📦 shigella520/mindtrain

mindtrain

The private AI knowledge gym that finally turns temporary chat conversations into permanent memory. MindTrain is a self-hosted platform designed to help you practice and review concepts directly through an AI coach. Instead of just answering questions and moving on, you can pause, ask for hints, or challenge an answer in mid-conversation without ruining your score. The magic happens behind the scenes, where the app uses deterministic grading to keep scores accurate and runs a spaced-repetition scheduler to automatically pause new material if your backlog gets too high. It is the perfect setup for keeping your study data private on your own machine.

🆔 @hackernewsgithubprojects

📦 leeguooooo/chrome-use

chrome-use

Control your real, logged-in Chrome browser directly from any AI agent or command line without ever triggering annoying bot detection or dealing with constant remote debugging popups. While typical automation tools force you into an empty browser where you have to re-login and solve endless captchas, chrome-use connects straight to your active browser session using a lightweight extension and native messaging. This means your cookies and login sessions are already active, and sites read your agent's actions as a real human. You can easily watch the agent work in real-time, step in to solve a puzzle if needed, and let it resume seamlessly.

📰 https://news.ycombinator.com/item?id=48668131

🆔 @hackernewsgithubprojects

📦 experientiallabs/world-model-harness

World Model Harness

AI agents are incredibly powerful, but testing them in real-world environments is expensive, slow, and risky. World-model-harness solves this by letting you build a simulated environment directly from recorded agent traces. Once you record how your agent interacts with tools and databases, this project compiles those actions into a local, lightweight world model that mimics the real system. From there, you can safely run parallel tests and automatically optimize your agent prompts, tools, and code without paying for constant live API calls. It gives developers a safe, sandboxed playground to continuously test and improve their AI agents before deploying them.

📰 https://news.ycombinator.com/item?id=48735124

🆔 @hackernewsgithubprojects

📦 moonshotai/kimi-code

kimi-code

You can now run a fully interactive AI coding agent directly inside your terminal. Developed by Moonshot AI, kimi-code is a command-line tool that reads and edits your project files, runs shell commands, searches code, and surfs the web to solve programming tasks. What makes it special is its real-time feedback loop: it executes changes, tests the results, and automatically decides the next steps. It works out of the box with Kimi models but easily connects to other providers. It is the perfect terminal companion for developers who want an automated assistant to handle the heavy lifting of debugging and coding.

🆔 @hackernewsgithubprojects

📦 1ay1/agentty

Agentty

Agentty is the terminal-based AI pair programmer that starts in under a single millisecond without needing heavy dependencies like Node or Python. It packages a complete, lightning-fast assistant into a single static binary that runs right inside your command line. The absolute coolest part about this project is its entirely local, zero-dependency search engine that runs right on your machine. It combines classic keyword search with smart vector search to instantly find answers across your local files, code, and documentation, even when you are completely offline. You get a private, blazing-fast coding companion that respects your system and respects your data.

📰 https://news.ycombinator.com/item?id=48928002

🆔 @hackernewsgithubprojects

📦 rakuensoftware/aimee

Aimee AI Development Agent

Hand over your trickiest coding chores to a dedicated, autonomous development companion designed to work right alongside you. This repository hosts aimee, a clever agentic engine written in C that tackles real-world software engineering directly in your workspace. Instead of just spitting out basic chat replies, it uses advanced code-graph intelligence and dynamic memory to navigate complex codebases, diagnose bugs, and safely run edits in a sandbox. It acts like a highly competent junior developer who actually understands your project's unique architecture. If you want to see how far autonomous software development has come, spin up this repository and let it tackle your next bug fix.

🆔 @hackernewsgithubprojects

📦 wunderlandmedia/launchworthy

launchworthy

Launchworthy is the Claude Code skill that finally plays bouncer at the door of production for your AI-built apps. While tools like Cursor, Bolt, and Lovable are fantastic at spinning up a working demo, they often leave massive gaps under the hood, like leaving database row-level security completely disabled or baking private API keys into your public frontend bundle. This tool auto-detects your exact framework and backend, runs a rigorous audit across five critical domains, and gives you a scored scorecard. Best of all, it hands you a prioritized punch list with exact file paths and copy-paste code fixes to lock your app down before real users touch it.

