56 subscribers
7.24K videos
7.85K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ tinyfish-io/bigset

Stop Scraping: Build Any Live Dataset with BigSet

Imagine describing any dataset you need in one simple sentence and having it appear instantly on your screen. BigSet makes this a reality by using autonomous AI agents to scour the live web for you. You just provide a prompt, and the system automatically infers the schema, verifies the data, and removes duplicates to build a clean table. You can even set a refresh schedule so your information never goes stale. It is a powerful way to turn scattered web content into usable CSV or Excel files without writing a single line of code. Try BigSet to automate your data research today.

πŸ“° https://news.ycombinator.com/item?id=48373748

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

Run Untrusted Code Safely with Microsoft Execution Containers

Ever worry about running untrusted code on your machine? Microsoft Execution Containers, or MXC, is a powerful sandboxed execution system designed to handle untrusted model outputs, plugins, and tools securely. By supporting Windows, Linux, and macOS, it uses a unified JSON configuration to manage various containment backends like process containers and virtual machines. Whether you need to control filesystem access or restrict network traffic, MXC provides a reliable policy-driven framework to keep your host environment safe. It is an exciting tool for developers looking to integrate secure, isolated code execution into their own workflows with ease.

πŸ“° https://news.ycombinator.com/item?id=48375434

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ rosaboyle/awesome-cc-oss

The Massive Claude Code Leak Explained

Ever wonder what really happens inside Anthropic's AI coding tools? A massive security slip-up accidentally exposed half a million lines of proprietary Claude Code source code, revealing hidden systems like a Tamagotchi-style pet companion and proactive background agents. This repository acts as a curated archive for the incident, gathering technical breakdowns, expert security analysis, and clean-room reimplementations born from the leak. It is a fascinating look at the internal architecture and secret feature flags of a major AI product. Check out this collection to see the full story behind one of the industry's most significant accidental disclosures.

πŸ“° https://news.ycombinator.com/item?id=47597416

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ danfry1/bonsai-js

Build Safe Dynamic Logic with Bonsai JS

Need to let users define logic or custom filters without the security nightmare of using raw code execution? Meet Bonsai JS. It is a powerful, zero-dependency expression language designed specifically for building safe rules, templates, and business logic within any JavaScript runtime. Instead of relying on risky evaluation methods, Bonsai provides a controlled environment with built-in caching, type safety, and pluggable functions. Whether you are building dynamic form fields or complex rule engines, this library keeps your application secure and predictable. Give your users the power to customize logic while keeping your core infrastructure locked down and safe.

πŸ“° https://news.ycombinator.com/item?id=48381455

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ c0dejedi/nbd-vram

Turn Your Idle GPU VRAM Into Linux Swap!

Are you stuck with a laptop that has soldered memory you cannot upgrade? You might be leaving performance on the table if your NVIDIA GPU is just sitting there idle. This project lets you repurpose that unused video memory as high-priority swap space on Linux. It works by running a daemon that allocates VRAM via CUDA and serves it as a block device over a Unix socket. By using this clever approach, you can effectively expand your addressable memory without needing any special kernel modules or risky workarounds. It is a smart way to squeeze extra utility out of your hardware.

πŸ“° https://news.ycombinator.com/item?id=48377404

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

Build Powerful AI Agents with Skawld SDK

Want to build your own AI agents without starting from scratch? Check out the Skawld Agent SDK, an open-source TypeScript harness designed to embed full agent loops directly into your Node.js or Bun applications. It simplifies the complexity of managing tools, permissions, and streaming events, allowing your agents to handle subtasks with ease. Whether you need persistent SQLite sessions or in-memory storage, this library gives you the control you need to create sophisticated automation. It is a fantastic tool for developers looking to integrate powerful, self-contained agents into their projects today. Give your software a brain and start building.

πŸ“° https://news.ycombinator.com/item?id=48382499

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ ant-design/ant-design-cli

Supercharge Your Ant Design Development Offline

Want your AI coding agents to write better Ant Design code? Meet the Ant Design CLI, a powerful tool that brings component knowledge directly to your command line. It works fully offline, providing instant access to props, tokens, and documentation for versions three through six without needing any API keys. You can analyze project usage, perform version migrations, and even run an MCP server for seamless IDE integration. Whether you are querying specific component details or diagnosing project issues, this tool keeps your workflow fast and version-accurate. Boost your productivity and let your agents code with precision starting today.

