📦 erictan7/veritaspp

Veritas++: The AI Detective for Fake Images

Spot when an image is AI-generated without guessing. Veritas++ is a smart model that acts like a forensic analyst for pictures, digging into pixel-level details to find the subtle flaws that slip past the eye. It doesn't just guess; it learns to spot specific visual anomalies, making it surprisingly reliable even on images it has never seen before. This is cool because it helps us trust what we see online, cutting through the blur of digital fakes. If you want to know if that photo is real, this tool shows you how to look closer, giving you a clear answer instead of a maybe.

🆔 @hackernewsgithubprojects

📦 nousresearch/hermes-plugin-backsearch

Time Travel for Your Web Search

Hermes Plugin Backsearch is the search tool that lets you browse the web exactly as it existed on a specific past date. It plugs into the Hermes Agent to give you access to a frozen news archive, meaning every result is locked to a point in time. This kills information leakage, so you can test your AI models or run research without accidentally seeing news that happened later. It is the perfect fix for anyone building systems that need consistent, repeatable answers. No more random updates ruining your data. You just set the date, and the web stays put, forever.

🆔 @hackernewsgithubprojects

📦 ggz14/vllm-mxfp4

The One-Command AI Server

A massive twenty-seven billion parameter AI model now runs entirely on a standard AMD graphics card, serving requests faster than many cloud servers. This project, called vllm-mxfp4, solves the headache of running large language models locally by wrapping a complex stack of custom computer code into a single, simple container. You don't need to build anything, install drivers, or tweak settings. You just run one script, and it automatically checks your hardware, downloads the necessary parts, and starts a live server that speaks the same language as major AI APIs. It even handles multiple cards automatically, making high-performance local AI accessible without a computer science degree.

🆔 @hackernewsgithubprojects

📦 jinchenma94/bazi-skill

Bazi Skill: AI Fortune Telling

Bazi Skill is the open source tool that turns a standard coding assistant into a traditional Chinese fortune teller. It solves the problem of needing a human expert to interpret your birth chart by letting an A.I. agent handle the entire process for you. You simply chat with it, providing your birthday and birth time, and it calculates your four pillars of destiny using a built in script. The most surprising part is that it references nine classic Ming Dynasty texts to provide detailed readings on your career and health.

🆔 @hackernewsgithubprojects

📦 weave-os/router

Router: The Cost-Cutting Switch for AI Agents

Router cuts your A I bills by forty to seventy percent by quietly swapping the smartest model for a cheaper one only when the task is simple. Think of it as a traffic cop standing between your software and the A I providers. In less than fifty milliseconds, it reads the request and sends it to the right brain. You do not need to rewrite your code. You just point your app at this new address. It is a smart switch that makes your systems cheaper without making them dumb.

🆔 @hackernewsgithubprojects

📦 felinics/memoh

Memoh: Every AI Agent Gets Its Own Computer

Memoh is the open-source platform that gives every AI agent its own cloud computer. It solves the problem of agents living only on your local laptop by assigning each one a dedicated workspace with its own file system, browser, and long-term memory. This means your agents stay online twenty-four seven, remembering context even when your laptop is closed. You can talk to them through Telegram, Discord, or a web interface, letting them work on tasks continuously. It is a fascinating way to build a team of helpful bots that are always ready to assist.

🆔 @hackernewsgithubprojects

📦 shinthink/blitzstrike

Blitz Strike: The Pentest Copilot

Blitz Strike hands AI agents a structured, step-by-step playbook for penetration testing, turning raw code into a clear map of where attacks can happen. Instead of guessing, it follows a strict path: find the entry points, trace the data flow, and prove the vulnerability with live tests. The killer feature? It ships with fifty-seven pre-built escalation chains and a catalog of over one-hundred-thirty specialized tools, all wired into one single server. This means any AI agent can plug in and run real, validated security checks without you having to teach it every command from scratch.

🆔 @hackernewsgithubprojects

📦 viitor-ai/viitor-voice-nar

ViiTorVoice-NAR: Edit Only What You Change

ViiTorVoice-NAR is the speech tool that fixes just the words you change. It takes a recording and your corrected script, finds the exact spot that differs, and re-voices only that tiny section. The rest of your original audio stays untouched, keeping the background and tone perfectly consistent. This is a massive time saver for podcasters and editors who hate re-recording entire takes. You get a finished clip instantly without the hassle of manual splicing or messy audio patching. It is a clever way to make your audio sound flawless. Try it out and see how simple editing really is.

🆔 @hackernewsgithubprojects

📦 qwq233/ohmykeymint

Oh My Keymint

Oh My Keymint is the Android security tool that replaces your phone’s hardware key manager with a perfect software fake. It works by intercepting every request for secure keys and answering with data that looks exactly like it came from the chip, which makes it incredibly difficult for apps to tell you are spoofing their security features. The project is written in Rust and includes an injector to hook into the system without a reboot, meaning you can test, fix, or swap the entire security layer on the fly without losing your work.

🆔 @hackernewsgithubprojects

📦 aardappel/goose

Goose: The Programming Language That Ditches the Heap

Compile systems code that runs faster than C++ while keeping the safety of Rust, all without ever touching the heap. Goose is a memory-safe language where every dynamic value lives inline on a data stack managed directly by the compiler. The most surprising part is that your data structure is already your file format. Because the language uses narrow relative links instead of traditional pointers, saving a complex structure is just a raw byte write, and loading it back is a simple read with automatic verification. No serializers, no schemas, and no pointer fixups needed. This makes saving and loading data nearly instant and completely safe from hostile files.

