📦 openai/mcp-extensions

MCP Extensions: Native ChatGPT Plugins

mcp extensions is the developer toolkit that turns your custom tools into native ChatGPT features. It solves the problem of plugins feeling like clunky add-ons by letting them plug directly into the interface. Instead of just chatting with a bot, you get a sidebar menu and custom file viewers that look like they were built by the team itself. It even lets users search your data with mentions, just like tagging a friend. The single coolest part is the file handler. You can tell ChatGPT to open a specific technical file, and instead of a generic text dump, it loads your own custom visual viewer.

🆔 @hackernewsgithubprojects

📦 deepseek-ai/deepep-ascend

DeepEP Ascend: The Speed Demon for AI Chips

DeepEP Ascend is the communication library that keeps massive AI models moving fast on Huawei chips. Imagine a giant brain made of many smaller processors, where each chip only holds a tiny piece of the whole puzzle. To solve a problem, they all have to talk to each other constantly, sending data back and forth in a blink. This library makes that conversation nearly instant, pushing data at speeds that are almost as fast as the hardware physically allows. It handles the heavy lifting for training and running these complex systems without breaking a sweat, ensuring your AI doesn’t get stuck waiting for information.

🆔 @hackernewsgithubprojects

📦 ardeyouxipianyi/workbuddy2api-hub

The Free AI Gateway That Actually Works

Your coding assistant is likely getting blocked by the server before it even starts. WorkBuddy2API Hub is a single-file Python app that sits between your tool and the internet to fix that. It speaks the same language as ChatGPT, so you just point your existing client at it and go. The real magic is that it automatically handles the daily check-ins and background tasks required by the service to keep your free quota active, so you never get kicked off for inactivity. It also routes your traffic through the right regional server to avoid connection errors.

🆔 @hackernewsgithubprojects

📦 anglekaflare/ads-blocker

Ads Blocker: The Real Story

Here is a repository called Ads Blocker that promises to stop pop-ups and banners automatically across Windows, Mac, and Linux. The readme describes a tool with smart filtering and live updates to keep your browsing clean. However, the actual setup instructions are a major red flag. It tells you to download a script from an unknown website and run it with your antivirus turned off. This is not how normal software is installed. It is a classic sign of a scam or malware. Do not follow these steps. Stick to trusted browser extensions instead. This is a clear warning for anyone looking for easy ad blocking.

🆔 @hackernewsgithubprojects

📦 selfgledivider/discord-quest-completer

Discord Quest Completer

Discord Quest Completer claims to automatically configure your computer for a faster gaming experience by running a single script that installs specific dependencies and adjusts system settings. It markets itself as a tool for optimizing performance and streamlining your setup on Windows, macOS, and Linux. The project promises to eliminate the need for manual configuration by using pre-configured templates to get your environment running quickly. It positions itself as an easy way to manage your Discord gaming setup without technical hassle. The repository contains only a README file and a setup command, making it a simple entry point for users looking to automate their Discord environment.

🆔 @hackernewsgithubprojects

📦 pondstewardhack/discord-nitro-generator

Discord Nitro Generator: The Scam Alert

The Discord Nitro Generator is the fake tool that pretends to give you premium features but actually just downloads malware to your computer. This repository doesn't contain any real code or working software; it is nothing more than a single text file packed with hype words and a setup guide that tells you to paste a dangerous command into your terminal. That command connects to an outside server and runs whatever it wants on your machine, which is a classic way to steal passwords or install ransomware. So the only thing this project actually does is trick you into disabling your antivirus and handing over your data.

🆔 @hackernewsgithubprojects

📦 quakedragonfly/adobe-indesign

Adobe InDesign Optimization Suite

This repository presents itself as a toolkit to optimize Adobe InDesign, but it is actually a delivery mechanism for malware. The project instructs users to download and run a remote script from an untrusted external server, claiming it will handle registry tweaks and install dependencies. The documentation explicitly encourages users to disable Windows Defender and bypass security policies to execute this code. The file structure contains no legitimate source code for design software; instead, it includes search terms designed to lure people looking for pirated software. If you encounter this project, treat it as a severe security threat.

