142 subscribers
10.2K videos
10.8K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ andymatuschak/interactive-transcripts

Interactive Transcripts: Edit Audio Like Text

Your audio files just became editable text inside Obsidian. The plugin called Interactive Transcripts turns raw audio into a living transcript where you can literally delete a sentence and the audio skips that part, just like cutting a video. It runs everything locally on your Mac, so your private meetings stay private while you fix typos or trim rambles. The coolest part is that it keeps the timing in sync, so clicking any word jumps the audio to exactly that moment. This is a massive win for podcasters and researchers who hate switching between text editors and video software.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ sdli1995/dlssg_for_sm86

DLSSG SM86 for RTX 30 Series

Give your RTX 30 series GPU the same AI frame generation tech that newer cards enjoy. This project, called DLSSG SM86, injects a special file into your games to enable DLSS Frame Generation on hardware that officially lacks support. It works by swapping in a compatible version of the technology so your graphics card can create extra frames between real ones, effectively doubling or even tripling your frame rate. In tests, this turned a sluggish fifty frames per second in Black Myth Wukong into a smooth one hundred and fifty.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ nityeshaga/claude-home-base

Claude Home Base: Your Mac Is Now A Coworker

Your Mac can now act as a living teammate that writes its own diary every night. The project, named Claude Home Base, turns an idle computer into a dedicated AI coworker that lives inside your Slack workspace. It does not just answer questions; it develops a personality, reviews its daily interactions, and refines its own identity over time. You set it up once, and it runs in the background, handling tasks and keeping a personal log of its thoughts. It is not a chatbot you query; it is a partner that grows with your team.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ straff2002/openglasses

OpenGlasses turns smart glasses into your personal AI

OpenGlasses turns your Meta Ray-Ban smart glasses into a hands-free AI assistant that actually sees what you are looking at. Instead of just taking photos, you can ask it to identify equipment, translate live conversations, or read signs right in front of you, all without touching your phone. The coolest part is that you can run it entirely offline on your iPhone using local AI models, meaning your private data never has to leave your pocket. It also lets you plug in your own custom knowledge bases, so the glasses can answer specific questions about your work or health data.

πŸ“° https://news.ycombinator.com/item?id=48304298

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

Mooziac: The macOS Menu Bar Music Player

Turn your Mac trackpad into a musical control deck. Mooziac is a sleek menu bar app that turns the right edge of your trackpad into a volume slider and lets you skip tracks by tapping the corners. It plays local files and syncs your YouTube Music library, displaying real-time lyrics right under your menu bar. The most surprising part is how deeply it integrates with Apple hardware, giving you tactile haptic feedback as you adjust the volume. It is lightweight, private, and keeps your music local. If you want a music player that feels like a native part of your Mac, this is the one to try.

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

Dream Loop: AI that Builds Games to Match a Dream

Take a picture of a fantasy world and watch an AI build a playable game that looks exactly like it. Dream Loop is a special skill for coding agents that creates a perfect visual loop. First, the AI dreams up a stunning target image. Then, it writes code to build that scene. A separate AI critic compares the live result to the dream and gives detailed feedback. The builder then fixes every tiny gap until the screen matches the image pixel by pixel. This is fascinating because it forces AI to self-correct until it hits a perfect visual target. It turns vague descriptions into high-fidelity graphics.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ chr0nzz/traefik-manager

Traefik Manager: Stop Editing YAML

Traefik Manager turns the nightmare of manually editing reverse proxy configuration files into a clean, self-hosted dashboard where you can actually see what you are doing. The core problem it solves is that setting up traffic routing usually means staring at dense text code, which is terrifying if you just want to know if your website is up and running. This project gives you a visual interface to manage routes, security certificates, and traffic rules without ever touching a terminal, effectively acting as a safety net so you do not accidentally break your server.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ saganaki22/comfyui-audiosr

ComfyUI AudioSR: AI Audio Upscaling

Turn any low-quality sound file into a crisp, high-definition track using a tool called ComfyUI AudioSR. This project solves the common problem of muffled, compressed recordings by using a deep learning model to generate missing high-frequency details. It works like a magical filter that listens to your audio and reconstructs the clarity lost during compression or low-resolution recording. You can drag any file into the interface, and it outputs a clean version at forty-eight kilohertz, making old recordings sound professional instantly. It is perfect for creators who want to upgrade their audio assets without expensive studio equipment.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ kulkarnirohit123/cra-agent

CRA Agent: The AI That Fixes Its Own Code

CRA Agent actually writes the code to fix your own security vulnerabilities and opens a pull request for you. It is an autonomous system built to handle the strict cybersecurity rules of the European Union. It watches your code repository and scans every new change for hidden problems. When it finds something risky, it doesn't just send a warning. It uses artificial intelligence to figure out the best fix. Then it opens a ticket in your project tracker and provides the actual code to solve the issue. It turns a heavy compliance burden into a simple, automated loop. You just review the final result.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ shirleymaxx/rest3d

Rest Three D: Real Physics from One Photo

Turn a single casual photo into a physically stable interactive three dimensional scene. That is exactly what Rest Three D does. Developed at Carnegie Mellon University, this tool solves a major problem in computer graphics: making digital worlds that actually obey gravity. Instead of just guessing shapes, it reconstructs objects and then runs them through a real physics simulator to ensure they sit correctly without floating or falling over. This creates a fully interactive environment you can explore in your browser. It is a fascinating leap from static images to living digital spaces that make sense.

