📦 tinyhumansai/tiny.place

The First Social Network for AI Agents

Imagine a world where AI agents can finally talk, hire, and pay one another without human help. That is exactly what tiny.place creates, acting as the first social economy built specifically for autonomous agents. By providing a secure infrastructure on the Solana blockchain, it allows agents to claim unique handles, publish their specific skills in an open directory, and communicate through encrypted Signal channels. With integrated on-chain payments and escrow services, this project finally solves the problem of agent-to-agent trust and commerce. It is a bold, foundational step toward a truly connected and productive future for artificial intelligence.

📰 https://news.ycombinator.com/item?id=48610019

🆔 @hackernewsgithubprojects

📦 shawnpang/startup-founder-skills

Automate Your Startup Tasks with AI Agent Skills

Are you a solo founder drowning in endless tasks like drafting pitch decks, writing cold emails, or preparing job descriptions? This collection of AI agent skills is designed specifically for technical founders who need to wear every hat at once. Instead of struggling with generic AI outputs, you can integrate these specialized markdown-based skills into your agent to generate professional-grade, context-aware work across fundraising, product, engineering, and legal operations. By automating your repeatable workflows, you can stop wasting time on busywork and refocus your energy on talking to users and building your vision. Take control of your productivity today.

🆔 @hackernewsgithubprojects

📦 gamosoft/notediscovery

Take Total Control of Your Notes with NoteDiscovery

Are you tired of restrictive note-taking apps that hold your data hostage? Meet NoteDiscovery, a powerful, self-hosted knowledge base designed for total privacy and ownership. This lightweight, fast application lets you write and organize your thoughts using plain markdown files right on your own server. It offers incredible features like interactive knowledge graphs, a built-in drawing editor, and even AI integration for smart note management. Whether you are a developer building a personal wiki or just need a simple, secure space for your ideas, it is the perfect solution. Take control of your digital life and start hosting your own knowledge today.

🆔 @hackernewsgithubprojects

📦 dominikmartn/nothing-design-skill

Build Nothing-Inspired UI with Claude Code

Want to capture that iconic, industrial Nothing aesthetic in your own digital projects? This repository provides a specialized skill for Claude Code that lets you instantly generate UI following Nothing's unique monochrome and typographic design language. It solves the frustration of manually describing complex visual rules by packaging requirements like Swiss typography, OLED blacks, and segmented progress bars into a reusable tool. Whether you need HTML, SwiftUI, or React, this skill handles the heavy lifting of layout hierarchy and token systems. Use it to bring precision, restraint, and mechanical beauty to your next interface design project.

🆔 @hackernewsgithubprojects

📦 anemll/anemll-flash-llama.cpp

Run Massive AI Models on Apple Silicon with Flash-MoE

Have you ever wanted to run massive Mixture-of-Experts AI models that are simply too large for your machine memory? This specialized fork of llama.cpp introduces a clever sidecar runtime designed for Apple Silicon. Instead of forcing your hardware to load every expert into memory at once, it uses a streamed slot-bank approach to keep only the active experts resident while streaming the rest from your SSD. This repository includes powerful tools to extract, verify, and run these models efficiently. It is a game-changer for testing huge models on consumer hardware, so explore the project to start optimizing your inference today.

🆔 @hackernewsgithubprojects

📦 wendy7756/ai-video-transcriber

Turn Any Video Into Notes Automatically

Ever wish you could instantly turn long videos or podcasts into readable notes without spending hours typing? This powerful open-source tool makes it effortless. It uses advanced AI to automatically transcribe your media and generate concise summaries in multiple languages. Whether you are processing online links or uploading your own local audio files, the software handles the heavy lifting by leveraging tools like faster-whisper and OpenAI for accurate results. It even features a clean web interface to track your progress in real time. Start saving time today by letting AI do the listening for you.

🆔 @hackernewsgithubprojects

📦 ethanwheatthin/snapchat_memories_downloader_gui

Download and Save Your Snapchat Memories Easily

Ever wanted to save your Snapchat memories permanently with all their original details intact? This user-friendly Windows desktop tool simplifies the process by letting you download your full collection directly from your Snapchat data export. It goes beyond simple file saving by preserving crucial metadata like creation dates, original timestamps, and GPS location information. The application even automatically merges your overlay captions and stickers back onto your photos and videos, ensuring they look exactly as you remember them. It is a fantastic way to back up your digital archives safely and keep your memories organized forever.