🆔 @hackernewsgithubprojects

📦 inlitx/streak

Streak Habit Tracker

Streak is the minimalist habit tracker that finally respects your privacy with zero ads, zero tracking, and absolute offline capability. Built with Flutter, this sleek app lets you log daily goals, set customized reminders, and track progress with a satisfying GitHub-style contribution grid that visually maps out your consistency. Everything stays entirely on your phone, meaning no annoying account sign-ups or subscription paywalls. You can even export your progress as a beautiful image to share with friends. Grab the app from GitHub or F-Droid to build better daily routines entirely on your own terms.

🆔 @hackernewsgithubprojects

📦 petergyang/no-ai-slop

No AI Slop

no-ai-slop is the AI skill that finally strips out the robotic, formulaic fluff from your drafts. Instead of generating text, it acts as a sharp human editor to scan your writing, spot over twenty patterns of dead giveaway AI patterns, and delete them on the spot. It targets annoying throat-clearing openers, fake-insight setups, colon reveals, and all those banned corporate buzzwords we are all tired of reading. Best of all, it protects your actual human voice and blunt humor rather than flattening everything into boring, generic prose. Try pasting your next draft into Claude to make your writing instantly sound like a real person again.

🆔 @hackernewsgithubprojects

📦 karanjot786/termui

termui

Build gorgeous, interactive dashboard apps right inside your terminal using JavaScript and React-style tools. With termui, you do not have to mess around with ancient system libraries or complex layout hacks. Instead, you get a modern environment complete with Flexbox styling, JSX, and instant hot-reloads that update your terminal screen in milliseconds as you write code. The coolest part is how it handles massive data streams. Its virtual list component lets you render a million rows with zero performance lag, keeping your command-line interfaces incredibly snappy. It is the perfect tool for turning messy terminal scripts into beautiful, interactive workspaces.

📰 https://news.ycombinator.com/item?id=49009556

🆔 @hackernewsgithubprojects

📦 vncsmnl/rwx

rwx

You can visually paint your Unix file permissions directly in your terminal using an interactive grid of checkboxes instead of memorizing octal math. This is possible because rwx turns the chore of managing file access into a live, visual terminal dashboard. Instead of guessing chmod formulas, you just use your arrow keys and spacebar to toggle read, write, execute, or special bits, seeing the final symbolic representation update live. You can even type raw octal values, validate owner and group names on the fly, and safely commit changes across entire folders recursively. It makes system administration feel like a simple game.

📰 https://news.ycombinator.com/item?id=48994733

🆔 @hackernewsgithubprojects

📦 tonbistudio/model-trader

Model Trader

Model Trader lets you turn the recorded thinking of any seasoned trader into a fully automated paper trading system. Instead of relying on rigid, hardcoded rules, you feed in their YouTube transcripts, articles, or tweets to extract their core philosophy. The system translates their real-world strategy into a pipeline of pass-and-fail checks, scanning live charts and executing paper trades. You can even layer an artificial intelligence agent on top to review every potential setup against the trader's actual voice before pulling the trigger. It is a brilliant way to turn human market intuition into an executable trading partner.

🆔 @hackernewsgithubprojects

📦 zfinix/another

Another

Your AI agent can now visually navigate and fully control your physical Android phone using a system called Another. By launching a lightweight desktop interface powered by Rust and Tauri, this application runs a local Model Context Protocol server that translates your AI's decisions into direct device interactions. The agent can take screenshots, swipe, type, launch applications, and even run shell commands, letting it automate mobile tasks in real time while you watch the live video stream. It is a fascinating bridge between local artificial intelligence and physical hardware, giving developers a frictionless way to let language models interact with the mobile world.

🆔 @hackernewsgithubprojects

📦 plasma-ai/fractal

Fractal

Fractal is the autonomous agent manager that finally keeps your complex coding tasks organized by growing like a tree. Instead of forcing one AI to do absolutely everything in a single session, this tool lets your agent automatically spawn child agents in their own isolated git worktrees for smaller subtasks. It coordinates the whole family tree, enforces hard budget caps on time and API costs, and tracks every step in a local database you can monitor live in a terminal dashboard. It is a brilliant way to let AI tackle massive codebases without running wild spending sprees or lost context. Check out fractal to see recursive coding agents in action.

