📦 memohai/memoh

Build Your Own AI Agent Fleet with Memoh

Imagine giving every one of your AI agents its own personal computer, complete with an isolated desktop, filesystem, and long-term memory. That is exactly what this open-source platform makes possible. It allows you to run multiple agents simultaneously on a single machine or server, providing each one with a secure containerized workspace. From browsing the web to executing complex tasks and managing scheduled workflows, these agents operate like real, independent workers. Whether you are scaling a team or automating personal projects, this project simplifies the entire process. Start building your own intelligent fleet and take full control today.

🆔 @hackernewsgithubprojects

📦 leoyeai/openclaw-master-skills

Supercharge Your AI Agent with 1200+ OpenClaw Skills

Ever wish your AI assistant could do more than just chat? OpenClaw Master Skills is a massive, curated collection of over twelve hundred specialized skills designed to transform your autonomous AI agent into a true powerhouse. Instead of relying on generic prompts, these modular skills act like expert instructions, teaching your agent how to handle everything from complex web scraping and marketing analytics to automated coding and project management. Whether you need to streamline your daily workflow or integrate new tools like GitHub and advanced APIs, this repository provides the building blocks to customize your agent’s capabilities today.

🆔 @hackernewsgithubprojects

📦 rose22/openlumara

Build Your Own Private AI Agent with OpenLumara

Stop relying on heavy, black-box AI tools and take control with OpenLumara. This modular, Python-based framework is built from scratch to be local-first, lightweight, and incredibly fast. It strips AI agents down to the essentials, drastically reducing token usage and enhancing security. Whether you need a personal assistant for habit tracking, notes, or complex task management, you can enable only the modules you truly need. It supports interfaces like WebUI, CLI, Telegram, and Discord while working seamlessly with local models. Explore this efficient, private way to run AI agents and customize your own digital life today.

🆔 @hackernewsgithubprojects

📦 alinaqi/maggy

Turn Claude Code into an Autonomous Engineering Powerhouse

Stop wasting tokens on expensive AI models for simple tasks. Meet Maggy, an autonomous AI engineering command center that transforms Claude Code into a professional-grade development system. It solves the frustration of context loss and model inefficiency by using a smart thirteen-tier routing system to pick the cheapest capable model for your work. With built-in test enforcement, architectural decision tracking, and persistent session memory, Maggy manages your coding standards while you focus on building. It turns your terminal into a reliable, automated agent team that handles everything from linting to complex deployments. Level up your developer workflow and ship faster.

🆔 @hackernewsgithubprojects

📦 rednote-hilab/dots.tts

Meet dots.tts: The New State-of-the-Art in Continuous Speech Synthesis

Ever wanted a text-to-speech system that sounds truly natural and human? Say hello to dots.tts, a powerful open-source project featuring a two-billion-parameter architecture that redefines speech synthesis. Unlike systems that rely on discrete tokens, this end-to-end model uses a fully continuous autoregressive approach, combining a semantic encoder with a sophisticated flow-matching acoustic head. Whether you need stable voice cloning or expressive, high-quality audio, this system delivers state-of-the-art performance across multiple languages. It even supports low-latency streaming for real-time applications. If you are ready to experiment with cutting-edge AI voice technology, check out this repository and start building.

🆔 @hackernewsgithubprojects

📦 giammarco-ferranti/deja

Deja: Smarter Autosuggestions for Your Terminal

Tired of your terminal failing to predict what you actually want to type next? Meet Deja, a lightweight Go-based daemon that brings intelligent, predictive ghost-text autosuggestions to your Zsh shell. Unlike standard plugins, Deja uses advanced fuzzy matching, directory awareness, and command sequence prediction to learn your specific workflow habits. It runs locally with zero latency, storing your data in a secure SQLite database without ever needing an account or external sync. With features like an inline alternatives picker and custom fuzzy sensitivity modes, Deja makes your shell feel truly personalized. Install it today to experience a faster, smarter terminal workflow.

📰 https://news.ycombinator.com/item?id=48434430

🆔 @hackernewsgithubprojects

📦 sauravrao637/oproxy

Debug Network Traffic Like a Pro with oproxy

Stop guessing what your applications are sending over the wire and start seeing the real data. oproxy is a powerful, open-source proxy designed for developers to intercept, inspect, and modify HTTP, HTTPS, and SOCKS5 traffic with ease. Whether you need to debug API calls, replay requests, mock responses, or even throttle network speeds, this tool gives you complete control directly from your local machine or Docker container. With its built-in management interface and support for advanced inspection, it is the perfect companion for testing complex service integrations. Take charge of your network traffic today and streamline your entire debugging workflow.

