📦 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

📦 deepjudge-agent-handoff-protocol/agenthandoffprotocol

Agent Handoff Protocol

Agent Handoff Protocol is an open communication standard that lets different artificial intelligence applications pass a user and their active work context back and forth without losing progress. Instead of forcing you to constantly copy and paste prompts, re-upload massive files, or explain your task from scratch when switching between specialized tools, this system packages your objective, conversation history, and documents into a secure bundle. It moves the entire task to a receiving assistant and generates a direct link to continue right where you left off. This creates a beautifully connected ecosystem where you can naturally transition between the best specialized tools for each phase of your work.

📰 https://news.ycombinator.com/item?id=49288551

🆔 @hackernewsgithubprojects

📦 sculpt-part/sculpt

Sculpt

Most 3D generators struggle to make objects you can actually disassemble, but a new tool called Sculpt is changing that. Instead of treating a 3D model like one solid blob, it builds highly detailed objects and naturally slices them into logical, textured parts inside its own digital brain. It works like subtractive manufacturing, separating things like chair legs or car doors so you can actually use them in games or design. It makes 3D generation incredibly practical for creators who need modular pieces. Keep an eye out for this one, because modular 3D design is about to get a lot easier.

🆔 @hackernewsgithubprojects

📦 bujiazi/hpsd

HPSD Video AI

Upgrade your text-to-video AI generation using its own best habits. Normally, video models create much better animations when we feed them a high-quality starting image instead of just raw text. To bridge this gap, hpsd lets the same AI model act as both a teacher and a student. The teacher uses premium image guides to create a beautiful, anchor trajectory, and then the student practices copying those smooth movements using only simple text prompts. It is like teaching the model to paint masterpieces without needing a reference image. Check it out to see how simple text prompts can finally generate stunning cinematic videos.

🆔 @hackernewsgithubprojects

📦 aeonfun/aeon

Aeon

Aeon is the autonomous agent framework that lets you set up background AI workers once and let them run forever without constant babysitting. Instead of keeping you trapped in endless approval loops to review every single command, it relies on self-contained skills written as simple markdown files that run on a schedule using GitHub Actions. It can automatically research topics, check your code, or monitor markets entirely on its own while you sleep. If something breaks, it even has self-healing loops to patch its own skills. It is the ultimate hands-off setup for turning AI into a quiet, reliable helper.

🆔 @hackernewsgithubprojects

📦 itsmeadarsh2008/opencode-senses

OpenCode Senses

Give your text-only coding models the ability to see by running a local vision layer right on your own machine. By connecting opencode-senses to your session, any attached screenshot or mockup instantly gets analyzed, giving your model exact text extraction, coordinates for user interface elements, and precise pixel measurements. Because it runs locally using the Moondream model on your own graphics card, your private files and desktop images never leave your computer. You can easily spot design changes, pull code straight from a mock image, and debug visual layout errors in seconds. Grab the package from node package manager to give your workspace a powerful, private set of eyes.

📰 https://news.ycombinator.com/item?id=49289890

🆔 @hackernewsgithubprojects

📦 charlesmod/infinite-tapedeck

Infinite Tapedeck

Your local music collection is about to become a radio station that never ends, powered entirely by your own graphics card. Infinite-tapedeck uses a clever local artificial intelligence pipeline to analyze your existing music folders, mapping out your exact personal taste in beats, keys, and vibes. It then automatically generates entirely new tracks matched to your library using local music models. A built-in critic automatically scores and rejects any tracks that do not fit your style before you even hear them. It is a brilliant way to enjoy customized, endless offline music, all running through a beautiful, responsive cyberpunk cassette deck interface.

🆔 @hackernewsgithubprojects

📦 zylwithxy/hrdit

HRDiT: Training-Free 4K AI Images

Hrdit is the smart tool that finally lets you generate massive four-K images using standard diffusion transformer models without any extra training. Usually, if you try to force models like Flux to generate giant resolutions, you get a chaotic, repeating mess, and your computer slows to a crawl. This project brilliantly solves both problems. First, it aligns positional data so the AI actually understands where things go in a massive frame. Second, it cleverly prunes unnecessary attention computations to keep generation times incredibly fast. You get gorgeous, ultra-high-resolution images straight out of the box with zero fine-tuning.

🆔 @hackernewsgithubprojects

📦 meta-models/meta-oss-cookbook

Meta OSS Cookbook

Build and deploy fully offline AI agents on the graphics card you already own. The meta-oss-cookbook repository is a hands-on guide for running Meta's Muse Glimmer, an open-weight model designed specifically for local, multi-step agent tasks. It gives you the exact recipes to set up tool-use loops, handle structured outputs, and configure model servers like ollama or llama cpp without needing cloud APIs. The best part is the step-by-step agent loop that lets the model plan, call local tools, and self-correct entirely on your machine. Grab the code, run the quickstart, and start building private, self-correcting agents today.

🆔 @hackernewsgithubprojects

📦 localgpt-app/localgpt

localgpt

You can actually build fully explorable 3D worlds with natural language using localgpt. This clever Rust project lets you prompt a local engine to generate complete interactive scenes with customized geometry, PBR materials, lights, spatial audio, and active behaviors. Instead of relying on heavy cloud services, it runs entirely on your own machine, combining a local AI assistant with a powerful game engine backend. You get a secure, sandboxed playground with smart memory that learns your style over time. It is perfect for quickly bringing wild concepts to life, giving developers a fast, private way to prototype 3D spaces.

🆔 @hackernewsgithubprojects