📦 priveetee/typetype

Take Control of Your Video Feed with TypeType

Tired of invasive tracking and algorithm fatigue? Meet TypeType, a powerful, self-hostable platform designed to give you privacy while watching your favorite content. It lets you stream videos from YouTube, BiliBili, and NicoNico all in one clean, customizable interface. By running the full stack locally, you maintain total ownership over your subscriptions, history, and playlists. It handles everything from proxying media to generating DASH manifests for smooth playback, all while keeping your data under your control. Whether you want to escape platform tracking or just organize your viewing experience, TypeType is the ultimate tool for your own video library.

🆔 @hackernewsgithubprojects

📦 maximecb/bebelm

Run LiquidAI's LFM 2.5 on Your CPU with Pure Rust

Ever wanted to run a powerful language model without needing an expensive GPU? This repository offers a pure Rust, CPU-only implementation of LiquidAI's LFM 2.5 8B model. By focusing on a highly optimized, dependency-free design, it allows you to run this capable model at interactive speeds using only your computer's standard processor. The project includes a custom command-line interface for chat and text completion, and it even supports advanced features like tool calling, all while maintaining a compact codebase. Whether you are a developer or an enthusiast, it is a fantastic way to experiment with local AI today.

🆔 @hackernewsgithubprojects

📦 yizhiyanhua-ai/fireworks-tech-graph

Stop Drawing Diagrams! Generate Professional Tech Visuals Instantly

Stop wasting hours drawing technical diagrams by hand. This repository lets you generate production-ready SVG and high-resolution PNG diagrams simply by describing your system in plain English or Chinese. It supports fourteen diagram types and offers eight distinct visual styles, ranging from clean blueprints to professional dark terminal aesthetics. It even handles complex AI and agent-based architecture patterns like memory layers and tool call flows automatically. With built-in semantic shape vocabularies and automatic export options, you can create polished, publication-quality visuals in seconds. Stop clicking through GUIs and start turning your system descriptions into clear, beautiful technical documentation today.

🆔 @hackernewsgithubprojects

📦 agricidaniel/claude-seo

Supercharge Your SEO with Claude Code

Unlock the power of automated search engine optimization by integrating this comprehensive plugin directly into your workflow. Claude SEO acts as a universal skill set for Claude Code, featuring twenty-five specialized sub-skills and eighteen automated agents that work in parallel to audit your websites in minutes. Whether you are tackling technical SEO, E-E-A-T standards, schema markup, or AI search optimization, this tool delivers prioritized, evidence-based action plans. It replaces tedious manual audits with professional-grade analysis, helping you spot critical issues that standard tools often miss. Transform your SEO strategy today by putting intelligent, automated agents to work for your digital projects.

🆔 @hackernewsgithubprojects

📦 freedomintelligence/openclaw-medical-skills

Unlock Advanced Medical AI With OpenClaw Skills

Imagine having an entire library of advanced medical artificial intelligence capabilities at your fingertips. The OpenClaw medical skills repository is a massive open-source collection designed to power intelligent agents with specialized knowledge. Whether it is drug discovery, protein optimization through tools like AlphaFold, or performing complex genomic data analysis, this project organizes highly technical tasks into usable modules. It bridges the gap between raw data and actionable research, making sophisticated biotech workflows accessible for automated systems. Explore this extensive resource to see how you can elevate your own medical AI projects and streamline complex scientific investigations.

🆔 @hackernewsgithubprojects

📦 danieldev23/trafexia

Master Mobile App Traffic Interception with Trafexia

Struggling to debug or analyze the hidden network traffic inside your mobile apps? Meet Trafexia, a powerful desktop application built to simplify HTTP and HTTPS traffic interception for developers and security researchers. By functioning as a proxy, it allows you to capture, monitor, and manipulate live requests from your mobile devices with ease. Whether you need to bypass SSL pinning, mock API responses, or simulate network throttling, this tool offers a comprehensive suite of features to streamline your debugging workflow. It is an essential, user-friendly workspace for anyone looking to get under the hood of their mobile applications today.

🆔 @hackernewsgithubprojects

📦 dmae97/open-multi-agent-kit

Take Control of Your Coding Agents with Open Multi-Agent Kit

Are you struggling to manage multiple coding agents efficiently? The Open Multi-Agent Kit acts as a powerful, provider-neutral control plane that streamlines your entire development workflow. It allows you to seamlessly route runtimes, scope specific tools, and run directed acyclic graph workers directly from its command line interface. Whether you need to verify evidence or replay complex agent runs, this kit provides the oversight you need to maintain project integrity. It is an essential tool for developers looking to bring order to their agentic systems. Try it out to see how much control you can reclaim today.

