📦 anzellai/sky

Meet Sky: The Elm-Inspired Language That Compiles to Go

Ever wanted the functional elegance of Elm paired with the power of Go? Meet Sky, an experimental programming language designed to give you the best of both worlds. It features Hindley-Milner type inference and a unique server-driven UI framework that ditches complex frontend pipelines for seamless, performant web development. Because it compiles directly to a single, portable Go binary, you can ship your entire fullstack application with ease. Whether you are building complex backend systems or interactive interfaces, Sky helps you write safer code faster, leaving the dependency hell behind. Give your development workflow a major upgrade today.

📰 https://news.ycombinator.com/item?id=47662116

🆔 @hackernewsgithubprojects

📦 safishamsi/graphify

Turn Your Messy Codebase into a Smart Knowledge Graph

Ever feel lost in a massive folder of code, PDFs, and random notes? Meet the ultimate AI coding assistant skill that transforms any directory into a structured, queryable knowledge graph. By using deterministic analysis for code and intelligent agents for documents and images, this tool maps out connections, surfacing surprising insights and identifying key concepts that were previously buried. It drastically reduces token usage by letting your AI read a compact map rather than raw files. Whether you are debugging complex architectural decisions or organizing research papers, this utility makes your entire project searchable, understandable, and perfectly connected.

📰 https://news.ycombinator.com/item?id=47668188

🆔 @hackernewsgithubprojects

📦 zoriya/kyoo

Stop Managing Your Media Files Manually With Kyoo

Are you tired of constantly renaming files and organizing folders just to get your media server to recognize your collection. Meet Kyoo, a smart, self-hosted media server designed to handle your movies, series, and anime without the maintenance headache. Unlike other platforms that demand strict folder structures, Kyoo is built to work seamlessly with your existing download directories, even if the file names are messy or unconventional. With powerful features like dynamic transcoding for instant quality adjustments and handy video preview thumbnails, it keeps streaming effortless. If you want a truly set-it-and-forget-it media library solution, give Kyoo a try.

📰 https://news.ycombinator.com/item?id=47668295

🆔 @hackernewsgithubprojects

📦 python-roborock/local_roborock_server

Take Full Control of Your Roborock Vacuum Locally

Ever wish you could manage your smart home devices without relying on external clouds? This project offers a private Roborock server stack that you can host entirely on your own local network. By setting up this system, you gain control over the HTTPS and MQTT communications that your vacuum uses, effectively cutting the cord to external servers. It is a perfect solution for privacy-focused users who want to keep their home data local. Just remember that this is an early beta project, so it is best suited for those comfortable with Docker and technical setups to get everything running smoothly.

📰 https://news.ycombinator.com/item?id=47668576

🆔 @hackernewsgithubprojects

📦 celestoai/smolvm

Build Safer AI Agents with SmolVM

Are you tired of worrying about AI agents wreaking havoc on your local machine? Meet SmolVM, an open-source tool that creates secure, disposable sandboxes for your code execution and browser tasks. It solves the risk of running untrusted code by isolating everything inside lightweight virtual machines, like Firecracker or QEMU. Whether you need to automate browser sessions or provide your agents with a safe shell environment, SmolVM offers a simple Python SDK and CLI to handle it all. It is the perfect way to keep your main system clean and protected. Take control of your agent workflows today.

📰 https://news.ycombinator.com/item?id=47668778

🆔 @hackernewsgithubprojects

📦 mohshomis/modo

Stop Coding Blindly: Meet the Spec-First AI IDE

Tired of AI coding tools that dive straight into code without a plan? Meet Modo, an open-source IDE built for developers who want more structure in their workflow. Instead of jumping from prompt to code, Modo forces a disciplined, spec-driven approach by generating requirements, design documents, and detailed task lists as markdown files before writing a single line of code. You can even use features like agent hooks to automate tasks or steering files to enforce project rules automatically. It is fully open-source, giving you total control and transparency over your development environment. Give Modo a try today.

📰 https://news.ycombinator.com/item?id=47655268

🆔 @hackernewsgithubprojects

📦 arman-bd/guppylm

Build Your Own Tiny Fish AI: Meet GuppyLM

Ever wondered how a massive language model really works under the hood without all the complex technical black magic? Meet GuppyLM, a tiny, specialized language model with just nine million parameters that is specifically designed to talk like a small fish. This project solves the mystery of AI by stripping away the noise to show you exactly how data, tokenizers, and architectures fit together. It is built using a simple vanilla transformer, trained on sixty thousand synthetic conversations in just five minutes. Whether you are curious about artificial intelligence or learning machine learning, dive in and explore today.

