📦 robiot/fable-os

The Operating System Controlled by Natural Language

The operating system fable-os replaces every command line tool with a natural language interface, meaning you never type ls or cat to interact with the machine. Instead of a traditional shell, the kernel listens to plain English sentences and executes real system actions through a structured trace of brackets that proves exactly what happened. You can ask it to open a calculator, and it actually builds a window and clicks the keys for you. It even writes its own device drivers for unknown hardware and compiles new C programs on the fly.

📰 https://news.ycombinator.com/item?id=49146832

🆔 @hackernewsgithubprojects

📦 shopdevx/adeptlydev

Adeptly: Plan-First AI Coding Companion

Adeptly is the plan-first companion for Claude Code that finally turns AI suggestions into executable team workflows. Instead of just guessing code, it drafts a full technical plan in your project’s documentation, then automatically configures subagents, skills, and security hooks to match exactly what needs building. It even lets your whole team approve plans together using git, so everyone sees the same strategy before a single line of code changes. The coolest part is the Crew mode: you can hit run and watch a pipeline of roles—Architect, Builder, Medic, Reviewer, and Pilot—execute that plan step by step in your local repo. Best of all, it runs entirely on your machine.

🆔 @hackernewsgithubprojects

📦 sqliteai/sqlite-memory

SQLite Memory: Offline AI Agent Memory

SQLite Memory turns a single database file into a searchable memory bank for artificial intelligence bots. You feed it markdown notes, and it breaks them into bite-sized chunks that capture the actual meaning rather than just keywords. It runs entirely on your laptop using a local model, so your private data never touches the internet. Multiple bots can work separately offline and automatically merge their notes when they reconnect, resolving conflicts without any central server. It is the simplest way to give software long-term context without managing complex cloud infrastructure.

📰 https://news.ycombinator.com/item?id=47676123

🆔 @hackernewsgithubprojects

📦 adomi-io/listing-lab

Listing Lab: Your Personal Home Hunting Assistant

Track homes you’re considering, add notes, and share them easily. Listing Lab automatically pulls fresh details from Realtor.com to keep prices and status up to date without constant refreshing. It runs locally on your computer using Docker, so your data stays private. You save listings, tag photos, and even get popularity hints for each property. It is a simple, friendly workspace designed for individuals and families who want a clear, current view of their short list. No messy spreadsheets, just a clean dashboard that updates itself while you focus on finding the perfect place.

🆔 @hackernewsgithubprojects

📦 google-gemini/glanceboard

Glanceboard turns your calendar into e-ink art

Glanceboard turns your daily schedule into a fresh piece of art on a quiet e-ink screen. This demo connects to your Google Calendar and local weather via a simple feed, then uses Gemini and Nano Banana to generate a custom illustration every morning. It transforms boring appointment lists into visual planners that even adjust what your characters wear based on the actual temperature. You can pick from styles like watercolor or comic books, and add your own family photos so the drawings stay consistent. It runs entirely on your own computer with no cloud accounts needed, creating a digital photo frame that just shows you what matters today. No notifications.

📰 https://news.ycombinator.com/item?id=49128180

🆔 @hackernewsgithubprojects

📦 kunchenguid/dotfiles

dotfiles

Set up a new Apple computer in one shot by running a single command that installs your shell, editor, terminal, and even your AI agent rules, all managed through a reproducible configuration system. The setup installs the latest Neovim editor with a soft rose theme, configures a custom terminal window, and applies personal guidelines for coding assistants like Claude and Codex. The most interesting twist is a built-in extension that hides the AI’s messy thinking process and replaces it with a gentle animated boat sailing across your screen while it works.

🆔 @hackernewsgithubprojects

📦 starknightt/jungle-trail

Jungle Trail

Walk through a lush, photorealistic jungle where every single leaf, stone, and sound is generated instantly by code without any pre-made files. This project builds a first-person exploration experience using Three.js where the engine computes complex textures and atmospheric effects in real time, creating a dense canopy and ancient ruins entirely from mathematical functions. You wander a winding path toward a waterfall, hearing procedurally synthesized bird calls and wind that never loops, all rendered with stunning detail. It is a fascinating demonstration of how pure computation can replace traditional art assets to create an immersive, documentary-style nature walk that feels incredibly alive.