📰 https://news.ycombinator.com/item?id=48431079

🆔 @hackernewsgithubprojects

📦 iblameandrew/open-deepthink

Stop Adding More Agents: Use Neural Reasoning Networks Instead

Are you tired of multi-agent systems that just brainstorm in a flat, repetitive circle? Meet the future of structured problem-solving. This repository introduces a Qualitative Neural Network where agents act like neurons in a layered, evolving graph. Instead of just adding more agents, it uses a process called Mirror Descent to rewrite agent prompts and refine their expertise through deep, iterative cycles. Whether you are performing complex knowledge distillation or deep conceptual brainstorming, this tool builds reusable reasoning artifacts that grow smarter with every epoch. Start evolving your agents today and move beyond simple parallel chatting for good.

🆔 @hackernewsgithubprojects

📦 iamzifei/show-me-the-money

Turn Your AI Into a 24/7 Automated Business

Ever wondered how to make your AI assistant do more than just write code? This repository provides a powerful skill suite that transforms your AI coding agent into a full-stack business operating system. It includes twenty-five specialized skills designed to help you discover market opportunities, validate demand, build products, and manage everything from marketing to financial reporting autonomously. By following structured, proven workflows, it acts as a persistent partner that remembers your decisions across every session. Whether you are an indie hacker or a technical founder, this tool helps you ship, operate, and scale your business without the overhead.

🆔 @hackernewsgithubprojects

📦 mysk-research/loupe

Is your iPhone leaking your privacy?

Ever wonder how advertisers track you across the internet without even knowing your name? It happens through device fingerprinting, where apps collect small, ordinary details about your iPhone to create a unique profile that follows you everywhere. Loupe is an open-source iOS app that pulls back the curtain on this hidden activity. It gives you a hands-on tour by reading the exact same public data any third-party app can access, from your screen settings to your installed apps. Download Loupe to see exactly what your device is quietly revealing and start taking control of your digital footprint today.

📰 https://news.ycombinator.com/item?id=48421327

🆔 @hackernewsgithubprojects

📦 forithmus/mr-rate

Understanding MR-RATE: AI for Medical Imaging

Have you ever wondered how artificial intelligence can help radiologists interpret complex brain and spine scans? Meet MR-RATE, a powerful foundation model designed specifically for medical imaging. This project provides a comprehensive framework that pairs 3D MRI volumes with radiology reports, using advanced contrastive pretraining to align visual data with medical text. It features an end-to-end pipeline that transforms raw scan files into standardized formats, enabling features like zero-shot pathology classification across dozens of conditions. By bridging the gap between imaging and clinical language, this work is helping to advance medical intelligence. Dive into the repository to explore the future of diagnostic AI.

🆔 @hackernewsgithubprojects

📦 mchughalex/skate3recomp

Play Skate 3 on PC with Native Recompilation

Ever wanted to play the classic Xbox 360 title Skate 3 natively on your modern computer? This impressive project provides an unofficial native recompilation of the game, allowing it to run directly on Windows, Linux, and even macOS. By utilizing a specialized software development kit, it transforms the original experience into a high-performance PC application that can push impressive framerates at 4K resolution. You simply provide your own legally obtained game files from an Xbox 360 disc to get started. It is a fantastic way to enjoy this legendary skating game with modern hardware and improved stability.

📰 https://news.ycombinator.com/item?id=48405166

🆔 @hackernewsgithubprojects

📦 abilityai/trinity

Trinity: Deep Agent Orchestration Platform

Are you tired of managing autonomous AI systems in isolation? Trinity is a powerful deep agent orchestration platform designed for sovereign infrastructure. It helps developers deploy, orchestrate, and govern complex autonomous AI agents through a centralized system. You can easily manage multi-agent collaboration, handle complex workflows with sequential or parallel tasks, and maintain granular control over agent permissions and scheduling. With integrated support for tools like Slack and Telegram, it simplifies the lifecycle management of your agents. Whether you are building research analysts or task-specific helpers, Trinity provides the essential framework to scale your AI operations effectively.

