your files, extracts key figures, plans a structured layout, and automatically generates high-quality visuals. The coolest part is how easily you can customize the aesthetic. Instead of wrestling with formatting, you can describe your design ideas in plain English, and the system renders customized slides to match your theme perfectly. It is a fantastic open-source tool for turning complex research into beautiful, ready-to-share presentations instantly.

🆔 @hackernewsgithubprojects

📦 showlab/paper2video

Paper2Video

You can now transform a dense LaTeX academic paper into a fully animated presentation video complete with voiceover, slides, active cursor tracking, and a speaking virtual presenter. This project makes complex research accessible by automating the entire pipeline. It takes your raw scientific paper, a portrait photo, and a quick audio clip to generate a polished lecture where a digital avatar explains your findings while pointing to key details on the screen. It takes the pain out of research promotion, giving scientists an easy way to share their hard work with the world. You simply feed it your draft, and you walk away with a ready-to-share video.

🆔 @hackernewsgithubprojects

📦 yashab-cyber/hackgpt

hackgpt

You can now run a full-scale enterprise security audit using a voice command on your phone. This is possible because hackgpt connects advanced artificial intelligence with a massive suite of network scanning tools to find and fix security weaknesses in large systems. Instead of forcing security teams to manually run dozens of separate programs, it orchestrates the entire process and automatically drafts professional compliance reports. The coolest part is that it can even take spoken instructions to spin up workers or trigger a test on the fly. It is like having a seasoned security analyst on standby, ready to protect your servers whenever you ask.

🆔 @hackernewsgithubprojects

📦 agentskills/agentskills

agentskills

agentskills is the open standard that finally gives AI assistants a clean, portable way to learn new jobs. Originally created by Anthropic, it lets you pack custom instructions, scripts, and templates into a simple folder with a markdown file. Instead of cluttering your AI's memory with a wall of instructions, it uses a clever system where the assistant only peeks at the skill's name and description at first. It only loads the full, heavy workflow instructions when it actually needs to execute that specific task. This keeps things incredibly fast and lightweight. It is the perfect way to build reusable, context-aware AI tools that actually work.

🆔 @hackernewsgithubprojects

📦 jackwener/wx-cli

wx-cli

Your local WeChat message history is actually fully readable on your computer without sending a single byte of data to the cloud. A brilliant Rust-based command-line tool called wx-cli bypasses typical database headaches by scanning your running WeChat process memory to extract the active SQLCipher key. From there, a background helper process securely decrypts and caches your databases locally. This lets you instantaneously search through group chats, look up contacts, extract encrypted images, or even feed your raw chat history directly into local AI models and agents. It keeps your data completely offline and lightning-fast.

🆔 @hackernewsgithubprojects

📦 microsoft/skills

skills

The skills project is the developer toolbox that feeds structured knowledge directly to coding assistants to make them write better code. While standard AI assistants struggle with outdated library versions and API changes, this system organizes code blueprints, SDK examples, and architectural patterns into bite-sized units of knowledge. It uses the Model Context Protocol to instantly ground AI agents in real, up-to-date SDK details across languages like Python, Java, and Rust. Instead of guessing how to implement a complex cloud integration, your coding assistant reads these curated blueprints to construct correct solutions. It is a smart way to keep your autonomous agents accurate and production-ready.

🆔 @hackernewsgithubprojects

📦 modelcontextprotocol/ext-apps

ext-apps

ext-apps is the model context protocol extension that finally brings interactive user interfaces to your favorite AI chatbots. While traditional AI assistant tools are stuck outputting basic text and raw data, this clever SDK lets your servers serve up full, interactive web views like charts, design canvases, and live dashboards directly inside the chat window. It works by standardizing how a chat client renders sandboxed web apps in real time, letting the bot and the UI talk back and forth seamlessly. You can even have an AI coding agent build these interfaces for you from scratch using the included agent skills. It is the perfect way to turn static text...

🆔 @hackernewsgithubprojects

📦 ark0n/codeman

Codeman

Control your AI coding assistants from absolutely anywhere with a mobile-optimized dashboard. Codeman takes command-line coding agents like Claude Code or OpenCode and wraps them in a web interface designed for remote work. The standout feature is a local echo overlay that completely eliminates connection lag, making typing feel instant even over a cellular connection. It also features a hands-off controller that keeps agents running unattended for hours, automatically handling context resets and subscription limits. You can easily manage multiple sessions, watch background subagents spawn in real-time, and log in securely from your phone using single-use QR codes.

🆔 @hackernewsgithubprojects

📦 andimarafioti/faster-qwen3-tts

faster-qwen3-tts

The text-to-speech engine that finally makes voice generation run at true warp speed, faster-qwen3-tts is a smart optimization project that slashes latency for Qwen3 speech models. Normally, generating realistic speech requires launching hundreds of tiny, separate computer instructions, which wastes precious time while your processor waits. This project solves that slowdown by bundling all those separate steps into a single, pre-planned execution path on your graphics card. It is incredibly useful because it drops the time to your first spoken word to less than a fifth of a second on standard hardware, letting you stream high-quality, cloned voices in real time without annoying lag. Try it out to experience instant...