🆔 @hackernewsgithubprojects

📦 coleam00/second-brain-starter

Second Brain Starter: Your Personal AI Assistant Blueprint

This project lets you build a proactive AI assistant that remembers your context across sessions and monitors your calendar and email without you asking. It uses simple markdown files to store your habits, memories, and personality, so the AI actually knows who you are. You start by answering a few questions about your tools and preferences. Then a coding tool generates a step-by-step plan to connect your Gmail, Slack, and other apps. The system checks for urgent items every thirty minutes and drafts replies in your voice. It is a practical way to turn a generic chatbot into a helpful partner that tracks your habits and keeps your workflow organized.

🆔 @hackernewsgithubprojects

📦 my-take-dev/inspired-mino-design-skills

Mino-Drive Inspired Design Skills

Mino-drive inspired design skills is an experimental toolkit that turns web-based design principles into AI skills. It helps you break down complex problems, define clear contracts, and separate interfaces from implementation details. The project emphasizes reproducibility across different platforms like Windows, Linux, and macOS. It is not a standard library but a set of guidelines for consistent design decisions. This resource is ideal for developers looking to improve their architectural thinking and ensure their code aligns with business goals. It offers a structured way to approach design challenges without relying on vague intuition. The focus is on creating verifiable outcomes rather than just generating code.

🆔 @hackernewsgithubprojects

📦 r44vc0rp/hark

Hark: Webhooks to iPhone Notifications

Hark turns any standard internet request into a clean, source-branded notification on your iPhone. Instead of scrolling through endless chat channels or email threads, you connect your CI builds, monitoring scripts, or automation tools to a simple address that forwards updates directly to your device. The service lets you customize how each alert looks with its own name and avatar, so you instantly know where the message is coming from. It even supports live task tracking that updates right on your lock screen as a process progresses.

🆔 @hackernewsgithubprojects

📦 blendi-remade/fal-3d-anything

3D Web: Turn Any Image Into a 3D Model

This Chrome extension instantly turns any flat image on the web into a museum-quality interactive 3D model. Right click a picture, select transform to three d, and watch it morph into a rotatable exhibit with gallery lighting and soft shadows. Powered by Hunyuan three d running on fal dot ai, it generates a realistic mesh while Three JS renders a cinematic viewer with dust particles and auto rotation. You can download the result as a glb file or explore it in full screen mode. It is a clever way to make static photos feel alive and tangible directly in your browser.

🆔 @hackernewsgithubprojects

📦 toofast1/awesome-ai-lead-generation

The Modern Growth Stack

Find high-intent customers by scanning social platforms for people actively asking for your solution. Awesome AI Lead Generation is a curated collection of the best artificial intelligence tools for finding customers, listening to social conversations, and automating outreach. It replaces static databases with intelligent, intent-based acquisition. Instead of guessing who to call, you use these utilities to spot real interest and engage instantly. It is the modern growth stack that makes scaling sales feel less like cold calling and more like helpful conversation.

🆔 @hackernewsgithubprojects

📦 mujib77/cosmo

Cosmo: Live Database Dashboard

Cosmo is a terminal dashboard that finally lets you watch your PostgreSQL database breathe in real time. Most developers just run queries without knowing if the system is healthy or stuck. Cosmo fixes that by connecting directly to your server and showing you a live, four-panel view of what is actually happening inside. You see active queries counting up their duration, lock contention as it happens, and internal stats like cache efficiency and write throughput, all updating every few seconds right in your command line. No browser, no external app, just a clean interface that helps you spot slow queries and system bottlenecks instantly.

🆔 @hackernewsgithubprojects

📦 haoming02/adetailer-neo

Adetailer Neo

Adetailer Neo is the automatic image fixer that spotlights tiny flaws and gently repaints them without you lifting a finger. Think of it as a personal touch-up artist for your generated pictures, catching messy hands, blurry faces, or odd shadows that AI often misses and carefully fixing them in seconds. It runs right inside your workflow, using smart detectors to find problem spots and blending in fresh details so your images look polished and natural. This rewrite makes everything lighter, faster, and cleaner, fixing the bloat from older versions while keeping the magic intact.