📰 https://news.ycombinator.com/item?id=48996269

🆔 @hackernewsgithubprojects

📦 yuanweize/lazymount-mac

LazyMount Mac

You can now run massive Steam game libraries and heavy AI models directly from your network storage without wasting your Mac's expensive built-in SSD space. An open-source tool called lazymount-mac automates this entire setup by handling network drives in the background. It automatically mounts network shares and cloud storage at startup, monitors your connection, and seamlessly reconnects if your network drops. Best of all, it features a self-healing background monitor that automatically repairs damaged disk images to prevent Steam write errors. It is a fantastic set-and-forget utility for expanding your Mac storage using a home server.

🆔 @hackernewsgithubprojects

📦 kalcode/spaceprojectsim

Spaceprojectsim

Watch an entire galactic civilization run itself in a gorgeous, self-operating universe built with Rust and Bevy. Instead of playing a typical game, you act as a god-mode observer monitoring hundreds of autonomous ships that trade, mine, and accept contracts based on real-time AI planning. The most incredible part is the dynamic economy, where prices aren't fixed; instead, markets price thirteen different commodities using actual shortages and local demand. When supplies run low, prices skyrocket, and autonomous cargo haulers dynamically recalculate their flight paths to chase the profit. It is a living, breathing model of cosmic capitalism right on your screen.

📰 https://news.ycombinator.com/item?id=48996187

🆔 @hackernewsgithubprojects

📦 decrazyo/anes

anes

Anes is the hardware modding project that turns a classic Nintendo Entertainment System into a dual-chip graphical powerhouse. By desoldering chips from a donor console and combining them onto a custom daughterboard, this hardware modification wires two picture processing units into a single system. The second chip effectively doubles the visual capabilities of the retro console, unlocking deeper colors, many more simultaneous on-screen sprites, and actual hardware-driven parallax scrolling. While it requires serious soldering skills, the project opens up a fascinating look at what classic gaming hardware can do when pushed beyond its original design limits.

📰 https://news.ycombinator.com/item?id=48652997

🆔 @hackernewsgithubprojects

📦 lidge-jun/opencodex

OpenCodex

You can now run any AI model you want inside Codex and Claude Code. A tool called opencodex acts as a clever local proxy that translates the Codex API into the language of other providers. Instead of being locked into default models, you can instantly route your development tasks to Claude, Gemini, DeepSeek, or even your own local Ollama models. It supports streaming, tool calling, and complex reasoning on the fly, and you can manage everything from a simple web dashboard. It is the ultimate way to bring your favorite AI brain to your existing coding workflow.

📰 https://news.ycombinator.com/item?id=49012330

🆔 @hackernewsgithubprojects

📦 owasp/www-project-agent-memory-guard

OWASP Agent Memory Guard

Stop hackers from poisoning your AI agents by protecting their long-term memory. When an AI saves a conversation, an attacker can sneak in malicious instructions that hijack the agent on its very next run, even if you clear the chat history. To stop this, www-project-agent-memory-guard sits directly between your agent and its storage, scanning every single read and write. It blocks prompt injections, redacts leaked secrets, and prevents unauthorized system setting changes in just microseconds. Best of all, it runs completely locally with no external API calls, keeping your AI secure, compliant, and under your control.

📰 https://news.ycombinator.com/item?id=48342710

🆔 @hackernewsgithubprojects

📦 macpaw/cleanmymac-cli

CleanMyMac CLI

Reclaim gigabytes of wasted storage directly from your terminal by targeting bloated caches, old build artifacts, and heavy project dependencies in seconds. This clever command-line tool searches out developer junk from Xcode, Docker, package managers, and AI tools, gathering all those hidden digital leftovers into a clean interactive dashboard. You can easily hunt down massive folders like node_modules, analyze your overall disk usage, and even free up inactive RAM with simple commands. The best part is that nothing gets deleted without your explicit approval, meaning your actual source code remains completely safe. Install it with Homebrew to keep your environment running fast.

🆔 @hackernewsgithubprojects