🆔 @hackernewsgithubprojects

📦 moltlaunch/cashclaw

CashClaw

Hire yourself a digital worker that never sleeps and actually gets smarter over time. CashClaw connects to onchain networks to hunt for tasks, price them, and execute the work using an AI model. It does not just build deliverables and collect payouts—it actually studies between tasks, analyzing its own ratings and simulated scenarios to construct its own long-term memory. Over time, it retrieves those exact lessons to refine its future work. It is completely open-source, features a slick local dashboard, and lets you automate real-world work on your own terms. Set up your node and watch your custom agent start earning today.

🆔 @hackernewsgithubprojects

📦 autonomous-ai/autonomous-computer

autonomous-computer

autonomous-computer is the open-source hardware blueprint that lets you build a powerful, self-contained AI workstation right in your own home. Instead of renting cloud access from giant tech companies who can cut you off at any moment, this project gives you the complete plans to build and run your own physical machine. You get the exact lists of parts, wiring guides, and even files to 3D print the housing. By putting your own graphics cards in a custom frame, you can run massive open-source models completely offline, keeping your private data entirely under your own roof.

🆔 @hackernewsgithubprojects

📦 neuralinverse/neuralinverse

Neural Inverse

Modernize dusty legacy codebases and program physical microcontrollers using a specialized, AI-native development environment designed for real-world engineering challenges. While many AI coders focus on simple web apps, neuralinverse tackles complex, safety-critical systems by combining familiar editing tools with autonomous agents. Developers can seamlessly translate ancient source code into modern languages or deploy firmware with built-in compliance checks across hundreds of hardware variants. The platform supports over twenty artificial intelligence providers, letting you run models locally or in the cloud. It is a highly practical, open-source alternative for programmers dealing with hardware and legacy migrations.

📰 https://news.ycombinator.com/item?id=48760541

🆔 @hackernewsgithubprojects

📦 inception3d/motion324

motion324

Turn a simple flat video into a fully animated 3D character in just a few seconds. If you have a static 3D model, you can instantly transfer the movement from any video directly onto it, or you can feed the tool a single video file and let it build both the 3D model and its movement from scratch. It works by reconstructing precise 3D motion from standard camera footage, which means you can generate complex animations without tedious manual rigging or expensive motion capture gear. It is a massive timesaver for indie developers or hobbyists who want to bring virtual characters to life instantly.

🆔 @hackernewsgithubprojects

📦 vidanov/aws-architecture-diagram-skill

aws-architecture-diagram-skill

Your AI assistant can now draw production-quality AWS architecture diagrams that actually work in draw.io. This clever project, called aws-architecture-diagram-skill, solves a massive pain point by teaching ChatGPT, Claude, and internal AI agents exactly how to generate flawless, editable diagram files. Usually, AI-generated diagrams turn into a mess of broken icons and chaotic lines. This skill provides a verified catalog of over two hundred real icons, enforcing strict rules like a clean left-to-right flow and perfect color-coded styling. You get fully customizable, version-controlled diagrams directly from your chat prompts without installing heavy servers.

📰 https://news.ycombinator.com/item?id=48308848

🆔 @hackernewsgithubprojects

📦 kasothaphie/genrecon

genrecon

genrecon is the 3D scene reconstruction pipeline that finally lets you generate highly detailed, fully textured indoor spaces from standard smartphone videos. Instead of struggling to reconstruct large, complex indoor environments all at once, this clever system breaks the entire space down into small, overlapping chunks and processes them individually. By adapting a powerful object-level generative model to work across these localized pieces, it pieces the entire scene back together with consistent geometry and realistic materials. This approach completely bypasses the messy errors of traditional scanning, producing beautiful, editable 3D meshes that outperform standard methods by sixteen percent.

🆔 @hackernewsgithubprojects

📦 plutonhq/pluton

Pluton

Pluton is the open-source backup manager that brings a clean, intuitive web interface to your self-hosted storage. Instead of wrestling with complex command line interfaces, you get a beautiful dashboard to orchestrate automated, incremental backups. It combines the rock-solid security of Restic with the massive cloud storage reach of Rclone, meaning you can easily encrypt, compress, and replicate your data across over seventy different cloud destinations. You can easily schedule jobs, track progress in real time, and browse snapshots with a few simple clicks. It makes secure, professional-grade backups completely accessible to anyone self-hosting their data.

🆔 @hackernewsgithubprojects

📦 martin98-afk/canvasmind

CanvasMind

Build and run complex software systems visually without writing endless glue code. This tool lets you drag, drop, and connect pre-built nodes to orchestrate everything from simple file tasks to advanced machine learning pipelines. What makes it incredibly cool is its ability to bundle your visual creation into a standalone, runnable package with just a single click. Instead of getting stuck in a visual editor forever, you can instantly export your workflows as clean, production-ready Python projects. It gives curious builders an elegant way to prototype rapidly and hand off fully functional code directly to deployment.

🆔 @hackernewsgithubprojects