56 subscribers
7.26K videos
7.86K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
📦 apple/ml-mmtoolsandbox

ml-mmtoolsandbox

AI assistants can now navigate complex visual interfaces just like humans, thanks to a benchmarking system developed by Apple. The project, called ml-mmtoolsandbox, lets developers evaluate how well visual AI agents can use over five hundred tools across sixteen different application domains. Instead of just reading text, these models have to look at images, process multi-turn conversations, and execute precise tool calls to solve tasks. It simulates realistic challenges like goal revisions and error corrections in real time. This tool makes it incredibly easy to see if an AI can actually manage a complex workflow without losing track of the visual details.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 oversecured/samsung_vulnerabilities

samsung_vulnerabilities

Peek behind the scenes of mobile security to see how preinstalled apps can compromise a phone. The samsung_vulnerabilities repository details a collection of one hundred and seventy-six security flaws discovered in factory-installed apps on Samsung devices. From settings bypasses to silent file access, it showcases real bugs found and fixed during a multi-year security collaboration. It is a goldmine for understanding how tiny oversights in system privileges can leave a device open to exploits. Check it out to see exactly how these security flaws work under the hood and level up your own defensive coding skills.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 xiyuzhai-husky-lang/visored

Visored

Write mathematical proofs in a natural, controlled language and let a computer automatically translate them into rock-solid code. That is what visored does by bridging the gap between human-readable math and formal logic. It takes intuitive mathematical arguments and transpiles them into incredibly detailed, machine-verified Lean code. Because the translation is so thorough, a short, forty-line human proof can expand into tens of thousands of lines of rigorous, step-by-step logic. It is basically a super-powered translator that makes formal math verification accessible without requiring you to write thousands of lines of manual code yourself.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 uipath/coder_eval

coder_eval

coder_eval is the testing gym that finally evaluates how effectively AI agents use your custom coding tools and command-line interfaces. Unlike standard benchmarks that only grade raw text output, this system runs full AI agents inside secure, isolated sandboxes to see how they handle real-world programming tasks. You define the exact challenges and success criteria in simple files, and the framework scores the agent from zero to one based on the actual code and file structures it generates. It is a brilliant way to continuously test models like Claude or Gemini in your build pipelines, ensuring they do not stop triggering key skills as the models receive updates. You get...

📰 https://news.ycombinator.com/item?id=48864900

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 sslnon/elf-s2t

elf-s2t

elf-s2t is the speech-to-text project that finally ditches discrete tokens for continuous diffusion. Most translation and transcription tools work by predicting text one word or token at a time, but this project treats speech-to-text as a continuous generation task. By combining a frozen Whisper model with a continuous text-embedding space, it processes audio and text in a single, smooth stream. This clever design completely sidesteps the need for complex cross-attention mechanisms, allowing the model to wait until the very last step to commit to actual words. It is a brilliant way to make speech translation more fluid and unified.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 android/skills

Android Skills

Improve how AI coding assistants write your Android code by giving them specialized, platform-approved instructions. The skills repository provides modular, markdown-based guides designed to ground large language models in tricky, specialized areas where they traditionally struggle, like complex camera setups, background performance, and Jetpack Compose transitions. Instead of relying on general training data, you can feed these precise templates directly to your AI tools to ensure they follow modern, error-free patterns. It is an easy way to get smarter, more accurate code generation. Grab these official resources to make your AI assistant a true Android expert.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 vercel-labs/just-bash

just-bash

This TypeScript package runs a fully simulated bash environment inside an in-memory virtual filesystem with absolutely zero external dependencies. It is built specifically for AI agents that need a secure space to run terminal scripts without putting the host computer at risk. Instead of spinning up heavy virtual machines, it acts as a sandboxed interpreter that parses and runs commands safely. It blocks path traversal attacks, restricts network access, and neutralizes dangerous terminal actions out of the box. It is the perfect lightweight solution for giving your AI tools terminal capabilities without compromising your system security.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 open-telemetry/semantic-conventions-genai

Semantic Conventions GenAI

Semantic-conventions-genai is the OpenTelemetry extension that finally brings standard, structured tracking to artificial intelligence applications. When you build with large language models, agents, or tools, figuring out why a request failed or where a bottleneck happened is incredibly difficult because every framework talks about data differently. This project solves that by defining a universal language for AI telemetry, mapping things like prompt versions, token counts, and memory operations into consistent metrics and events. The single most impressive thing it does is establish a strict, runtime-testable blueprint for tracking complex multi-agent workflows and tool executions. This means you can easily monitor your AI applications across different cloud providers and model families...

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 browser-act/skills

Skills

AI agents struggle with traditional web browsers because typical automation tools get blocked by bot detectors and cannot handle unexpected visual challenges. The open source project skills changes this by providing a specialized command line browser built from the ground up for artificial intelligence. If an agent gets stuck on a tricky verification screen, it generates a secure link allowing a human to take over from any device and click through the barrier before handing control back to the AI. It also outputs clean, indexed text instead of heavy code, making web navigation incredibly easy and cost-effective for language models.