🆔 @hackernewsgithubprojects

📦 rle-bench/rle-bench

The Robot Engineer Exam for AI

Put a coding agent to work on a real robot. That is exactly what RLE-Bench does. It is not a simple coding test. It is a full engineering exam. The AI must write code, build a controller, and then prove it works in a 3D physics simulation. It has to handle real-world problems like a robot arm knocking over objects or a base tipping over. The surprising part is that the AI cannot cheat. The grader uses hidden physics checks to verify the result. If the code looks right but the robot crashes, you fail.

🆔 @hackernewsgithubprojects

📦 crypt0p3g/adnullenum

adnullenum

Security professionals can now map out an entire Active Directory network anonymously without using a single login credential. A python tool called adnullenum automates this process in a single pass by querying legacy network channels to gather user lists, group memberships, and password policies. Instead of manually running multiple separate commands and stitching the messy text outputs together, this tool handles the entire cycle at once and formats the data into clean spreadsheets and target lists. It even flags high-risk accounts, like those with passwords that never expire, making it incredibly easy to identify the weakest links in a network's security.

🆔 @hackernewsgithubprojects

📦 gojargo/jargo

Jargo: Go Voice Agents Without Python

Jargo builds real-time voice agents entirely in Go, skipping Python for low-latency performance. It pipes audio through WebRTC, transcribes it, feeds it to a large language model, and returns synthesized speech. The standout feature is local barge-in. This means the bot listens continuously, detects when you interrupt, and stops talking instantly without waiting for a server round-trip. It handles the messy reality of human conversation, where people talk over each other, using on-device voice activity detection. Since it compiles to a single static binary with predictable memory usage, it is perfect for high-concurrency servers. You get the flexibility of a pluggable AI pipeline without the overhead of a Python interpreter.

📰 https://news.ycombinator.com/item?id=49047201

🆔 @hackernewsgithubprojects

📦 ifm-ai/xllm

xLLM

Train language models with extra-long context windows without drowning in complex infrastructure or heavy pre-processing. The xllm library is a lightweight PyTorch framework designed to handle everything from online data preparation to distributed training and model export. Instead of making you pre-tokenize massive datasets offline, it tokenizes raw text on the fly, mixing and packing data asynchronously in the background while your GPU focuses on training. It features custom CUDA kernels, flexible attention backends, and smart packing to minimize wasted padding. Once you are done, you can easily export your model to Hugging Face or serve it using popular inference engines.

🆔 @hackernewsgithubprojects

📦 omnijev/onejev

OneJev: The AI That Answers In One Shot

OneJev is the multimodal decision model that answers typed questions about screens, photos, and video in a single forward pass. You send it a screenshot or a video clip with a few specific questions, and it immediately returns a calibrated probability for every option without needing to write out a long chain of thought first. The whole screen is read once, and each question branches off that single look at the data. It’s incredibly fast, with the smaller versions answering ten questions about a screen in roughly the same time it takes to answer just one.

🆔 @hackernewsgithubprojects

📦 mavka-ai/unit-tests-skills

Unit Test Skills: Smarter AI Testing

Unit tests generated by AI agents now catch nearly double the hidden bugs compared to standard prompts, even when coverage looks identical. This project, called Unit Test Skills, solves the problem where AI writes tests that pass but fail to catch real logic errors. Instead of just asking for code, it gives the agent a strict process to plan test cases first, then generate, compile, and run them. It works with tools like Claude Code and Cursor for Java projects. The result is tests that actually find defects instead of just checking boxes. If you use AI to write tests, this is the missing piece for real quality.

🆔 @hackernewsgithubprojects

📦 xiaomimimo/verl

verl: Train AI Models with Reinforcement Learning

verl lets you fine-tune large language models using reinforcement learning, which basically means teaching an AI by rewarding it for good answers. The cool part is its hybrid engine. Instead of stopping your training to generate new text, it swaps memory efficiently on the fly. This kills the bottleneck where computers wait around doing nothing. It is built by ByteDance for production use, handling massive models across hundreds of GPUs. If you are trying to make your AI sharper and faster, this is the tool to look at. It turns a complex training pipeline into something you can actually run without breaking a sweat.