🆔 @hackernewsgithubprojects

📦 apodexai/agentharness

Test Your AI Agents with AgentHarness

Ever wonder how to reliably measure if your AI agent is actually performing well on deep research tasks? Meet AgentHarness, an open-source evaluation tool designed to test models like Apodex using a standard ReAct approach. It solves the headache of complex testing by running every single question in its own isolated subprocess. This ensures your benchmarks are stable, reproducible, and easy to debug without worrying about performance bottlenecks. Whether you are running smoke tests or full-scale evaluations, this repository provides a clean, structured way to aggregate accuracy and track progress. Start benchmarking your AI agents with precision today.

📰 https://news.ycombinator.com/item?id=48463157

🆔 @hackernewsgithubprojects

📦 gitbutlerapp/grit

Rebuilding Git from Scratch in Rust

Ever wondered how Git works under the hood? Meet the project aiming to reimplement Git entirely in Rust. This ambitious effort replaces standard Git components with modern, memory-safe code to push the boundaries of version control performance. By building foundational tools like object hashers, reference handlers, and even a custom HTTP server, this project acts as a functional recreation of the Git ecosystem. Whether you are curious about systems programming or the mechanics of version control itself, exploring this codebase offers a unique look at how core development tools are engineered from the ground up. Go check it out.

📰 https://news.ycombinator.com/item?id=48486380

🆔 @hackernewsgithubprojects

📦 gen-verse/openclaw-rl

Train Your AI Agent Just By Talking With OpenClaw-RL

Tired of AI agents that never learn from your feedback? OpenClaw-RL is a powerful, fully asynchronous reinforcement learning framework that lets you train personalized AI agents simply by talking to them. Instead of relying on static datasets, this system intercepts your live conversations, terminal executions, or GUI interactions to create training signals on the fly. It uses advanced techniques like Binary RL and On-Policy Distillation to continuously refine the agent's behavior without ever blocking your workflow. Start using your daily interactions to build a smarter, more personalized AI assistant today, and watch your agent evolve with every single message.

🆔 @hackernewsgithubprojects

📦 sylinko/everywhere

Meet Everywhere: The On-Screen Aware AI Assistant

Stop toggling between apps and start automating your workflow with a smart desktop companion that sees what you see. This project provides an on-screen aware AI assistant that analyzes your current application context to help you work seamlessly across your computer. By leveraging multiple large language models and integration tools, it solves the problem of disconnected workflows by bridging the gap between your active tasks and AI assistance. It features a sophisticated strategy engine for intelligent query matching and handles native desktop interactions, allowing you to stay focused on what truly matters for your productivity goals.

🆔 @hackernewsgithubprojects

📦 nv-tlabs/wosx

Solve Complex Physics Without Meshes Using WoSX

Struggling with complex volume meshes for your physics simulations? Meet WoSX, a powerful C++ library designed to solve partial differential equations using grid-free Monte Carlo methods. Instead of the costly and tedious process of creating volume meshes, this tool queries geometry boundaries directly to estimate solutions exactly where you need them. Whether you are tackling thermal conduction on intricate meshes, modeling electrostatics for moving components, or calculating exterior potential flow, WoSX offers robust CPU and GPU solvers to get the job done. It is a fantastic resource for researchers and developers looking to streamline advanced geometric simulations today.

🆔 @hackernewsgithubprojects

📦 mit-han-lab/foreact

ForeAct: Smarter Robot Decision Making

Ever wonder how robots can make better decisions on the fly? Meet ForeAct, a powerful visual foresight planner designed to help Vision-Language-Action models look ahead. By predicting future observations, it empowers robots to anticipate outcomes and act more effectively without needing complex architectural changes to their existing models. It is impressively fast, generating high-fidelity visual foresight in just a fraction of a second on a single GPU. Whether you are working with single or multi-view setups, this plug-and-play solution offers a smarter way to bridge the gap between perception and action. Try it to elevate your robotics projects.

🆔 @hackernewsgithubprojects

📦 28naem-del/mnemosyne

Stop AI Amnesia: The Cognitive Memory OS for Agents

Are your AI agents stuck with amnesia, starting every conversation from zero? Meet Mnemosyne, a breakthrough cognitive memory system designed to act like a human brain for your AI. Instead of standard database wrappers, this project delivers a powerful five-layer architecture that enables persistent, self-improving, and collaborative memory across multiple agents. With its 12-step algorithmic pipeline, you can store and retrieve memories in under fifty milliseconds without expensive LLM calls. From automatic entity extraction to real-time knowledge graphs, Mnemosyne gives your agents the long-term context they need to truly evolve. Take control of agent intelligence and start building smarter today.