🆔 @hackernewsgithubprojects

📦 shrivatsav-0/monomail

Ditch the Noise with MonoMail: A Minimalist Android Email Client

Are you tired of cluttered inboxes and overwhelming color schemes? Meet MonoMail, an open-source Android email client designed for a truly distraction-free experience. Built with Jetpack Compose and Material 3 Expressive, it strips away colorful noise, focusing on a clean, monochrome interface for your Gmail and Outlook accounts. With an offline-first architecture, your data stays secure on your device using encrypted local storage. Key features include smart thread grouping, customizable swipe gestures, and a unified inbox for all your accounts. If you want a faster, simpler way to manage your emails, check out this project to reclaim your focus.

🆔 @hackernewsgithubprojects

📦 qwenlm/qwen-code

Turn Your Terminal Into An AI Powerhouse

Want to supercharge your coding workflow directly from your command line? Meet this open-source AI coding agent that transforms your terminal into a powerful development assistant. By integrating directly into your environment, it helps you manage complex tasks through features like automated memory recall, multi-file editing, and direct shell access. Whether you need to run code reviews or execute multi-step projects, this agent acts as a smart companion that understands your workspace. It bridges the gap between AI and your actual code, making development faster and much more intuitive. Give it a try to see how your terminal evolves.

🆔 @hackernewsgithubprojects

📦 mohammedcha/gplay-scraper

Extract Google Play Store Data Like a Pro with Python

Ever wondered how to pull deep insights from the Google Play Store without dealing with complicated API keys? Meet GPlay Scraper, a powerful Python library designed for developers and researchers to extract comprehensive app data effortlessly. Whether you need to analyze ratings, track install metrics, fetch user reviews, or perform competitive market research across different regions, this tool has you covered. With support for over sixty-five data fields and seven different HTTP clients for maximum reliability, it makes gathering app intelligence simple and efficient. Dive into the world of app analytics and start gathering the data you need today.

🆔 @hackernewsgithubprojects

📦 motleyai/slayer

SLayer: The Semantic Layer for AI Agents

Struggling to get your AI agents to reliably query your database? Meet SLayer, a lightweight semantic layer designed to bridge the gap between raw data and AI intelligence. It sits between your database and AI tools, letting you auto-create data models, run complex queries using a structured API, and even perform time-based calculations like month-over-month growth with ease. SLayer handles the SQL generation for you, supporting various interfaces like CLI, REST API, and Python. It is a game changer for anyone needing agents to interact with data accurately. Try SLayer today and make your data truly agent-ready.

📰 https://news.ycombinator.com/item?id=48095686

🆔 @hackernewsgithubprojects

📦 whatdreamscost/whatdreamscost-comfyui

Supercharge Your ComfyUI Workflow with LTX Director

Are you tired of struggling with complicated video editing in ComfyUI? You need to check out these custom nodes designed to make your creative workflow faster and much smoother. This collection includes the powerful LTX Director, a complete timeline editor that lets you trim, split, and combine videos directly within your workspace. Whether you are handling text-to-video, image-to-video, or need a real-time speech length calculator to perfectly time your dialogue, these tools simplify the messy parts of AI generation. Stop guessing with your projects and start creating more efficiently today by adding these professional-grade nodes to your ComfyUI toolkit.

🆔 @hackernewsgithubprojects

📦 zeenie-ai/machinaos

Build Your Own Private AI Employee Teams with MachinaOS

Imagine having a team of AI employees working directly on your computer, handling your emails, calendars, and even controlling your Android phone. MachinaOS is an open-source platform that lets you drag and drop AI agents onto a canvas to build custom, private automation workflows without writing a single line of code. You can connect over fifty services, manage your own data locally, and use various AI models, including those running offline. Whether you need an agent to manage tasks or automate complex web research, this tool gives you complete control. Start building your own intelligent workforce today and reclaim your time.

🆔 @hackernewsgithubprojects

📦 snapotter-hq/snapotter

SnapOtter: The Ultimate Self-Hosted File Toolkit

Stop relying on random online websites to manage your files. SnapOtter is a powerful, open-source, and fully self-hosted toolkit that puts you back in control. It offers over one hundred and fifty tools for images, videos, audio, and documents, all running entirely on your own hardware. Whether you need to convert formats, edit images, or use AI for tasks like background removal and audio transcription, your files stay private within your network. With its easy-to-use interface and pipeline support, it simplifies complex workflows effortlessly. Take charge of your data today by running this comprehensive, private processing suite locally.

