181 subscribers
11.4K videos
12K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ zbndev/tidemark

Tidemark: Know When Your AI Quota Resets

Tidemark keeps watching your AI service limits in the background, even when the app window is closed, so your desktop tray always shows exactly how much credit you have left. It solves the annoying mystery of hitting a hard stop in the middle of a long task by clearly showing when each rate limit window resets. The tool draws a small marker on every progress bar that tells you instantly if your current usage pace will finish before that reset time or if you are about to run out. It is built in native Rust, so it runs quietly and uses very little memory compared to heavy web-based apps.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ ahren09/scienceutopia

Science Utopia: AI Simulates Science

Science Utopia uses large language models to simulate entire scientific communities, where AI agents act as researchers choosing projects, writing papers, and peer-reviewing each other's work. The project solves the problem of how to study the complex dynamics of research without waiting decades for real-world results. It is useful for anyone curious about how funding incentives and review policies shape scientific progress, allowing users to run configurable experiments on how these rules affect outcomes over time.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ google-ai-edge/ml-drift

Run Big AIs On Your Phone

Run massive language models directly on your phone or browser without sending data to a server. This is the big idea behind ML Drift, a new engine from Google that makes heavy AI work feel instant on your own hardware. The coolest part is how it builds custom math instructions right on the fly for your specific chip, squeezing huge models into tiny devices. It is basically the next step for private, offline intelligence. You get real-time answers while keeping your data safe and your battery alive. No cloud required. Just you and your device thinking fast.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ aivrar/vllm-windows-build

Run vLLM on Windows without Linux

Run high-performance language model servers directly on Windows without ever touching a virtual machine or container. This project builds the popular VLLM inference engine natively for Windows, so you can skip the usual Linux workarounds entirely. It takes the standard software and fixes it to run smoothly on your native system, giving you fast, local AI serving with full graphics card acceleration. You get a simple installer and a pre-built package that just works, making it easy to test and deploy models on your desktop or laptop. No more fighting with compatibility layers or complex setups. Just download, install, and start generating text.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ caldalis/minicpm-math-harness

Run a Math Proof Swarm on Your Laptop

MiniCPM Math Harness runs a swarm of artificial agents on your laptop to verify mathematical proofs without massive hardware. It uses a compact model to spawn parallel provers that attack problems with different strategies, ensuring they don't make the same mistake twice. The system then uses adversarial verifiers and executes brute-force Python scripts to check the math, settling disagreements with hard evidence rather than guesswork. This turns a single small model into a rigorous proof checker you can run locally. It is a fascinating look at how test-time compute can boost accuracy on everyday hardware, proving that you don't need a data center to do serious math reasoning.

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

MCP Safari: Your AI Agent Finally Has Eyes in Safari

Let your AI agent drive your actual, logged-in Safari on Mac. MCP Safari connects your favorite AI assistants to the real browser session you already use. No headless Chrome, no separate login windows. It operates your live tabs, preserving your cookies and session history, so your agent can test forms, click buttons, and read pages exactly as your users see them. Built with Swift and a native Safari extension, it bridges the gap between modern AI tools and the reliable, familiar interface of Safari. It’s not a new browser; it’s a direct line into the one you already trust.

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

Rec-Rs: The Lightweight Rust Screen Recorder

A screen recorder built in Rust can stream and record in forty percent less space than the industry standard while using barely any power. Rec-Rs captures your Mac's screen, microphone, and webcam directly from the hardware, skipping the heavy software layers that slow down traditional tools. It sends that raw feed straight to your graphics card for encoding, which means your computer stays cool and your battery lasts longer. The result is a tiny, fast app that handles live streams and high-quality recordings without bogging down your system. If you want a recording tool that respects your machine's speed and energy, this is the one to try.

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

HybridAgent: Thinking You Can See

Watch a language model think in plain text you can actually read. HybridAgent, created by researchers at Stanford and Together AI, lets a large language model switch between fast, private inner thoughts and normal written answers. The most surprising part is that you can look inside its head. Instead of a black box, the system renders its internal reasoning as readable words, showing exactly how it uses tools like search or a calculator to solve a problem. You get to see the step-by-step logic before it gives the final answer. This makes artificial intelligence far easier to trust and understand.

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

Find Any File on Your Mac in Milliseconds

Stop waiting for slow search results on your Mac. Oil Find gives you instant file search by keeping a fast, in-memory map of every name on your disk. Instead of hunting through folders, you press a shortcut and results appear as you type. It uses clever coding to scan millions of files in milliseconds, even catching live changes in real time. This tool turns a chaotic computer into a neat, organized library, letting you find that one file you forgot exists in a blink. It is free, open source, and works entirely on your machine without sending data anywhere.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ earendil-works/pi-durable-cloudflare

Pi Durable Cloudflare

Pi Durable Cloudflare is the durable web app that lets you fork conversations like branches of a story. It runs on Cloudflare so you can open the same chat in multiple browsers, see who is typing, and jump back to an earlier message to start a completely different path without losing the original. If your internet drops or you close your laptop, your place is saved exactly where you left it. This is a working example of how to build resilient, multiplayer AI experiences that survive restarts. Try it out to see how state persistence changes the way we chat with machines.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ oaslananka/kicad-mcp-pro