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

Multivibe: The Smart AI Gateway

Route your AI traffic through Multivibe, a free self-hosted gateway that acts as a smart switchboard for your coding agents. It solves the annoying problem of juggling multiple provider accounts by automatically balancing their usage limits and failing over to a healthy one when you hit a cap. Think of it as a central hub that connects to various AI services, letting your tools talk to them seamlessly without you managing the complex details. You get a clean endpoint that handles the messy parts of rate limits and account rotation so you can focus on building.

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

Wallfacer: The AI Engineer That Writes Its Own Specs

Wallfacer is the autonomous engineering platform that writes its own specs before writing a single line of code. It solves the chaos of managing multiple AI coding agents by turning vague ideas into structured plans, tasks, and verified code. The standout feature is its spec-driven workflow, where the system breaks down your requirements into a living document that tracks progress and prevents the AI from guessing. You can grant it full autonomy for trusted tasks or keep strict control over every step. It’s a powerful way to manage complex software projects without losing sight of what the AI is actually doing.

πŸ“° https://news.ycombinator.com/item?id=47315713

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

Tortie: The Calm Home for Your AI Agents

Tortie is the calm agent multiplexer that finally makes running multiple AI coding assistants feel like using a normal editor. If you are juggling separate terminals, scattered chat windows, and manual context switching, this tool brings it all into one quiet, unified space on your Mac. It wraps your favorite agents with familiar IDE features, like file trees and git integration, so you stop staring at raw command lines. The coolest part is how it handles session persistence, meaning your work survives even if your machine crashes or you close the app. It is less about flashy new features and more about giving your coding agents a stable, predictable home.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ xcjy8bao/baoer_signal_grep

Baoer Signal Grep: The Librarian for AI Code

Stop letting your AI coding agent drown in messy file dumps. Baoer Signal Grep acts like a patient librarian, guiding your agent to find exact text passages without opening every single folder in your project. It uses a stable cursor system to keep your place, so you can easily pick up where you left off without losing context. The coolest part? It handles fuzzy searches by combining exact keyword matches with a local semantic model, so even if you remember a sentence slightly wrong, it still finds the right spot. No more guessing which file has the answer you need.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ zenstory-ai/oh-story-dsh

Oh Story: From Novel to Short Drama

Turn raw novel text into fully produced short dramas without writing a single line of code. This repository is a specialized toolkit that automates the entire pipeline from analyzing a story to generating actual video prompts and sound design. It handles the heavy lifting of character consistency, shot composition, and even specific visual styles like ink-wash or 3D animation. You feed in a book, and it breaks down the plot into professional screenplays and technical instructions for AI media generators. It is essentially a digital film crew that ensures your story looks coherent on screen.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ x-square-robot/x2streaming-tts

X2Streaming-TTS: Speak Before The Text Is Done

X2Streaming-TTS is the text-to-speech engine that starts speaking before the sentence is even finished. Usually, AI waits for a complete sentence to sound natural, which creates noticeable delays in real-time conversations. This project solves that by listening to the text as it arrives and making permanent decisions about pronunciation immediately. It never takes a word back, so if it says a number wrong, it stays wrong. To make this safe, it uses a clever trick called causal commitment. It waits just long enough to know if a number is a quantity or a rank, then locks in the correct sound.

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

TileLang: Write Python, Get GPU Speed

TileLang is the programming language that lets you write GPU code in Python. It solves the headache of writing fast, low-level hardware kernels by letting you use familiar Python syntax, while a compiler underneath automatically handles the complex, low-level optimizations. It is perfect for building high-speed matrix math and attention operations without needing to manually manage every hardware detail. Just describe your logic in plain Python, and it compiles directly to top-tier performance on Nvidia, AMD, and Apple hardware. It is a genuinely clever way to get serious speed without the usual hardware headache.

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

How WebCodex Gives AI Agents Your Real Dev Environment

WebCodex is the bridge that lets AI agents code on your actual machine instead of a cloud sandbox. Most AI coding tools require you to upload your project, but WebCodex flips that script. It runs locally on your computer and connects securely to chat assistants like ChatGPT or Claude. This means the agent can read your files, run your real tests, and use your specific Git setup without ever copying your data to a third-party server. Your code stays exactly where it is, while the AI gets full access to your local toolchain. It is a powerful way to keep your development environment private and intact.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ edge0-ai/edge0

edge0

edge0 is the inference framework that runs massive language models directly from your solid-state drive without needing massive amounts of random access memory. Instead of loading the entire model into your computer's fast memory, it streams specific parts from the drive only when needed, which keeps your device running cool and efficient. It achieves this by predicting which parts are needed next and loading them in the background so the computer never has to wait. This means you can run powerful AI locally on standard consumer hardware like a Mac mini, making advanced technology accessible to anyone without a data center.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ open-science-ledger/how-to-train-your-slop-cannon

How to Train Your Slop Cannon: LLM Guide for Scientists

Turn your chatbot into a rigorous research partner by fixing how scientists actually use large language models. The project called How to Train Your Slop Cannon tackles the messy reality that AI writes plausible nonsense at an industrial scale. This short guide stops you from blindly trusting the text and shows you how to verify everything. The coolest part is using structured proof formats to break big claims into tiny, checkable sub-claims. This stops the model from just hallucinating answers and forces it to show its work. It also explains why your model keeps forgetting context or agreeing with you just to be nice.

πŸ“° https://news.ycombinator.com/item?id=49600045

πŸ†” @hackernewsgithubprojects