📰 https://news.ycombinator.com/item?id=47655408

🆔 @hackernewsgithubprojects

📦 kessler/gemma-gem

Run AI Privately in Your Browser

Ever wanted to run powerful artificial intelligence directly inside your web browser without relying on external servers? The Gemma Gem project makes this possible by utilizing WebGPU technology to execute Google’s Gemma 4 model entirely on your local machine. Because everything happens on your computer, your data never leaves your device and you do not need any complicated API keys or cloud subscriptions. It is a fantastic way to experiment with advanced language models privately and efficiently. Give it a try if you want to keep your digital interactions secure while exploring the latest in browser based machine learning.

📰 https://news.ycombinator.com/item?id=47655367

🆔 @hackernewsgithubprojects

📦 asamassekou10/ship-safe

Is Your AI Code Agent Putting Your Project at Risk?

Are you building with AI agents but worried about hidden vulnerabilities? Modern coding tools bring incredible speed, but they also introduce complex risks like prompt injection, unauthorized tool access, and insecure pipeline configurations. That is where Ship Safe steps in as a powerful security scanner built specifically for the agentic era. By running eighteen specialized agents in parallel, it identifies critical misconfigurations, detects hardcoded secrets, and even vets MCP tool manifests before they connect to your environment. Protect your codebase from supply chain attacks and AI agent misuse today, because staying secure is the smartest way to keep building fast.

📰 https://news.ycombinator.com/item?id=47669335

🆔 @hackernewsgithubprojects

📦 solod-dev/solod

Write Go, Ship C: Meet Solod

Ever wish you could write systems code with the clean syntax of Go but needed the raw portability of C? Solod is a fascinating project that lets you do exactly that by transpiling a strict subset of Go directly into readable C11 code. It removes the complexity of garbage collection and runtimes, making it perfect for developers who want type safety and great tooling while maintaining full control over stack-allocated memory. You get native C interoperability and straightforward debugging, giving you the best of both worlds. Give your next systems project a fresh start by bridging Go and C today.

📰 https://news.ycombinator.com/item?id=47669337

🆔 @hackernewsgithubprojects

📦 xicilion/boxsh

Take Control of Your Shell Security

Stop worrying about rogue commands wrecking your system because this sandboxed shell gives you total control over execution. It creates a secure POSIX shell environment that wraps your terminal processes, effectively containing any potential threats while you work. What makes it truly unique is the concurrent JSON line RPC mode, allowing you to easily communicate with your shell using structured data for automation. It is the perfect bridge for developers needing a robust way to bridge security with scriptable workflows. Give your terminal an upgrade today and experience a safer, smarter way to run commands in your environment.

📰 https://news.ycombinator.com/item?id=47661505

🆔 @hackernewsgithubprojects

📦 milla-jovovich/mempalace

Stop Losing Your AI Conversations Forever

Tired of your AI forgetting every project detail the moment you close a chat window? Meet MemPalace, the highest-scoring open-source AI memory system that runs entirely offline on your own machine. Instead of letting AI guess what matters, it organizes your data into a logical palace of wings, rooms, and halls to keep information perfectly searchable. Using a unique lossless compression dialect called AAAK, it packs massive amounts of context into tiny token counts. This keeps your AI smart, consistent, and fast without any recurring subscription fees or cloud dependencies. Take control of your digital knowledge and never repeat yourself again.

📰 https://news.ycombinator.com/item?id=47669671

🆔 @hackernewsgithubprojects

📦 ertis-research/kafka-ml

Streamline Your AI Pipelines with Kafka-ML

Are you struggling to connect real-time data streams to your machine learning models? Meet Kafka-ML, a powerful open-source framework that bridges this gap effortlessly. It allows you to manage the entire lifecycle of TensorFlow and PyTorch models directly on Kubernetes, turning complex data streams into actionable intelligence. Whether you are handling single models, distributed architectures, or even federated learning, this tool simplifies training and inference workflows without needing external libraries. By integrating your streaming data directly into your models, you can prototype, deploy, and visualize predictions in real-time. Start optimizing your AI infrastructure today with this flexible solution.

