143 subscribers
10.2K videos
10.8K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ kaankiziltug/logo-design-skill

Logo Design Skill: The AI Logo Designer

The most striking feature of Logo Design Skill is its private library containing over fourteen hundred real world logo files that an AI agent can search to understand design trends without copying existing brands. This project turns coding assistants into professional identity designers by guiding them through discovery briefs to final vector files. It uses simple Python scripts to automatically test every draft for readability at tiny sizes and color contrast issues before you even see the result. The system stops at a checkpoint to show you a concept overview with a recommendation, ensuring the final brand kit only matches a direction you actually approve.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ angel291592/intent-router

Intent-Router: The Intent Compiler for AI Agents

A tiny prompt-only tool turns vague requests into strict contracts before any AI agent begins working. Intent-Router scans your actual code, docs, and ticket history to answer questions that already have answers, so it never interrupts you with forty-six follow-ups. Instead, it asks exactly one question that only you can answer, then saves the result as a machine-readable file called an IntentSpec. This means the next agent, session, or teammate starts from a shared contract rather than guessing from zero. It is the missing input layer that stops models from hallucinating context and forces them to respect what your project already says.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ xiaopuouo/openchatx-mcp

OpenChatX MCP

Long-running artificial intelligence tasks can finally survive the end of a ChatGPT session without forcing you to manually reconstruct your work. OpenChatX MCP connects ChatGPT directly to your computer using the official, secure Model Context Protocol tunnel rather than unstable browser workarounds. By running a local runtime, it equips your regular chat with coding-grade file and shell tools, custom skills, and rules, all without draining your specialized agentic allowance. You can seamlessly bundle your folders into projects, delegate tasks to custom subagents, and generate unique session handoffs to transfer complete context to a fresh chat window instantly.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ yuta-fywoo/jev-gui-delegate

Jev GUI Delegate

Running complex browser and desktop tasks with artificial intelligence can quickly drain your tokens because models keep reading the screen, selecting buttons, and repeating commands. Jev-gui-delegate solves this by introducing a local controller that handles the repetitive, deterministic clicks on Windows and Chrome, calling on a smart model only when semantic judgment is needed. In real-world tests, this smart delegation slashed the main model's token consumption by up to ninety-one percent and made end-to-end task execution over three times faster. It keeps operations safe with built-in user takeovers, strict boundaries, and outcome verification, saving computing power while keeping you in control.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ lemomo-ai/lemo-opuscar

lemo-opuscar

An artificial intelligence agent can now direct, draw, score, and mix an entire short film from scratch using absolutely no video generation models or stock footage. The lemo-opuscar repository lets your coding agent act as a miniature film studio, rendering canvas and WebGL pages frame by frame to produce stunning animations. You just pick from thirty-nine distinct artistic styles, like retro eighty-column CRT terminal art, eighty-era cel anime, or traditional Chinese ink washes, and let the agent write the code to bring your story to life. It is a brilliant, hands-on way to watch code become cinema.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ microsoft/windowsdeveloperconfig

Windows Developer Config: One Command Setup

Windows Developer Config is the setup tool that turns a fresh Windows machine into a complete dev station in one go. You run a single command, it installs your favorite tools like Git and VS Code, tweaks your settings, and even handles the tricky restart needed for WSL. It picks back up automatically after you sign back in. This is great if you hate spending hours configuring your environment. It gives you a standard, tested setup that is safe to run again. You get a clean, distraction-free workstation without the guesswork. It’s a huge time saver for anyone starting a new project or swapping laptops.

