📦 shivateam/driveteach-vla

DriveTeach-VLA

DriveTeach-VLA teaches self-driving models to recognize traffic scenes and plan paths by combining visual understanding with spatial guidance. It uses driving-aware vision distillation to help the model focus on key road elements, while trajectory-guided prompts align its predictions with real driving paths. This approach replaces complex reasoning with direct spatial grounding, making the system more reliable and precise. By integrating these techniques, the project offers a clearer way to improve autonomous driving performance through better visual learning and trajectory alignment.

🆔 @hackernewsgithubprojects

📦 neul-labs/grite

Grite: The Issue Tracker That Lives in Your Repo

Grite is the local issue tracker that lives inside your git repository, solving the messy problem of AI agents losing track of their work by keeping tasks and notes permanently tied to your code. Instead of relying on slow external servers or cluttering your files with messy notes, this tool stores every change as a secure, unchangeable log directly within git, allowing multiple coding assistants and developers to coordinate smoothly without stepping on each other's toes. You can create tasks, claim work, and store learning notes while staying completely offline, knowing that everything syncs automatically when you push changes.

🆔 @hackernewsgithubprojects

📦 nickjiang2378/value-axis

Value Axis: The Inner Compass of AI Models

The value axis project reveals that large language models actually encode a hidden signal indicating whether they are on the right track. Researchers identified a specific direction in the model's internal activity that measures task confidence. By steering the model along this axis, you can causally influence its behavior. Push toward high value and the model persists with its current approach. Push toward low value and it starts backtracking. This works consistently across math problems, coding tasks, and preference learning. The repository provides the tools to build and use this axis, letting you probe how well the model believes it is succeeding.

🆔 @hackernewsgithubprojects

📦 kuaishougamemind/trace-bench

TRACE BENCH: How AI Roleplay Testing Finally Gets Honest

TRACE BENCH is the evaluation platform that finally forces roleplay AI to prove it can handle complex, multi-step tasks instead of just making polite small talk. Most testing tools only check if a character stays in voice, but this tool assigns a smart digital interviewer to actively interrogate the model. This interviewer carries a private checklist and uses conversation tools to deliberately probe for specific behaviors, ensuring every requirement is actually met before signing off. It turns vague personality traits into hard, traceable scores. If you want to see which AI characters can truly deliver on their promises, this is the transparent testing ground you have been waiting for.

🆔 @hackernewsgithubprojects

📦 neur0map/glazepkg

GlazePKG

Manage every package manager on your computer with a single command. GlazePKG acts like a unified controller for over forty different package managers, including brew, pip, cargo, npm, and apt, across Linux, macOS, and Windows. Instead of memorizing dozens of different commands and flags for different systems, this tool lets you search, install, update, and roll back applications using one simple syntax. It features a beautiful, searchable terminal dashboard to view all your installed software in one place, take configuration snapshots, and even back up your entire setup to migrate to another machine. Keep your system clean and organized.

🆔 @hackernewsgithubprojects

📦 nicepkg/ctxport

CtxPort

Moving your deep AI conversations between different chatbots usually means dealing with broken formatting, missing code blocks, and a mountain of manual copying. CtxPort fixes this instantly by letting you grab any thread from ChatGPT, Claude, Gemini, or DeepSeek as a clean, structured Markdown file with just one click. What makes it incredibly clever is the sidebar hover feature, allowing you to instantly copy a thread directly from your chat history list without waiting for the actual page to load.

🆔 @hackernewsgithubprojects

📦 duelion/homebox-companion

Homebox Companion

Homebox Companion is the smart inventory assistant that turns photos of your physical belongings into organized digital data. Instead of typing out descriptions and serial numbers manually, you simply take a photo of a room, shelf, or box. The app uses advanced vision artificial intelligence to automatically identify multiple items in a single image, extracting details like the manufacturer, model, and retail price, and then saves them directly to your self-hosted setup. You can even use the built-in conversational assistant to find, move, or update your inventory just by chatting. It makes keeping track of your physical gear completely painless.

