📦 tencentarc/pixal3d

Pixal3D: Turn Photos into 3D

Pixal3D is the image-to-3D generator that makes every pixel count. It doesn't just guess what your photo looks like in 3D; it mathematically traces each pixel back to its exact spot in space. This creates a 3D model that looks almost identical to the original picture, with sharp details and accurate materials. It solves the problem of blurry or wrong shapes you usually get from AI. If you want a realistic 3D asset from just one flat photo, this is the tool that gets it right. Stop settling for vague 3D guesses; start generating precise models from your photos today.

🆔 @hackernewsgithubprojects

📦 soumatheusgomes/vibe-coding-toolkit

Vibe Coding Toolkit: Real AI Dev Workflow

The Vibe Coding Toolkit is the AI coding workflow that stops treating your code assistant like a guessing game. Instead of hoping a large prompt produces the right result, this collection provides the exact structure to make an AI agent act like a real team member. The most fascinating part is how it organizes your coding sessions into parallel waves. By splitting work into independent streams, multiple agents can code at the same time without ever stepping on each other’s toes. This turns a chaotic chat window into a disciplined engineering process.

🆔 @hackernewsgithubprojects

📦 wishval/wamp

Wamp: Winamp Nostalgia on macOS

Wamp is the native macOS music player that faithfully recreates the classic Winamp interface. It is not a web wrapper or a browser app; it is built entirely from Swift code, ensuring it feels like a true Mac citizen with media keys and menu bar integration. The standout feature is its ability to load original Winamp skin archives, instantly transforming the entire app to look exactly like the late-nineties classic you remember, complete with bitmap fonts and custom colors. It also handles complex audio files properly, splitting long recordings into individual tracks with perfect timing.

📰 https://news.ycombinator.com/item?id=47692731

🆔 @hackernewsgithubprojects

📦 tailscale/tailscale-rs

Tailscale, but in Rust

The Tailscale team is writing their entire virtual private network client in Rust, and it already works with your existing Python, C, and Elixir code. This project lets you open secure, encrypted sockets to other devices on your private network without installing a heavy system-level agent. It handles the complex encryption and routing under the hood, so your application can just send data to a friend's computer as if it were on the same Wi-Fi. Because it is built as a library rather than a standalone app, you can embed secure networking directly into your own tools.

📰 https://news.ycombinator.com/item?id=49517953

🆔 @hackernewsgithubprojects

📦 leopard627/fire-your-seo-agency

Fire Your SEO Agency: AI Audit Skill

Replace your expensive monthly SEO retainer with a single AI agent skill that actually does the work. Fire Your SEO Agency audits your website across five distinct search lanes, including the specific requirements for Naver and modern AI answer engines that most global guides completely ignore. It reads your site exactly like a crawler does, fixes broken technical issues, and structures your content so AI systems can extract and cite your data accurately. The coolest part is that it refuses to stop at making changes; it schedules a re-measurement to prove the results with real numbers.

🆔 @hackernewsgithubprojects

📦 usail-hkust/dslighting

DSLighting: AI Data Science Assistant

Hand a plain English task and a messy spreadsheet to D S Lighting, and watch it write, run, and fix its own code until it gets the answer right. This tool acts like a tireless junior data analyst that never sleeps, automatically cycling through planning, coding, and self-correction so you don't have to manually debug every single line. It’s basically hiring a smart, instant assistant that lives entirely in your terminal, turning vague questions into working results without the usual back and forth of prompting. You get to focus on the insights while the software handles the tedious syntax.

🆔 @hackernewsgithubprojects

📦 tencent/contextpilot

ContextPilot: The AI That Cleans Its Own Desk

Make your AI agent smarter by teaching it to clean up its own memory. ContextPilot solves the problem of agents getting overwhelmed by too much information. Instead of letting a model drown in endless conversation logs, this tool trains it to actively organize, summarize, and forget useless details. It uses a clever reinforcement learning trick to figure out exactly which pieces of info matter, so the agent keeps a compact, focused workspace. This leads to better answers on long, complex tasks without needing massive amounts of raw data. It is a smart way to build agents that stay sharp, even when the conversation gets really long.

🆔 @hackernewsgithubprojects

📦 amap-ml/looparena

LoopArena: Testing AI Managers

LoopArena is the benchmark that finally measures which AI models make the best project managers. It tests a model acting as a controller guiding a separate coding agent through complex tasks, revealing who can actually steer the work. The twist is that the best model still succeeds on less than twenty-five percent of full tasks, proving that guiding AI is far harder than letting it code alone. If you care about AI reliability, this gap is exactly where the next breakthroughs will happen.

🆔 @hackernewsgithubprojects

📦 kingbootoshi/cartographer

How Cartographer Maps Your Codebase

Cartographer turns any codebase into a local, navigable map that AI agents can actually read. Instead of letting an LLM guess its way through your files, this tool spins up parallel subagents to analyze your code in parallel, then stitches their findings into a single, clear architecture document. It handles the heavy lifting of understanding dependencies and data flows, so you don't have to manually trace every file. The result is a living map of your project that updates as you make changes, giving your coding assistants precise context instead of vague guesses.

🆔 @hackernewsgithubprojects

📦 tetreesex/tetreesagent_ex

Tetrees Agent EX: Train AI Without a GPU?

Tetrees Agent EX is the integration kit that lets you run trained AI intelligence without owning a single expensive graphics card. Most developers assume training or running complex models requires heavy local hardware, but this tool flips that script by handling all the heavy lifting on hosted servers. You can search for specific AI packs, test them out, and even build your own custom intelligence that connects to your local tools. It handles the buying, building, and publishing process right from your command line. The best part is that your private data and credentials stay on your machine while the computation happens remotely.