πŸ“° https://news.ycombinator.com/item?id=49871976

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ supercorp-ai/supercov

Supercov: The QA Boss for AI Coder

Supercov turns your AI coding assistant into a disciplined engineer that proves its own work. Instead of just generating code, the agent runs your real test suite through Supercov to find exactly which lines and branches are missing coverage. It then writes one specific test for that gap, reruns the suite, and uses the diff to verify the improvement. This loop creates a verifiable record of quality, meaning your AI never claims success without solid evidence. It is a simple way to keep automated coding safe and accurate, ensuring every change is backed by real results. Stop trusting blindly and start demanding proof from your machine coder.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ admte/orc-claude-plugin

ORC8R Claude Plugin

Connect your Claude assistant directly to your cloud infrastructure with the orc-claude-plugin. This handy Model Context Protocol tool lets you manage your cloud projects, nodes, and billing right from your chat box. Instead of jumping between tabs to check log files or run terminal commands, you can just ask Claude to check on your nodes or look up usage metrics. It safely uses your existing cloud permissions through secure authentication, so you can inspect resources or even deploy changes with simple conversational prompts. It turns your favorite AI assistant into a highly capable, hands-on cloud administrator.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ agentsystemlabs/agent-office

Agent Office

Your software development tasks can now be completed inside a multiplayer three dimensional cartoon building where digital workers sit at desks and write code. This virtual space clones your code repositories onto separate office floors where you can hire artificial intelligence assistants to solve software issues and open pull requests. You can walk around using standard movement keys, look over the shoulders of your digital team to watch their terminals in real time, and jump into the terminal with them to type together. When a task succeeds, a brass gong rings and confetti falls from the ceiling.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ elmasas/lcs-recomp

LCS Recomp

Play Grand Theft Auto Liberty City Stories natively on your modern PC by transforming the original PlayStation Portable code directly into high-performance C plus plus. Instead of running a traditional, resource-heavy emulator, this project uses static recompilation to translate the game's executable files into native code for Windows and Linux. By running the game natively, you bypass the usual emulation bottlenecks, allowing for smooth rendering through modern graphics interfaces like Vulkan and DirectX 12. It delivers a highly responsive gaming experience with native windowing and audio support, giving a classic handheld title a brand new life on modern hardware.

πŸ†” @hackernewsgithubprojects
❀1
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ imikerussell/beebots

Beebots

Race three artificial intelligence trading bots against each other in real time with paper money. Beebots lets you deploy three customized virtual trading agents on your own server to run on perpetual futures markets. Every single trading decision is powered by Typesafe AI's decision model, named Jev, while a built-in safety layer written in plain code enforces hard risk controls like daily loss stops and leverage limits. You can describe how you want each agent to trade in a single simple sentence, and OpenAI automatically generates their rules, assets, and portraits. Watch every order and fee live on your personal dashboard, or share your results on the public leaderboard.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ danfessler/trellis

Trellis

Build dynamic web workspaces where users can freely arrange their own layouts. Trellis lets you nest panels as deep as you want, split, float, or hide tabbed views, and easily zoom into any part of the interface without reloading. The magic is that every view stays mounted in the background, so running canvas drawings, interactive states, and active iframes never lose their place or reset when dragged around. It works beautifully with React or vanilla JavaScript, automatically managing complex resizing and animations. It is a fantastic way to give your web applications a rich, desktop-grade workspace that feels incredibly smooth and responsive.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ promethe-us/awesome-jev

What is Jev? The Fast Decision Model

Jev is a specialized artificial intelligence that makes split-second choices without writing a single word of code. Released by TypeSafe AI, this System One model is built to handle massive volumes of text in milliseconds, returning a simple yes, no, or ranked list of options instead of a long paragraph. It is designed for high-speed tasks like routing support tickets or validating data where speed matters more than creative writing. The repository awesome-jev acts as a central hub, organizing these technical specs alongside community experiments and research papers. If you are building applications that need instant decisions, this collection provides the verified sources you need to get started.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ sunkeke-ai/life-compass-obsidian-cn