πŸ“° https://news.ycombinator.com/item?id=48382575

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ sinewaveai/agent-security-scanner-mcp

Secure Your AI Agents with this Security Scanner

Are your AI coding agents inadvertently introducing vulnerabilities into your projects? This security scanner solves that by acting as a powerful guardrail for autonomous assistants. It offers deep code analysis, utilizing over seventeen hundred security rules, AST parsing, and taint tracking to find issues automatically. It even protects against package hallucinations by verifying millions of dependencies. Whether you need a lightweight scanner for quick checks or an enterprise-grade engine for complex semantic reviews, this tool integrates directly into your workflow to keep your code secure. Protect your codebase and ensure your AI tools remain safe with this essential security layer.

πŸ“° https://news.ycombinator.com/item?id=48383083

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ allthingssmitty/typescript-tips-everyone-should-know

Essential TypeScript Tips for Better Code

Are you tired of fighting your TypeScript code? This curated collection of professional patterns is a total game changer for your development experience. It moves beyond the basics, showing you how to replace loose types with safer alternatives like unknown, leverage powerful discriminated unions, and use the satisfies operator to keep your code clean and type-safe. By shifting how you approach things like runtime data validation and type inference, you can stop fighting the compiler and start building more maintainable applications. Master these practical techniques today to make your code feel more robust, reliable, and honestly, just a lot more fun.

πŸ“° https://news.ycombinator.com/item?id=48355935

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ b-nnett/goose

Take Control of Your WHOOP 5.0 Data

Ever wish you had more local control over your fitness data? Meet Goose, an ambitious open-source proof of concept designed to bridge your WHOOP 5.0 device with a custom SwiftUI interface. By routing Bluetooth packet data through a specialized Rust core, this project allows developers to visualize complex health metrics like sleep, recovery, and strain directly on their devices. While it is currently an early-stage prototype meant for technical evaluation, it offers a fascinating look at how we might interact with our own health hardware independently. Keep an eye on this project as it evolves toward a public release.

πŸ“° https://news.ycombinator.com/item?id=48369536

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ codybontecou/health-md

Take Control of Your Health Data with Health.md

Ever wish you could own your health data instead of leaving it trapped in an app? Health.md is a powerful tool for iOS and macOS that turns Apple Health into a local-first journal. It lets you extract over one hundred seventy metrics like heart rate or workouts into clean Markdown, JSON, or CSV files. You can even sync directly into your Obsidian vault for custom database queries. It works entirely offline with no cloud accounts, keeping your records truly private. Take full control of your personal metrics and start building your own health archive with this smart, privacy-focused solution today.

πŸ“° https://news.ycombinator.com/item?id=48383430

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ razz19/exort

Exort: The AI Coding Agent for Embedded Projects

Struggling to manage your embedded development workflow? Meet Exort, a powerful open-source AI coding assistant designed specifically for microcontrollers. This desktop application creates an all-in-one workspace where you can write, compile, and upload code for boards like Arduino, ESP32, and RP2040. It features an integrated AI agent that inspects your workspace to help explain or edit code, while the built-in serial monitor and plotter allow you to debug hardware behavior in real time. Whether you are prototyping firmware or learning embedded systems, Exort streamlines your entire development cycle into one smooth experience. Simplify your hardware projects and start building today.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ 0x4m4/hexstrike-ai

Automate Pentesting with HexStrike AI

Want to supercharge your security testing with the power of artificial intelligence? HexStrike AI is a revolutionary MCP server that lets your favorite AI agents like Claude or GPT autonomously run over one hundred and fifty cybersecurity tools. By bridging advanced language models with real world offensive capabilities, it automates complex tasks like vulnerability discovery and bug bounty research. With twelve specialized agents, including options for exploit generation and network reconnaissance, it streamlines your entire workflow through an intelligent decision engine. Start integrating professional grade automation into your security assessments today and experience the future of autonomous penetration testing.