🆔 @hackernewsgithubprojects

📦 coreyhaines31/marketingskills

Supercharge Your AI Agents with Marketing Expertise

Want your AI agent to think like a seasoned CMO? This repository provides a comprehensive collection of marketing skills designed specifically for AI agents like Claude Code. It solves the problem of generic AI outputs by giving your agents specialized frameworks for conversion optimization, SEO, copywriting, and growth engineering. By using these markdown-based skill files, your agent gains access to professional templates and expert workflows for complex tasks like A/B testing or site architecture. Enhance your technical stack today and transform your AI into a powerful marketing partner that truly understands how to drive results.

🆔 @hackernewsgithubprojects

📦 rakile/neuralcompanion

Build Your Own Custom AI Companion on Windows

Ever wanted to create a fully personalized AI companion right on your own desktop? This project offers a powerful, addon-driven platform for Windows that brings together chat, speech, and visual avatars into one cohesive experience. Whether you want to roleplay with custom personas, use local models like Ollama, or drive interactive avatars through engines like MuseTalk and VSeeFace, this flexible system handles it all. It solves the complexity of managing disparate AI tools by providing a unified, configurable runtime that grows through community addons. Dive in to customize your digital partner today and take full control of your AI journey.

🆔 @hackernewsgithubprojects

📦 google-deepmind/representations4d

Understanding 4D Representations from Google DeepMind

Have you ever wondered how AI models truly track objects moving through space and time? The 4D Representations repository from Google DeepMind offers a powerful toolkit for exactly that. It explores advanced self-supervised learning for videos, helping models go beyond simple images to understand depth, camera motion, and object tracking. By leveraging transformer architectures and innovative techniques like off-the-grid token movement, these models effectively learn from dynamic scenes. Whether you are interested in recurrent masked autoencoders or aligning multi-sensory visual data, this project provides the essential tools and checkpoints to push the boundaries of modern computer vision.

🆔 @hackernewsgithubprojects

📦 advdebug/brovan

Brovan: The Ultimate Emulator for Reverse Engineering

Are you tired of invasive debugging tools that tip off the malware you are trying to analyze? Meet Brovan, a powerful user-mode x86_64 binary emulator built for deep security research. Instead of running binaries directly on your CPU, Brovan provides a safe, sandbox environment that lets you inspect execution flow, trace system calls, and even dump network traffic without the binary knowing it is being watched. Whether you are dealing with PE, ELF, or raw memory dumps, this tool gives you total control. Dive into your next reverse engineering project with the visibility you need to truly understand binary behavior.

📰 https://news.ycombinator.com/item?id=48155896

🆔 @hackernewsgithubprojects

📦 archie-judd/agent-sandbox.nix

Run AI Agents Safely with Declarative Sandboxing

Stop worrying about your AI agents running wild and accidentally deleting your files or exposing your secrets. This project provides a lightweight, declarative sandboxing solution for CLI-based AI agents on Linux and macOS using Nix. By leveraging bubblewrap and system-level security profiles, it enforces strict boundaries on what your agents can access, read, or write. You can explicitly declare allowed directories, restrict network traffic to specific domains via a proxy, and keep your home directory protected. It is the perfect way to confidently run powerful agents while keeping your local machine completely secure and under your control.

📰 https://news.ycombinator.com/item?id=47321775

🆔 @hackernewsgithubprojects

📦 bobjohnson24/comfyui-int8-fast

Boost Your ComfyUI Speed with INT8 Quantization

Want to supercharge your image generation speeds in ComfyUI? This repository offers a custom node that utilizes INT8 quantization to accelerate models like Flux2, Ideogram4, and Chroma. By reducing the precision of model weights and activations, it delivers a massive 1.5 to 2 times speed boost on NVIDIA 30-series GPUs and beyond. It supports powerful features like torch compile and LoRA integration, helping you generate high-quality outputs faster than ever before. Whether you are working with on-the-fly quantization or pre-quantized checkpoints, this tool is a game-changer for efficient AI workflows. Give your GPU the speed upgrade it deserves today.

🆔 @hackernewsgithubprojects

📦 somnusochi/vlm-autoyolo

Supercharge Your YOLO Workflow with AI Auto-Labeling

Stop wasting hours on manual object annotation and speed up your computer vision projects with this powerful AI-driven platform. It creates a seamless end-to-end pipeline that turns your images and videos into trained YOLO models with ease. By leveraging advanced tools like LocateAnything-3B for auto-labeling and SAM2 or SAM3 for precise segmentation, the system automates the heavy lifting of data preparation. You can refine masks, extract video keyframes, and trigger training with a single click. It even manages GPU memory for you across Mac and Windows. Experience a smarter, faster way to build and validate your custom detection models today.

🆔 @hackernewsgithubprojects