📰 https://news.ycombinator.com/item?id=49512825

🆔 @hackernewsgithubprojects

📦 anysearch-team/anysearch-dsh

AnySearch for DeepSeek Harness

Give your AI agent live eyes on the web with AnySearch. This tool plugs into DeepSeek Harness to instantly add real-time web search and clean content retrieval, letting your model pull fresh facts right when it needs them. The coolest part is the batch search capability, which lets the agent run up to five different queries at the same time so one slow result doesn't hold up the whole process. You also get vertical search for specific areas like code or finance, all without needing any API key to get started. It is the easiest way to make your local AI agent actually useful for real-world research.

🆔 @hackernewsgithubprojects

📦 google-gemini/jot-gemini-transcribe-macos

Jot: Smart Dictation for macOS

Your Mac can now listen to you change your mind mid-sentence and fix it for you. A developer created Jot, a free dictation app that turns your speech into clean, punctuated text directly at your cursor. The real surprise is how it handles corrections. If you say you want to meet at one o'clock, then immediately backtrack and say two o'clock, Jot writes only the final decision. It strips out the hesitation and gives you a polished sentence without you having to edit a single word. It runs locally on your machine, keeping your audio private while using a specialized model to understand context.

🆔 @hackernewsgithubprojects

📦 ga1i13o/foundyou

FoundYou: One Model, Two Superpowers

FoundYou is the unified computer vision model that lets you find and trace a single object across massive datasets. You show the system just one picture of a specific item, like a blue mug, and it instantly locates every other instance in a library of one hundred million photos. It can even highlight exactly where that object sits in new images. This tool is incredibly fast and lightweight, running on a fraction of the hardware previous systems required. It bridges the gap between spotting something and cutting it out from the background. If you are building search engines or editing photos, this is the efficient engine you have been missing.

🆔 @hackernewsgithubprojects

📦 amap-ml/dreamx-creator

DreamX Creator Makes Video Sound

DreamX Creator takes a single image and a text prompt, then generates both video and sound at the same time. It is not just adding a soundtrack to a silent clip; the model builds the two streams together so the audio actually matches the on-screen action. This creates a realistic experience where what you hear is driven directly by what you see. The project is open source, meaning you can study the method or use the code to build your own synchronized media. If you want to create video that feels alive, this is the place to start.

🆔 @hackernewsgithubprojects

📦 yifanzhang-pro/fast-weight-attention

Falcon: How AI Models Learn On The Fly

Falcon changes how neural networks handle memory by treating every new piece of information as a quick, on the spot learning opportunity. Instead of trying to remember everything in a massive list, these models compress endless streams of data into a tiny, fixed size summary that updates constantly. This is called fast weight attention, and it turns the standard attention mechanism into a kind of live learning rule. You get a system that keeps adapting to what it sees right now without needing to rewind and retrain on old data. It is a clever way to make machines that learn continuously without getting bloated or forgetting what matters.

🆔 @hackernewsgithubprojects

📦 zjunlp/autoscirub

AutoSciRub: The Grader That Fixes AI Research

AutoSciRub is the research plugin that stops guessing and starts grading. Instead of letting an A I agent wander blindly through a scientific task, it first builds a specific checklist of what a good answer actually looks like. It checks the literature and the available data to define exactly which evidence proves success. Then, it uses that list to catch every gap in the draft, guiding the agent to fix only what is missing. It is the difference between hoping for a good result and verifying one. If you are building autonomous research tools, this is the missing link.

🆔 @hackernewsgithubprojects

📦 cognicore-dev/cognicore-env

CogniCore: AI Agents That Actually Remember

CogniCore gives AI agents a memory that actually sticks, solving the frustrating problem where software forgets everything the moment it restarts. Instead of relying on expensive cloud calls for every single interaction, this open-source framework stores information locally using a method that is surprisingly efficient, requiring almost no extra data to find the right answer. It even includes a safety layer that acts like an immune system, automatically blocking malicious tricks that try to trick the AI into revealing secrets or ignoring instructions. If you are building tools that need to learn from experience, this is the one project to watch.

🆔 @hackernewsgithubprojects

📦 valeoai/vatix

How Far Can 5,500 Hours of Driving Take You?

Researchers at Valeo discovered that training video models on five thousand hours of real driving footage reveals a clear rule for how these systems improve. They built a series of video generators from small to massive scale to see how data and size affect performance. The surprising finding is that letting a model train on the same data for longer improves accuracy much faster than simply building a larger model. This matters because driving video is hard to collect and expensive to create. For anyone working with limited data, this study shows that time spent training is a far better investment than just adding more parameters.

🆔 @hackernewsgithubprojects

📦 wujh2001/atgs

ATGS: The Future of 3D Video

ATGS lets you render long, high-fidelity volumetric videos without falling apart. It uses anchored temporal Gaussian splatting, a fancy way of saying it tracks moving objects over time by anchoring them to stable points in space. This solves the messy problem of keeping 3D scenes coherent when things move or change, which is hard with standard methods. It is cool because it handles long sequences, not just short clips, using a flexible encoder that models how things change frame by frame. If you want to see how 3D video tech is evolving, this is a solid starting point.

🆔 @hackernewsgithubprojects

📦 dongping-chen/game2world

Game2World: The AI Editor That Cleans Gameplay Videos

Game2World acts as a specialized video editor that strips away the clutter from real gameplay recordings, removing health bars, maps, and menu screens while leaving the actual game action completely intact. This tool solves a major hurdle in artificial intelligence research, where computer models need clean, unobstructed footage to learn how the world moves and reacts. By providing this pristine training material, the project helps researchers teach machines to understand complex environments without getting confused by the user interface. This single capability is what makes the project so valuable to the field.

🆔 @hackernewsgithubprojects