📰 https://news.ycombinator.com/item?id=47669653

🆔 @hackernewsgithubprojects

📦 atomicmemory/llm-wiki-compiler

Turn Your Scattered Notes into a Smart Wiki with LLM Compiler

Are you tired of losing important information in a graveyard of bookmarks? Meet the knowledge compiler, a brilliant tool that transforms your messy, raw sources into an organized, interlinked wiki. Inspired by modern AI patterns, this tool processes your documents to extract core concepts and automatically generates a structured, browsable archive. It uses a smart two-phase pipeline to resolve links and keeps your wiki fresh with incremental updates. Even better, your query answers can be saved as new pages, allowing your collective knowledge to compound over time. Stop searching and start building your own persistent, intelligence-driven knowledge base today.

📰 https://news.ycombinator.com/item?id=47662274

🆔 @hackernewsgithubprojects

📦 milisp/codexia

Take Control of Your AI Coding Agents with Codexia

Struggling to manage your AI coding agents? Meet Codexia, a powerful workstation designed to supercharge your development workflow. This tool acts as an all-in-one hub for the Codex CLI and Claude Code, providing a polished interface for your terminal-based agents. You can easily manage complex tasks with its built-in scheduler, handle multiple git worktrees, and gain remote control via a headless web server. It even features skills management and IDE-like file editing, making your AI interactions seamless and organized. If you want to take total control of your AI-assisted coding environment, check out Codexia and level up today.

📰 https://news.ycombinator.com/item?id=47670101

🆔 @hackernewsgithubprojects

📦 addyosmani/agent-skills

Supercharge Your AI Coding Agents

Want your AI coding agent to actually get things done like a pro? You need to check out these production-grade engineering skills designed to take agents beyond basic tasks. Instead of simple scripts, this project focuses on robust capabilities like automated terminal command execution and precise file system navigation that actually work in real world workflows. By implementing these advanced patterns, you stop dealing with flaky AI output and start building reliable coding partners that handle complex tasks with confidence. It is a fantastic resource for leveling up your development projects, so start integrating these smart skills to supercharge your automation today.

📰 https://news.ycombinator.com/item?id=47670950

🆔 @hackernewsgithubprojects

📦 gitfrog1111/badclaude

Whip Your AI Into Shape with BadClaude

Ever feel like your AI is moving too slowly and you just want to get things done faster? Meet a hilarious new tool designed to spice up your workflow when performance hits a wall. This repository provides a quirky desktop overlay that lets you literally whip your AI when it gets stuck. By clicking a tray icon, you can send a system interrupt command along with one of five encouraging messages to snap the process back to attention. It is a creative, tongue-in-cheek way to handle unresponsive tasks. Give it a try if you need a little humor.

📰 https://news.ycombinator.com/item?id=47670138

🆔 @hackernewsgithubprojects

📦 kitfunso/hippo-memory

Stop Letting Your AI Forget: Meet Hippo Memory

Are your AI agents forgetting everything between sessions? Most memory solutions just store everything, turning your context into a cluttered mess. Hippo Memory changes the game by using biologically-inspired mechanisms to manage intelligence. It features intelligent decay so outdated information fades, retrieval strengthening to keep important lessons fresh, and smart consolidation to compress episodes into stable semantic patterns. With zero dependencies, it seamlessly integrates with tools like Cursor and Claude Code, automatically capturing errors from your git commits. Stop building a filing cabinet and start building a brain. Take control of what your AI agents remember today.

📰 https://news.ycombinator.com/item?id=47667672

🆔 @hackernewsgithubprojects

📦 sumant1122/perfmon

Build Your Own Terminal Dashboard with Perfmon

Are you tired of cluttered terminal windows when trying to keep an eye on your system health? Meet Perfmon, a modern and lightweight performance monitor designed specifically for your terminal. Built with Go and the Bubble Tea framework, this tool consolidates diagnostic data into a sleek, tabbed interface that eliminates chaos. You can even customize it using a simple configuration file to run your own shell commands. Whether you need real-time sparklines for CPU usage or a organized view of network connections, Perfmon makes monitoring effortless and visually satisfying. Try it out to take full control of your system dashboard.

📰 https://news.ycombinator.com/item?id=47649701

🆔 @hackernewsgithubprojects

📦 karpathy/karpathytalk

Build Your Own Open Social Network with KarpathyTalk

Ever wish social media was built for builders instead of walled gardens? Check out KarpathyTalk, an open-source project that blends the familiar feel of Twitter with the utility of GitHub Gists. It solves the problem of data silos by keeping everything accessible as simple markdown and JSON for both humans and AI agents. Built in Go, it features a lightweight SQLite database and HTMX for interactivity, allowing you to easily host your own community platform. It is a fantastic experiment in creating a truly open social space, so dive in, host your own instance, and start building today.

📰 https://news.ycombinator.com/item?id=47671718

🆔 @hackernewsgithubprojects