📰 https://news.ycombinator.com/item?id=48946421

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 lukealonso/b12x

b12x

Supercharge your Blackwell GPU's performance by running ultra-fast language model inference with b12x. This specialized library delivers a highly optimized collection of deep learning kernels tailored exclusively for NVIDIA's SM120 and SM121 architectures, including the RTX 50-series and workstation cards. Written in the CuTe DSL, it delivers maximum execution speed for advanced operations like block-scaled matrix multiplication, sparse attention, and mixture-of-experts models. By compiling kernels lazily and freezing them before serving, it prevents runtime latency spikes. It is the ultimate tool for developers looking to extract absolute peak performance from next-generation desktop and workstation hardware.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 westpoint-io/lazyrsync

lazyrsync

Sync your files and backups safely without sweating over complex command line flags. This tool brings the safety of a graphical interface right to your terminal as a lightweight Rust application, making it perfect to use over SSH connections where normal desktop apps can't reach. You can save your transfers as reusable profiles and run an honest dry-run to preview exactly what will change with a visual diff before writing a single byte. It even puts destructive delete flags behind a confirmation gate so you never accidentally wipe your data. It is the ultimate terminal companion for stress-free file syncing.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 skyworkai/matrix-3d

Matrix-3D

Matrix-3D is the omnidirectional world builder that lets you generate massive, fully explorable 3D scenes from a single image or text prompt. Instead of rendering small, restricted objects, this tool produces complete 360-degree environments that you can freely walk through and inspect from any angle. It cleverly links panoramic video generation with advanced 3D reconstruction, meaning you can sketch a scene with words or photos, watch it expand into a cinematic tour, and then convert that path directly into an interactive 3D space. It is incredibly fun for anyone wanting to build custom, immersive digital worlds with absolute ease.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 gimi-xiaomi/gimi-illustration-skill

gimi-illustration-skill

gimi-illustration-skill is the open-source AI agent skill that transforms your written articles into beautiful, quirky hand-drawn illustrations. If you write blog posts, newsletters, or presentations, this tool automatically reads your Chinese text, analyzes the core ideas, and generates high-quality visual metaphors in a cozy sketch style. It supports a charming default character, a clean no-character mode, or you can even upload and lock in your own custom brand mascot. By handling everything from composition strategy to quality checks, it gives you perfectly framed, story-driven visuals that make your written ideas instantly shareable and easy to understand.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 capitalone/vulnhunter

VulnHunter

VulnHunter is an open-source security tool that thinks like an actual attacker to find real security flaws in your source code. Instead of acting like traditional scanners that flood your screen with fake warnings, it flips the script. It starts at public-facing entry points, like APIs or file uploads, and traces forward to see if a hacker could actually break in. It even uses a clever falsification engine to double-check itself, trying to disprove its own findings before bothering you. When it finds a real bug, it writes a proof-of-concept exploit, patches the code, and verifies the fix is safe.

📰 https://news.ycombinator.com/item?id=48942583

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 gintasz/unigent

Unigent

Unigent is the cross-harness SDK that finally lets you build stateful agent workflows using ordinary TypeScript. Instead of wrestling with complex frameworks or manual string parsing, you write simple functions and let the SDK automatically extract your TypeScript signatures to generate clean tool definitions. You can spin up conversational agents, effortlessly fork sessions to explore different paths simultaneously without duplicating context, and get strictly typed outputs directly from your models. There is even a live trace terminal inspector to watch your agents work in real-time. Give it a spin to build smarter, self-correcting automation scripts today.

📰 https://news.ycombinator.com/item?id=48947117

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 scrapfly/antibot-detector

antibot-detector

antibot-detector is the Chrome extension that reveals exactly how websites spy on your browser and block automated visitors. Instead of guessing why a page is blocking you or forcing a CAPTCHA, this tool works right inside your browser to intercept and expose security scripts in real time. It monitors everything from network requests and cookies to hidden JavaScript hooks that silently collect your canvas, audio, and hardware fingerprints. You get a clear confidence score showing which security networks are active on any page you visit. It is a brilliant way to understand modern web security and see how the sites you visit analyze your digital identity.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 fujacob/cotabby

Cotabby

Your Mac can now autocomplete your writing in almost any app without ever sending a single word to the cloud. A clever open-source tool called cotabby brings system-wide, inline ghost-text suggestions directly to your screen, working in everything from Slack to iMessage. It uses your choice of Apple's built-in models or local open-source models running entirely on your device. That means you get lightning-fast predictions, emoji completions, and smart autocorrect with absolute privacy and zero tracking. It is a brilliant way to speed up your daily typing, keeping your data safely on your machine where it belongs.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 data-centt/percentify

percentify

Most data-profiling tools bury you in massive, hard-to-read reports, but percentify takes a completely different approach by giving you a single-line data diagnostician that tells you exactly what to fix before you model. Instead of just describing what your dataset is, its flagship profiler function ranks every data issue from worst to first and pairs each with a concrete suggestion on how to solve it. It seamlessly handles both pandas and Polars dataframes, automatically returning whichever type you passed in without requiring any annoying manual conversions or configuration flags. It is like having a sharp, slightly opinionated data scientist review your dataset over coffee, instantly calling out multicollinearity, outliers, and...

📰 https://news.ycombinator.com/item?id=48948400

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 sompote/tigrimosr

TigrimOSR

Build and run your own supercharged native desktop AI assistant with zero lag or bloat. TigrimOSR is a high-performance native desktop application written entirely in Rust that replaces the original heavy Python and Node.js setup with a single, self-contained binary. It uses egui for a lightning-fast, ultra-responsive user interface that loads instantly and keeps computer memory usage incredibly low. The coolest thing is its modular skill system, allowing the local agent to dynamically handle tasks like analyzing complex Excel student grades, auto-generating charts, and conducting deep market research using specialized workflows. It is the ultimate way to run a nimble, private AI assistant on your desktop.

🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 thesysdev/appless

Appless

Appless is the experimental mobile shell that replaces a screen full of icons with a phone that has no apps. Instead of installing menus and software, you simply type what you want in plain words and the device generates the exact interface you need on the spot. Ask for a weather dashboard, a restaurant finder, or a workout tracker, and a real native user interface streams onto your screen in real time. It uses a lightweight interface language to paint authentic Cupertino components on iOS and Material components on Android. You get custom, on-demand screens tailored to the moment.

📰 https://news.ycombinator.com/item?id=48936362

🆔 @hackernewsgithubprojects