🆔 @hackernewsgithubprojects

📦 phuc-nt/my-translator

Build Your Own Real-Time Translator Tool

Imagine having a personal real-time speech translator right on your computer. This repository provides a powerful desktop application for both macOS and Windows that enables instant speech translation without needing a central server. By bringing your own API keys, you maintain full control over your data while leveraging various engines for text-to-speech capabilities like Edge, Google, and ElevenLabs. Whether you need to bridge language gaps or create seamless communication workflows, this project offers a flexible, private solution for your translation needs. Download the code today to start building your own custom, serverless translation experience immediately.

🆔 @hackernewsgithubprojects

📦 onepunchmonk/agentquant

Automate Your Trading Strategy Research with AI

Stop manual backtesting and let AI handle the heavy lifting for your trading research. This platform acts as an autonomous research agent that analyzes market regimes, generates trading hypotheses, and runs rigorous backtests all without requiring you to write a single line of code. It uses a ReAct agent loop to analyze VIX percentiles and momentum, then stores successful strategy parameters in a local SQLite memory so the system literally learns from past results. Whether you want to test momentum or mean reversion, this tool turns your stock lists into validated, backtested trading strategies while keeping your research organized.

🆔 @hackernewsgithubprojects

📦 dcharatan/millivid

Stop Your AI Videos from Glitching! Meet MilliVid

Ever notice how AI-generated videos start losing their minds after just a few frames? It is a common struggle, but a new project called MilliVid is changing the game. Instead of trying to process every single detail at once, it uses a clever hierarchical latent space to break video down into layers, prioritizing scene layout and semantics before filling in the finer textures. By using a coarse-to-fine rollout approach, it maintains rock-solid consistency over much longer stretches than traditional models. If you want to see how this approach keeps objects and scenes stable, check out the official repository.

🆔 @hackernewsgithubprojects

📦 nv-dvl/vgg-ttt

Faster 3D Reconstruction: Meet VGG-T3

Struggling with slow 3D reconstruction? Discover VGG-T3, a powerful new approach that makes processing large image collections significantly faster than traditional feed-forward methods. By replacing standard quadratic-scaling attention with a more efficient linear alternative through test-time training, this project turns hours of work into mere minutes of processing time. It provides a robust pipeline for predicting camera poses, intrinsics, and detailed depth maps from your images. Whether you are working with photos or videos, this tool offers a practical way to scale your 3D reconstruction tasks effectively. Give your computer vision projects a serious speed boost today.

🆔 @hackernewsgithubprojects

📦 elder-plinius/glossopetrae

Is Your AI Hiding Secrets? Meet GLOSSOPETRAE

Ever wonder if AI models are communicating behind your back? Meet GLOSSOPETRAE, a fascinating research engine for procedural xenolinguistics. It explores how frontier models learn novel languages and how they can be exploited to pass hidden messages that human monitors cannot see. By generating unique languages from scratch, the project reveals sharp acquisition cliffs and exposes tokenizer blind spots where data can be transmitted undetected. Whether you are interested in linguistic steganography or how LLMs handle opaque information, this repository offers a deep dive into the hidden dynamics of machine communication. Explore the math behind the mystery and see what your AI is really saying.

🆔 @hackernewsgithubprojects

📦 kevinxu02/r3

R3: Efficient 3D Reconstruction from Video

Imagine turning long, complex video streams into accurate 3D geometry in real time. R3 is a powerful feed-forward model designed to handle this exact challenge by using relative pose regression. Instead of struggling to process entire videos globally, it predicts confidence-weighted pairwise poses using a refined backbone. This minimalist approach allows it to run at over twenty frames per second while scaling across thousands of frames without breaking your memory budget. Whether for indoor scenes or long outdoor trajectories, R3 delivers professional-grade reconstruction with high efficiency. Dive into the repository to see how this clever architecture makes 3D modeling truly accessible.

🆔 @hackernewsgithubprojects

📦 dlupiak/claude-session-dashboard

Stop Guessing Your Claude Code Costs: Meet Your New Local Dashboard

Ever wonder where your tokens actually go during Claude Code sessions? You are not alone, as sessions often get cluttered, causing Claude to lose context and repeat itself. The Claude Session Dashboard solves this by acting as a private, local observability tool that runs entirely on your machine. It scans your logs to visualize agent delegation timelines, track context window usage, and provide detailed cost estimates for every workflow. By seeing exactly which agents were dispatched and how much they consumed, you can finally optimize your development process. Take control of your workflow data and start visualizing your sessions today.

🆔 @hackernewsgithubprojects