🆔 @hackernewsgithubprojects

📦 hustvl/eovsam

EOVSAM: Segmentation 300x Faster

EOVSAM is the AI segmentation model that finally cuts processing time by three hundred times without losing accuracy. Most systems struggle by guessing every object one by one, which is painfully slow. EOVSAM changes the game by generating all masks in a single pass using a new aggregation method that handles open-vocabulary tasks efficiently. This means it can identify and outline any object described in text instantly, rather than crawling through a list. It combines top-tier precision with incredible speed, making real-time visual understanding practical for the first time. If you want fast, accurate image analysis that scales with your needs, this is the breakthrough you have been waiting for.

🆔 @hackernewsgithubprojects

📦 parskatt/romav2

RoMa v2

Match points of interest between two different images with incredible accuracy, even under difficult lighting and perspectives. By building on top of deep vision models, this project estimates dense, highly accurate correspondences and maps overlapping areas across image pairs in a clean, pythonic way. This is perfect for computer vision tasks like reconstructing 3D scenes or registering images, as it bypasses traditional sparse feature tracking in favor of a robust, dense matching approach. Best of all, you can load a pretrained model and run it on your own images with just a few lines of code.

🆔 @hackernewsgithubprojects

📦 aagentah/nw_wrld

nw_wrld

Trigger jaw-dropping live visuals using web technologies you already know. With nw_wrld, you can code custom visual modules in plain JavaScript using libraries like p5 and Three.js, then orchestrate them in real time using a slick native interface. Launching the app opens two screens: a control dashboard and a clean output projector. You can choreograph your graphics using a built-in sixteen-step sequencer or map your visual methods to external triggers like MIDI keyboards, OSC signals, and live audio capture. It is the ultimate playground for interactive performances, installations, or prototyping, right from a portable project folder.

🆔 @hackernewsgithubprojects

📦 fasouto/termaid

Termaid

You can now render complete Mermaid diagrams directly in your terminal without spinning up a browser or calling an external web service. A clever new Python tool called termaid translates complex diagram syntax into beautiful, readable text art right in your console. It supports eighteen different diagram types, from flowcharts and sequence diagrams to git graphs and mindmaps. It even intelligently handles pie charts by converting them into clean, horizontal bar charts that actually make sense in text. With zero dependencies, built-in color themes, and automatic terminal-width fitting, it is the perfect utility for documenting systems over secure shell connections or inside terminal-based applications.

🆔 @hackernewsgithubprojects

📦 rrrrrrzy/fm-geometry

Free Uncertainty Detection with Flow-Matching Geometry

Accelerate your AI safety checks by reading the denoising path of a flow-matching model without running a single extra calculation. This project introduces a free proxy that spots uncertainty just by watching how the system bends during its own cleanup process. When the AI is certain, its internal path is smooth and straight, but when it is guessing or confused, the trajectory starts to wiggle. By measuring that physical curvature using basic math, you get an instant alarm before a failure happens. It works on everything from simple toy models to real robot arms, catching mistakes early while using zero extra computing power.

🆔 @hackernewsgithubprojects

📦 zihangtian/arco

ARCO: LLMs That Grade Themselves

ARCO is a Python project that lets language models grade their own step-by-step thinking without any external judges. Instead of waiting for a final score, the model generates a simple three-point checklist for every single action it takes, then scores that action against the checklist right away. Because the grading model and the problem-solving model train together on the same data, the checker learns to spot useful steps while the solver learns to earn better points. This creates a self-correcting loop where the agent improves its reasoning by constantly evaluating and adjusting its own process. It is a fascinating look at how models can become their own teachers.

🆔 @hackernewsgithubprojects

📦 juror-ai/juror

Juror AI

Run parallel reviews on your pull requests using multiple top-tier artificial intelligence models directly inside your own GitHub Actions. By fanning out your code changes to a diverse panel of models, this tool catches far more defects than single-agent setups while keeping your source code safe inside your own runner. It automatically groups duplicate findings, calculates a transparent cost receipt down to the penny, and posts a single clean summary on your pull request. It is the ultimate way to get deep, multi-model feedback without any third-party indexing or expensive monthly software subscriptions.