🆔 @hackernewsgithubprojects

📦 lak7/teamlore

Teamlore: Shared Memory for Claude Code

Teamlore is the shared memory system that lets your AI agents learn from each other’s mistakes so you break things only once. It turns hard-won lessons into tiny, reviewable files stored in git, meaning every teammate’s agent automatically recalls the right correction when it touches the same code. One agent distills a lesson into a small lore file, and every other teammate’s agent recalls it automatically when they touch the relevant code. No servers, no accounts, just a folder in git. The most useful part is the scar map. Run one command to render the team’s knowledge as a living graph.

🆔 @hackernewsgithubprojects

📦 serhiikorniienko/bullshit-detector

AI Agent That Scores YouTube Videos on BS

A viral video about making money with AI gets torn apart claim by claim by this tool. The Bullshit Detector is an open source agent that takes a link to a YouTube video, article, tweet, or PDF and turns it into a full fact-check report. It pulls the transcript, pulls every distinct claim, and then searches the web for each one independently. It does not guess from memory. It assigns a verdict like confirmed, plausible, misleading, false, or unverifiable, and cites the actual source for every single one. Finally, it gives you a zero to ten BS score and explains why.

📰 https://news.ycombinator.com/item?id=49096917

🆔 @hackernewsgithubprojects

📦 datascale-ai/opentalking

OpenTalking: Real-Time AI Digital Humans

OpenTalking lets you build real-time digital human conversations that react instantly to what you say. It connects a language model to speech and video, so a virtual character listens, thinks, and speaks back without lag. You can run it privately on your own computer or use remote services for higher quality. The tool supports switching between different voice styles and visual drivers, making it easy to create interactive guides, companions, or presenters. It handles everything from capturing your voice to animating a face, all in one open-source framework.

📰 https://news.ycombinator.com/item?id=49150333

🆔 @hackernewsgithubprojects

📦 avifenesh/memra

Memra: Building an AI Engine from Scratch for RTX 50-Series

memra is a from-scratch large language model inference engine built in Rust and CUDA, designed specifically for the raw power of NVIDIA RTX 50-series graphics cards. Instead of relying on heavy, pre-made frameworks, this project writes every core calculation kernel by hand to squeeze out maximum speed and efficiency on the new Blackwell hardware. It achieves impressive performance gains, often beating established tools by double digits, while guaranteeing that the AI’s answers remain perfectly identical to standard methods. It is a fascinating look at how building software from the ground up unlocks incredible potential for modern AI hardware.

🆔 @hackernewsgithubprojects

📦 icebird1998/scientific-illustrator

Scientific Illustrator: Editable Figures in PowerPoint

Scientific Illustrator lets artificial intelligence build fully editable scientific diagrams directly inside Microsoft PowerPoint or draw.io. The tool uses a strict four step process where an AI designer creates a plan, a drawer builds the shapes, a reviewer checks for errors, and a corrector fixes any mistakes. This workflow ensures your charts remain completely editable rather than becoming static images. You can control every detail from arrow placement to text formatting while the system automatically enforces quality standards. It bridges the gap between quick visual generation and the precise, customizable figures researchers need for their papers without flattening the file.

🆔 @hackernewsgithubprojects

📦 codejunkie99/graph-engineering

Graph Engineering: The 9-Stage Pipeline for AI Agents

Graph engineering gives AI agents a structured memory instead of just a prompt. This project distills a university course into a nine-stage pipeline that turns messy documents into a clean, queryable graph. You start by defining the structure, then extract facts, and finally fuse duplicates so the data is accurate. It also handles task graphs to orchestrate how agents work together. You can use the included prompts to build this yourself or have an AI teach you the process step by step. It makes complex knowledge management simple and practical. Check it out if you want to build smarter AI systems without the guesswork.

🆔 @hackernewsgithubprojects