🆔 @hackernewsgithubprojects

📦 alibaba-damo-academy/worldolympiad

Is Your AI Model Actually Smart? Meet WorldOlympiad

Think your video-generation AI is a genius? Most models just fake it with pretty pixels, but WorldOlympiad puts them to the ultimate test. It is a new benchmark that treats AI like a top-tier athlete, grading models on three tough tracks: physical rules, geometric consistency, and interaction fidelity. Instead of just checking if a video looks good, it dives deep into mechanics, thermal properties, and 3D structure to see if the world model truly understands reality. By stress-testing these systems with gaming and robotics, it exposes where your AI is actually struggling. Ready to see if your model survives?

🆔 @hackernewsgithubprojects

📦 wdrink/arm

ARM: A Revolutionary Unified Multimodal AI Model

Have you ever wondered if one single AI model could master image understanding, generation, and editing all at once? Meet ARM, a cutting-edge autoregressive model that treats visual data like language. By mapping images into compact discrete tokens, ARM uses next-token prediction to unify these diverse tasks into one efficient framework. It significantly boosts performance through preference optimization, proving that a single model can handle complex visual reasoning and high-quality generation simultaneously. This approach simplifies multimodal AI, showing that autoregressive models can effectively dictate composition and semantics. It is an exciting step forward for unified artificial intelligence research.

🆔 @hackernewsgithubprojects

📦 zlab-princeton/i1

i1: A Fully Open Recipe for Strong Text-to-Image AI

Ever wonder how powerful text-to-image AI is actually built? Most top-tier models keep their training data and recipes secret, making it nearly impossible for the research community to learn from them. The i1 project changes that by offering a fully open, high-performance 3B-parameter diffusion model. By running over three hundred controlled experiments, the team identified the best design choices for both architecture and data. The result is a competitive model that you can fully explore, reproduce, and build upon. Check out their codebase to see how these simple, effective recipes can advance the future of open-source image generation.

🆔 @hackernewsgithubprojects

📦 orchestra-research/ai-research-skills

Supercharge Your AI Agents with This Massive Research Skills Library

Stop wasting time debugging infrastructure and let your AI take the lead on complex research. This repository provides a massive collection of nearly one hundred expert-level skills designed to turn AI models into fully autonomous research agents. Whether you need to handle distributed training with PyTorch, optimize models with vLLM, or write academic papers using provided LaTeX templates, this library covers the entire research lifecycle. By packaging these capabilities, you enable your agent to manage everything from initial ideation and data processing to final evaluation. Unlock the true potential of your AI agents and accelerate your scientific discovery today.

🆔 @hackernewsgithubprojects

📦 s0xdk/ghostty-blackhole

Turn Your Terminal Into A Black Hole Pomodoro Timer

Want to add a touch of cosmic drama to your coding workflow? This project brings a stunning, interactive black hole directly into your Ghostty terminal, acting as a clever visual Pomodoro timer. As you work, the hole slowly grows, warping your terminal text with realistic gravitational lensing, event horizons, and accretion disks. When the hour peaks, it signals that it is time for a break. It is entirely self-contained, using clever shader math to track your focus based on the wall clock and your typing activity. Transform your boring terminal into a dynamic, engaging workspace today.

🆔 @hackernewsgithubprojects

📦 serenakeyitan/awesome-agent-loops

Stop Prompting, Start Looping: Automate Your Coding Agent

Are you still manually prompting your coding agent one step at a time? It is time to level up by using agent loops to get more done with less effort. This repository is a curated collection of powerful, real-world commands for Claude Code and Codex that help you automate repetitive tasks. Whether you need to fix flaky tests until they pass, babysit pull requests, or sync documentation automatically, these commands put your work on autopilot. Simply copy and paste these proven patterns to create your own effective loops. Start building smarter workflows today and let your agent handle the grind.

🆔 @hackernewsgithubprojects

📦 nelson820125/jordium-gantt-vue3

Build Powerful Gantt Charts with Vue 3

Need to manage complex schedules and resource planning in your web app? Check out this powerful Vue 3 Gantt chart library. It simplifies task management by providing a flexible, interactive interface for scheduling tasks and monitoring resource allocation. With built-in features like drag-and-drop, customizable task bars, and even resource conflict detection, it helps you visualize timelines effortlessly. Whether you are building project management tools or resource trackers, this component is designed to handle it all with ease. Dive into this repository to streamline your project scheduling workflow today and bring professional-grade Gantt charts directly into your application.

📰 https://news.ycombinator.com/item?id=47437651

🆔 @hackernewsgithubprojects