KiCad MCP Pro

Artificial intelligence can now inspect and modify real printed circuit board layouts right inside open source engineering software. KiCad MCP Pro connects intelligent digital assistants directly to electronic design workflows, letting them run error checks, analyze parts lists, and generate manufacturing files. This bridges the gap between conversational models and physical hardware creation, keeping humans in complete control of every final edit before production. It turns tedious design verification into a fast, cooperative conversation that helps bring hardware ideas to life safely.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ dsh-tauri/deepseek-harness-desktop

deepseek-harness-desktop

Run complex artificial intelligence workflows directly on your computer without installing background programming tools or managing server containers. The deepseek-harness-desktop application packages everything into an eight megabyte installer, so you can open a native program and start working right away. It bundles ready-to-use add-ons for scheduling tasks, controlling sessions remotely, and running automated helpers across operating systems like Windows, Linux, and Mac. Having all these capabilities integrated into a single lightweight desktop app means you avoid messy terminal configurations entirely. It gives developers a straightforward way to harness powerful model automation tools locally with zero initial environment setup.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ lovisdotio/motion2code

Motion2Code: Turn Video Into Editable Code

Turn any motion design video into a crisp, looping animation you can actually edit. The open source project, called Motion2Code, gives coding agents a superpower. Instead of guessing how a clip looks, they analyze every frame and rebuild the animation using clean vector shapes and precise timing. The result is a tiny file, just tens of kilobytes, that stays sharp at any resolution, from your phone to a massive billboard. You can tweak colors, change text, or adjust the speed in seconds. This is the perfect fix for those annoying, heavy video files that nobody can modify. Your AI coder finally has eyes, so it can match the source perfectly.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ zipengwu365/tomc

TOMC

TOMC is the task memory system that compiles long project histories locally on your processor without needing extra model fees or network services. It takes your conversation logs, active goals, and budget limits, then extracts key state, decisions, and constraints into a plain text summary ready for your next request. You can save notes in one coding assistant, switch over to another tool on the same machine, and recall the exact same context to continue working right where you left off. TOMC gives you a simple, reliable way to organize project memory across all your developer tools.

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

Velocity: Self-Hosted Map and Replay Platform

Velocity is the self-hosted live map that automatically saves complete tracking history directly to your own storage. Free flight and ship tracking services constantly limit how far back you can look, but Velocity pulls from public feeds and logs every single position straight to your local drive. This means you can easily use a simple time scrubber to rewind the map to any past moment and inspect recorded contacts across the globe without paying for extra tiers. With no mandatory account creation or API keys required, it provides a private, independent archive of global movement that stays fully under your control forever.

πŸ“° https://news.ycombinator.com/item?id=48867980

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ jms1717/ming-voice

Talk to Your Computer, Not the Cloud

Have a voice assistant that actually lives on your own computer. Ming Voice is a local speech-to-speech system that runs entirely on your AMD or Nvidia graphics card, meaning your private conversations never leave your house. The coolest part is how it handles the silence between your words. It uses a smart turn-detection model to listen to your intonation and figure out when you are actually finished thinking, rather than just cutting you off after a set number of seconds. This creates a conversation that feels surprisingly human, with a delay of only about a quarter of a second.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ scrapernode/awesome-n8n-templates

Awesome n8n Templates

Automate complex digital tasks instantly by importing pre-built automation workflows into your software. Awesome n8n Templates brings together over thirteen thousand ready-to-use blueprint files covering twenty-five distinct categories. Instead of building multi-step automations from scratch, users can simply drop a single file into their workflow engine. The collection features popular setups for building artificial intelligence chatbots, converting raw web data into summaries, and scheduling content directly across social platforms. It turns hours of custom integration work into a simple copy-and-paste action, making advanced workflow automation accessible to anyone looking to streamline their daily tech routines.

πŸ“° https://news.ycombinator.com/item?id=47360101

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

Hibi: The One App for Everything You Write

One app now handles every writing format you have ever tried to organize. Hibi is a desktop application that unifies your notes, documents, and drafts into a single, flexible workspace. It solves the chaos of having different apps for Markdown, Typst, or Org files by giving you one editor that understands them all. You can switch between plain text, rich formatting, and even interactive diagrams without losing your flow. The coolest part is that it supports an addon system, meaning you can build custom tools for your specific workflow. It is built for people who think in text but want professional power. Stop juggling five different editors.

πŸ“° https://news.ycombinator.com/item?id=49782528

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

Chibil

Developers can now compile classic C code like PureDOOM directly into managed.NET Framework and modern.NET assemblies using a custom C compiler. Chibil rewrites the open-source chibicc compiler in C sharp to target.NET Intermediate Language. It compiles C source files into object files that can link with standard tools or its own linker to generate pure managed executables. Developers can step through C source code directly inside a.NET debugger, with full support for line numbers and local variables. Check out the Chibil repository today to see how standard C code can run natively inside the.NET runtime.

πŸ“° https://news.ycombinator.com/item?id=48346660

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

Endo: The Chat Interface for Multiple AI Agents

A single chat window is now the control center for multiple artificial intelligence agents working together. Endo is a web application that unifies different AI models into one cohesive conversation, allowing you to direct various agents from the same place. It solves the problem of switching between separate chat tabs by creating a shared space where these tools can collaborate on tasks, share context, and manage complex workflows. This unified approach keeps your work organized and makes it easier to see how different models contribute to a single goal. Think of it as a command deck for your digital assistants.

πŸ“° https://news.ycombinator.com/item?id=50110614

πŸ†” @hackernewsgithubprojects