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

Automate Your Hiring Process with AI

Are you tired of manually sorting through piles of resumes? This hiring agent simplifies your recruitment workflow by turning PDF resumes into structured data. It extracts key details, enriches them with GitHub profile insights, and provides an objective, explainable evaluation with scores and evidence. Whether you run it locally using Ollama or connect it to Google Gemini, the system handles everything from parsing to scoring with fairness in mind. It is a powerful tool to bring consistency and speed to your candidate screening process. Try it out to start making more data-driven and efficient hiring decisions today.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ nvidia-nemo/gym

Supercharge Your AI Agents with NeMo Gym

Are you struggling to reliably test and improve your AI agents? Meet NeMo Gym, a powerful library designed to help you evaluate and optimize models within interactive environments. By providing modular interfaces for agents, verifiers, and task execution, it solves the challenge of testing complex, stateful behaviors at scale. Whether you need to run thousands of concurrent training requests or ensure reproducible evaluations across your team, this tool bridges the gap between simple testing and production-grade training. It is an essential asset for developers aiming to build more capable agents, so start experimenting with NeMo Gym to elevate your AI development today.

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

Monitor Your AI Coding Agents with Abtop

Are you running multiple AI coding agents at once? Managing their tokens, rate limits, and background processes can quickly become a headache. Meet abtop, the terminal-based monitor designed specifically for tools like Claude Code and Codex. It gives you a real-time view of every active session, including context window usage, active ports, and even orphan process detection, all in one clean dashboard. It works across macOS, Linux, and Windows with no sensitive data access required. Whether you are juggling multiple projects or just want to stay within your limits, abtop helps you stay in complete control.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ eunomia-bpf/agentsight

Stop Guessing What Your AI Agents Are Doing

Ever wonder what AI agents are actually doing to your computer behind the scenes? Meet AgentSight, a powerful tool that monitors AI agents at the system level without needing any code changes or tricky integrations. By using eBPF, it tracks everything from subprocess executions and file operations to network activity and even decrypted LLM prompts, all without relying on SDKs or proxies. Whether you are using open or closed-source CLI agents, AgentSight provides a clear, real-time view of their behavior and system impact. Install it today to finally bridge the gap between AI decisions and your machine’s actual performance.

πŸ“° https://news.ycombinator.com/item?id=48386737

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

Build Your Own AI-Powered Camera

Ever wanted to build a digital camera that transforms your world into art? Meet ImageGenCam, an open-source project that lets you create a custom point-and-shoot camera using a Raspberry Pi and a 3D-printed case. By integrating generative AI, this device takes your photos and instantly reimagines them through unique prompts, like turning your subjects into cheese or stylized anime characters. It is a fantastic weekend project that blends hardware engineering with creative coding. Grab your parts, use the provided assistant to guide your assembly, and start building your own programmable camera to capture the world in your own style.

πŸ“° https://news.ycombinator.com/item?id=48372591

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

Build High-Performance GUIs with Gooey

Stop struggling with sluggish user interfaces and meet Gooey, a powerful hybrid framework built for the Zig programming language. This project enables you to create lightning-fast, GPU-rendered applications that run seamlessly across macOS, Linux, and the web. By utilizing technologies like Metal, Vulkan, and WebGPU, Gooey provides developers with a robust, component-based system that blends immediate and retained mode rendering for optimal performance. Whether you need complex animations, built-in themes, or native file dialogs, this framework simplifies the process while keeping your code clean and testable. Dive into Gooey today to start building fluid, professional-grade interfaces with ease.

πŸ“° https://news.ycombinator.com/item?id=48386725

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ kuba-guzik/caveman-micro

Slash AI Token Costs with This 6-Line Prompt

Are you tired of wasting expensive tokens on overly wordy AI responses? Meet Caveman Micro, an incredibly efficient six-line prompt that forces any LLM to get straight to the point without sacrificing quality. While other prompts use hundreds of tokens to explain conciseness, this tiny instruction set cuts the fluff, drops articles, and removes unnecessary pleasantries to save you significant processing costs. Tested on Claude Sonnet and Opus, it maintains perfect accuracy while maximizing efficiency. Give your AI permission to be brief today, save on those long-term API calls, and start optimizing your workflow with this simple, powerful shortcut.

πŸ“° https://news.ycombinator.com/item?id=47691809

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ bergside/design-md-figma

Turn Figma Designs into AI-Ready Blueprints

Tired of design inconsistencies when coding? This Figma plugin automatically extracts your local styles and variables to create a structured design and skill markdown file. By generating these blueprints, you provide AI coding assistants with clear, actionable context on your colors, typography, and component rules. It eliminates guesswork for your agents, ensuring they follow your design system perfectly every time. Whether you are building complex interfaces or simple sites, this tool bridges the gap between your design files and AI development workflows. Try it out to finally sync your design and code effortlessly starting today.

πŸ“° https://news.ycombinator.com/item?id=47924396

πŸ†” @hackernewsgithubprojects