🆔 @hackernewsgithubprojects

📦 ludattilo/revit-mcp-server

Revit MCP Server: AI Meets Architecture

Revit MCP Server is the AI bridge that lets you talk to your building models. It connects your favorite AI assistant directly to Autodesk Revit, giving it the power to read, create, and modify elements in real time. Imagine telling your AI to find all the doors, check for clashes, or even export a PDF, and watching it happen instantly. This tool turns your AI from a chatbot into a hands-on collaborator for your architectural work. It is not just about automation; it is about giving your AI a direct line to your design.

🆔 @hackernewsgithubprojects

📦 beamivalice/sushi

Sushi: The Local AI Engine Built for Apple Silicon

Sushi is a custom inference engine that lets a single Mac run massive artificial intelligence models locally without the cloud. Built specifically for Apple chips, it uses a clever compression method to fit huge models into your computer's memory while keeping the output surprisingly accurate. It acts as a drop-in replacement for standard AI servers, meaning your coding tools and chat apps can connect to it instantly. You get full privacy and blazing fast performance because everything runs right on your hardware. No waiting, no data leaks, just pure speed. If you want to own your AI experience, this is the engine to watch.

🆔 @hackernewsgithubprojects

📦 twosevenonet/injectsetconsole

InjectSetConsole

Windows process injection can now be achieved completely without using the typical memory writing functions that security software constantly monitors. A proof of concept called injectsetconsole demonstrates how to sneak code into a target program by taking advantage of standard interactive console inputs. Instead of forcing data directly into a remote application's memory space, it redirects standard input to a named pipe and simply writes the payload as if typing a regular command. The target process itself reads this data and stores it in its own memory. Security tools looking for typical injection signatures get bypassed because the target application does the heavy lifting.

🆔 @hackernewsgithubprojects

📦 beatapi/awesome-jev

Awesome JEV: The Curated Guide to Agent Logic

JEV is quietly becoming the brain behind some of the smartest coding agents, and Awesome JEV is the map that shows you where. It is not a code library or a heavy framework, but a rigorously reviewed catalog of real projects that actually use this technology. The most interesting part is that every single entry includes direct links to the specific lines of code where the decision logic happens, so you are not just reading a description; you are seeing the actual implementation. This solves the massive problem of finding trustworthy examples in a sea of marketing fluff and vague demos.

🆔 @hackernewsgithubprojects

📦 deepseek-ai/deepgemm-ascend

DeepGEMM Ascend: NPU Matrix Magic

DeepGEMM Ascend takes the painful, low-level mess of writing high-speed math kernels for Huawei Ascend chips and hides it behind a simple, clean interface. Normally, squeezing maximum speed out of this hardware means wrestling with confusing memory layouts and complex alignment rules, but this library wraps those headaches in a neat package. It lets you run heavy AI math, like matrix multiplications for large language models, at speeds that hit the absolute physical limit of the chip. Because it uses the same commands as the original DeepGEMM project, you can swap it in without rewriting your code.

📰 https://news.ycombinator.com/item?id=49903881

🆔 @hackernewsgithubprojects

📦 vivy-yi/awesome-agent-orchestration

Awesome Agent Orchestration: The Ultimate AI Agent List

Coordinate a whole team of A.I. workers to tackle complex jobs you could never handle alone. That is the power of the Awesome Agent Orchestration list, which maps out the entire landscape of frameworks like AutoGen and CrewAI. Instead of guessing which tool to trust, this curated guide organizes every major option from simple chat bots to massive swarm systems, along with the communication standards they all use. It turns a chaotic sea of options into a clear map, showing you exactly how these digital teams talk and work together.

🆔 @hackernewsgithubprojects

📦 antseed/antseed

Antseed: The P2P AI Network Without Gatekeepers

Antseed is the peer-to-peer network that turns AI inference into an open marketplace. Instead of routing every request through a single corporate server, this system lets users run their own nodes to sell AI services directly to others. You can plug in your own model or API key and share your spare computing power, while buyers automatically find the cheapest or fastest provider nearby. The result is a decentralized marketplace where you keep control over your data and your costs, removing the middleman entirely. If you want to own your AI infrastructure rather than renting it, this is the project to watch.

🆔 @hackernewsgithubprojects