Life Compass Obsidian CN

This unofficial Chinese translation lets anyone run a complete personal operating system inside Obsidian without needing to understand English interfaces. The project takes a detailed life management vault originally built by Daniel Agrici and converts its navigation, habit trackers, and task boards into Simplified Chinese. It solves the problem of language barriers by keeping the original system intact while changing how it looks to you. You get a structured space for journaling, planning, and project tracking that feels native to your language. The result is a personal dashboard that guides your daily decisions and long-term goals, making complex life organization accessible to a new audience.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ yuedizhibo/mhi2q-carplay-altscreen

mhi2q-carplay-altscreen

Display your native Apple CarPlay navigation map directly on your Audi Virtual Cockpit dashboard. The mhi2q-carplay-altscreen project completes the missing software logic for Audi vehicles running on the high-end MIB2 platform, allowing the instrument cluster to show real-time secondary navigation views while keeping your main center screen completely unaffected. It acts as an add-on overlay for the popular MIB2 Toolbox, using custom scripts and system configurations to bridge the video stream directly to your digital instrument cluster. It is incredibly useful for drivers who want a more integrated, distraction-free navigation experience without buying expensive hardware adapters. Try loading it onto your SD card to upgrade your dashboard display.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ reinauer/xsysinfo

Peek Inside Your Classic Amiga with XSysInfo

Peek inside your classic Amiga without opening the case. XSysInfo digs into the hardware to tell you exactly what processor, memory, and expansion boards are actually running your machine. It goes way beyond a simple list, giving you a detailed report on your software setup and even running a quick benchmark to see how fast your system is. This is perfect for anyone who wants to know exactly what their beloved retro machine is capable of. It turns a mysterious box of circuits into clear, readable data. No more guessing about your hardware.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ juhlabs/juhradial-mx

JuhRadial MX: The Missing Mouse Control for Linux

JuhRadial MX is the missing mouse control app that finally gives Logitech MX mice their full power on Linux. If you are running Wayland or Hyprland, you know the official software is a ghost, leaving your fancy buttons and haptic feedback useless. This open source tool steps in to bridge that gap, letting you remap buttons, trigger shortcuts, and even switch computers with a single gesture. The real magic is the radial menu that pops up right under your cursor, turning your mouse into a command center. It is a simple fix for a frustrating gap, giving your hardware the respect it deserves without any cloud nonsense.

πŸ“° https://news.ycombinator.com/item?id=49855875

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ limin112/min-skill

Min Skill: The Code-Based Video Builder

Min Skill is the coding toolkit that treats your video project like a version control repository instead of a messy folder of files. Instead of dragging boxes in a slide deck or wrestling with a complex timeline editor, you write a simple HTML file that drives the entire production. This single source of truth generates the visuals, the narration script, and the subtitle timing automatically. It is fascinating because you can track every change like code, roll back mistakes instantly, and tweak the voice or music without re-creating the whole video. It turns video editing into a transparent, repeatable process that any developer can master.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ thinkflowlab/system1-agents

system1-agents

AI agents are running up to six times faster and twenty-five times cheaper just by bypassing heavy chat models for basic actions. Instead of using a giant language model to decide every single mouse click or simple choice, system1-agents delegates those quick, split-second decisions to specialized, lightweight decision models like Jev, Laya, or Cua-S1 Nano. It acts like a fast-thinking brain for tasks like browsing the web, clicking through desktop apps, routing customer support tickets, or playing games. You get lightning-fast execution and a fraction of the API bill, while leaving the complex reasoning to your main chat model. Check it out to build lightning-fast agents today.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ vilin97/lean-pool

Lean Pool: The AI-Maintained Math Archive

Lean Pool is a massive archive of machine-verified mathematical proofs that uses artificial intelligence to handle the boring parts of code review so humans can focus on the math. It sits in the gap between massive, slow-moving libraries and small, isolated projects, allowing new formalizations to be merged quickly without sacrificing correctness. The coolest part is the challenge mode, where anyone can post an unsolved theorem, and the system automatically verifies if your proof actually works using a kernel check. It turns the tedious process of mathematical validation into an automated pipeline, proving that AI can maintain rigorous logic just as well as any human reviewer.

πŸ†” @hackernewsgithubprojects