📰 https://news.ycombinator.com/item?id=49244029

🆔 @hackernewsgithubprojects

📦 praetorian-inc/nerva

Nerva Service Fingerprinter

Identify over one hundred and seventy different network protocols instantly when scanning ports. This clever tool takes raw IP and port lists and immediately figures out exactly what is running on the other side, whether it is an obscure industrial control system, a 5G telecom node, or a self-hosted AI server. Instead of guessing, it queries the port to pull rich metadata like software versions and even flags major security issues like unauthenticated APIs or weak encryption. It is incredibly handy for securing your network. Grab it on your terminal and start exploring what is actually exposed on your servers.

🆔 @hackernewsgithubprojects

📦 aslost/pixtale

Pixtale

Pixtale automatically extracts embedded digital camera data from your photos to organize your entire collection chronologically on a beautiful masonry grid. This self-hosted, personal photo gallery lets you aggregate images from both local storage and cloud buckets into a single, cohesive feed. It runs efficiently on light hardware, utilizing virtualized rendering and lightweight thumbnail generation to keep scrolling quick even on slower mobile networks. By keeping your memories self-hosted and private, you can manage multiple accounts for friends and family without relying on third-party cloud platforms. It is the perfect weekend project to finally take control of your photo library.

🆔 @hackernewsgithubprojects

📦 astropuzzo/comfyui-minimax-h3-image-studio

comfyui-minimax-h3-image-studio

Generate and edit still images using the powerful MiniMax H3 model inside ComfyUI with comfyui-minimax-h3-image-studio. This experimental toolkit adapts a native audio-video model into a highly optimized still-image pipeline, giving you clean tools for text-to-image, image-to-image, and detailed reference editing. The most interesting feature is its smart frame-profile handling, which lets you render a sequence of frames and automatically extracts the single best, sharpest, and most stable image from the batch. Complete with built-in presets for fast-rendering adapters, this extension brings advanced control to your creative setup. Download the nodes today to upgrade your generative workflow.

🆔 @hackernewsgithubprojects

📦 dsh-market/dsh-market

DSH Market

The new DSH Market plugin is a game changer for anyone running DeepSeek Harness, letting you browse, search, and install over three hundred community plugins with a single click right from your settings page. It features an incredibly slick dedicated themes tab where you can live-switch skins instantly with no server restart required. Under the hood, this tool solves frustrating setup issues by auto-detecting missing components, running background update checks, and verifying that everything actually matches the community registry. It is a fantastic, zero-hassle way to completely customize your workspace without ever touching a command line.

🆔 @hackernewsgithubprojects

📦 jinshanmu/crouzeixconjecture

Crouzeix Conjecture Proof Verification

Verify a candidate proof for one of the most famous unsolved problems in matrix analysis. This repository houses a formal, computer-checked verification of a candidate proof for Crouzeix's conjecture, written using the Lean four theorem prover. The conjecture proposes that for any complex matrix and any polynomial, the norm of the matrix polynomial is at most twice the maximum value of the polynomial on the matrix's numerical range. By leveraging computational audits, a detailed manuscript, and formal Lean proofs, this project establishes a rock-solid mathematical foundation for this elusive constant of two, bringing absolute certainty to a major mathematical milestone.

🆔 @hackernewsgithubprojects

📦 xiaobright/dsh-anchored-standard

dsh-anchored-standard

DeepSeek V4 Pro scores significantly higher when it starts with a minimal tool set, but you usually have to sacrifice all your advanced tools to get that performance boost. That is where dsh-anchored-standard comes in. This clever community preset for DeepSeek Harness gives you the best of both worlds by splitting your session into two distinct phases. On the very first request, it strips away distracting workspace context and presents only a couple of basic tools like a platform shell and a read command. Once the model makes its first reply or tool call, the preset automatically unlocks the complete standard catalog of twenty-five tools.

🆔 @hackernewsgithubprojects

📦 xiaobright/modeltest

Modeltest

Put large language models to the ultimate test by running them through real-world software engineering and system maintenance challenges. Instead of using standard, predictable public benchmarks, modeltest acts as a rigorous private evaluation harness built to see how models actually perform when fixing complex codebases, managing hardware-level integrations, and debugging messy, broken pipelines. It throws practical tasks at them, like refactoring embedded firmware and handling system deployments, scoring their actual reasoning trajectories. If you want to see which artificial intelligence truly possesses genuine engineering grit rather than just memorized exam answers, this private playground is the ultimate reality check.

🆔 @hackernewsgithubprojects