🆔 @hackernewsgithubprojects

📦 xiayutian11/maskit

Maskit: The Privacy Shield for AI Coding

Your code assistant might be quietly sending your secret database passwords and internal server addresses straight to a cloud server. A local gateway called Maskit fixes this by sitting between your computer and the AI. It scans your outgoing messages and swaps sensitive details for harmless placeholders before they leave. The AI works on those placeholders, and your software instantly turns them back into real data as it types. This keeps your private information safe without slowing you down or breaking your workflow. It runs entirely on your machine, so your data never touches the outside world.

🆔 @hackernewsgithubprojects

📦 kajisho5/ffmpeg-skill

The Local Video Editor for AI Agents

Forty-two distinct video editing tasks are now available to coding agents without touching a single cloud service. The project called F F M P E G skill turns natural language requests into precise, local video edits by wrapping a standard media tool with a strict set of safety rules. It solves the problem of unpredictable code execution by ensuring every cut, caption, or audio adjustment follows a verified workflow that never touches your original files. The most interesting part is that it refuses to guess; it probes your files first and verifies the output against your exact request.

🆔 @hackernewsgithubprojects

📦 minimax-ai/minimax-code

minimax-code: The Terminal Agent

Build, run, and manage complex software tasks directly from your command line using MiniMax Code. This open source tool turns your terminal into an intelligent workspace, letting you ask an AI to write, review, and fix code while you keep your hands on the keyboard. The real magic lies in its safety guard, which watches over the agent to stop it from making dangerous or unintended changes to your files. You get the speed of automation with the peace of mind of knowing exactly what is happening, making it a powerful companion for developers who want to move faster without losing control.

🆔 @hackernewsgithubprojects

📦 modelscope/ms-cookbook

The ModelScope Cookbook

ModelScope Cookbook is a forty-chapter open source book that teaches you to build real AI apps using open models. It skips the theory and shows you exactly how to pick a model, run it on your laptop, and tweak it to fit your specific data. You will learn to measure results so you know when an update actually helps. Instead of vague concepts, you get step by step recipes for things like voice assistants and image generation. If you want to stop guessing and start building with confidence, this guide gives you the practical skills to do it.

🆔 @hackernewsgithubprojects

📦 agent-launch/agent-launcher

Agent Launcher: One App for All Coding Agents

You can now run six different AI coding assistants from a single window on your desktop. Agent Launcher solves the headache of managing separate command line tools for every specific model you want to use. It finds the agents already installed on your computer and lets you configure their login details and model settings right inside the app. Instead of typing cryptic commands, you just pick your tool, choose your project folder, and start chatting. The app even installs missing tools for you if you want it to. It keeps everything local and organized in one place.

🆔 @hackernewsgithubprojects

📦 creatorberry/flick

Flick: Your Script, In Motion

Turn any video or script into a set of distinct animated scenes with Flick. This open source tool acts as a motion director, taking your source material and converting it into a visual plan. It breaks your content down into specific moments, then builds a custom animation for each one. You control the aspect ratio, brand assets, and style, while the system handles the heavy lifting of turning words into moving visuals. The result is a library of reusable, editable scenes rather than just a static file. If you create short form content, this workflow transforms your scripts into dynamic, professional animations without needing to code every frame yourself.

🆔 @hackernewsgithubprojects

📦 nicosuave/memex

Memex: Your Agent Memory

Memex is the search engine that finally makes your coding agent history findable again. It reads the transcripts from tools like Claude Code and Cursor, letting you search for exactly how you solved a problem weeks ago. The most surprising part is that it does not just show you the text; it lets you resume that exact session right where you left off in the original tool. It also tracks token usage so you can see what each project actually costs. It turns your scattered chat logs into a searchable, resumable archive that lives entirely on your computer.

📰 https://news.ycombinator.com/item?id=49754771

🆔 @hackernewsgithubprojects

📦 tianyucodings/nanojev

NanoJev: The Tiny AI That Thinks in Probabilities

Navigate mazes and play Snake without writing a single word of code. That is exactly what NanoJev does. It is a tiny six-hundred-million parameter model that skips the usual chatbot output entirely. Instead of generating text tokens one by one, it reads the game state and spits out a complete probability map for every possible move in a single instant. This zero-decoding approach is surprisingly fast and lets the small model beat its much larger parent, Jev, on specific tasks. You can watch it dodge walls and chase food in a live browser demo. It proves you do not need a massive supercomputer to make smart real-time decisions.

🆔 @hackernewsgithubprojects

📦 virtuslab/orca

Orca: Code with AI that actually finishes the job

Orca turns messy, unpredictable AI coding into a reliable, step-by-step assembly line you control in code. Instead of hoping a chatbot does the right thing, you write a script that forces the AI to plan, build, and review its own work before it ever touches your real files. The coolest part is that every step is saved as a permanent checkpoint. If your computer crashes or the AI gets stuck, you just run the command again and it picks up exactly where it left off, rather than starting over from zero.

📰 https://news.ycombinator.com/item?id=49755856

🆔 @hackernewsgithubprojects

📦 kael-odin/awesome-academic-research-skills

Awesome Academic Research Skills: The Daily Ranking

Awesome Academic Research Skills is the daily leaderboard that cuts through the noise of generic AI tools to find only genuine research helpers. Instead of letting you drown in thousands of random coding repositories, this project automatically scans GitHub every single day to hunt down specific skills for writing papers and doing literature reviews. The coolest part is how it actually works. It uses a double-signal filter to make sure a repository is not just about AI, but is truly built for academic workflows like peer review and experiment reproduction.

🆔 @hackernewsgithubprojects