📦 mlpc-ucsd/pixarmesh

PixARMesh

PixARMesh is the 3D scene reconstruction tool that directly outputs clean, native computer graphics meshes from a single camera snapshot. Instead of relying on messy intermediate steps like volumetric grids or complex mathematical functions that you have to decode later, it models entire rooms and objects as native geometric meshes. By predicting both where objects are and what they look like in a single, unified sequence, it simplifies the transition from a flat picture to a fully realized 3D environment. This makes it incredibly easy to turn real-world photos into usable assets for game engines, virtual reality, or physical modeling.

🆔 @hackernewsgithubprojects

📦 softcane/human-state-skills

human-state-skills

human-state-skills is the AI assistant toolkit that changes its entire communication style based on your current mental energy. Most AI tools give you a giant list of steps when you ask for advice, but if you are exhausted or overwhelmed, a wall of text is the last thing you need. This project lets you activate specialized modes like overloaded, foggy, or burnout directly in your AI chat. Instead of telling you to re-plan your whole week, the AI might give you just one single action to take next, like putting a document on the table, and tell you exactly where to stop. It adapts the assistant to match how your...

🆔 @hackernewsgithubprojects

📦 arya51-ai/obsidian-vault-sync

obsidian-vault-sync

obsidian-vault-sync is the local script that turns your messy Claude conversations into a beautifully organized knowledge graph inside Obsidian. Instead of letting your best AI chats vanish into browser history, this tool automatically pulls your Claude sessions, formats them into clean markdown, and files them away by project. The coolest part is how it handles memory. It actually symlinks Claude's own memory files directly into your vault, meaning the notes Claude keeps about your work become real Obsidian notes you can link and search. It even updates notes as your conversations continue, keeping your personal knowledge base perfectly in sync.

🆔 @hackernewsgithubprojects

📦 freecomputinglab/rheo

Rheo

Rheo is a publishing engine that compiles a single folder of Typst documents into a PDF document, a static HTML website, and an EPUB e-book all at the exact same time. Instead of managing separate source files or fighting with fragile conversion tools, you write your content once using clean Typst markup and let this tool handle the rest. It features a built-in development server with automatic browser refresh for real-time editing, and it even resolves links between documents automatically across every format. It is a brilliant way to publish beautiful books, websites, and documents simultaneously with zero extra effort.

📰 https://news.ycombinator.com/item?id=48730169

🆔 @hackernewsgithubprojects

📦 pzqpzq/lsf_mdia

lsf_mdia

Compress complex language model reasoning into ultra-compact symbolic dialects instead of wasting time and money on long, rambling chain of thought explanations. By letting different AI models invent, refine, and route their own custom symbolic shorthand, this system cuts down token usage dramatically while actually boosting accuracy on complex tasks. It treats communication as a dynamic social process where models create task-specific codes tailored to each other. This elegant approach proves that machines do not need to think in human paragraphs to solve tough problems. Check out the repository to see how language models can design their own efficient languages.

🆔 @hackernewsgithubprojects

📦 frumu-ai/tandem

Tandem

Tandem is the desktop safety manager that finally gives you total control over what autonomous AI agents can actually do on your machine. Instead of letting AI tools run wild with your files, memory, and code, this app steps in as an active gatekeeper to monitor and approve every single action they take. You get real-time approvals, clean audit trails, and pre-configured skill packs for specialized tasks like data analysis or legal research. It acts like an operating system sandbox with human-in-the-loop oversight. Keep your local files safe while letting your AI agents do the heavy lifting.

🆔 @hackernewsgithubprojects

📦 internscience/agents-a1

agents-a1

A relatively compact thirty-five-billion parameter AI model can match the performance of trillion-parameter giants simply by scaling up its reasoning horizon. The agents-a1 project introduces an open-source mixture-of-experts model trained on massive agentic trajectories averaging forty-five thousand tokens. By connecting external knowledge, actions, and feedback, it tackles incredibly complex, multi-step tasks across six domains like scientific research and coding. It uses a clever multi-teacher training approach to pack specialized expert knowledge into a single deployable model. It is a brilliant reminder that smarter training and longer reasoning paths can easily beat sheer model size.

🆔 @hackernewsgithubprojects

📦 epoch-research/mirrorcode

MirrorCode

An artificial intelligence model once spent nineteen straight days working on a single problem in this evaluation suite. This is mirrorcode, a rigorous benchmark designed to test the limits of machine learning on complex programming tasks. Built on the Inspect framework, it forces artificial intelligence to tackle real-world software engineering challenges using actual source code and documentation from popular tools like Ruff and JQ. Instead of simple coding puzzles, it evaluates how systems handle deep, multi-step engineering workloads over long periods. It is a fascinating look at how researchers measure the boundary between human developers and next-generation software agents.

🆔 @hackernewsgithubprojects

📦 fansunqi/videotool

VideoTool

Large multimodal AI models can now analyze video questions with unprecedented accuracy by strategically combining specialized temporal and spatial tools. videotool is an open-source framework from NeurIPS 2025 that equips language models with a collaborative toolkit containing frame selectors, object trackers, and image captioners. Instead of relying on a single AI to guess its way through a video, this project coordinates these specialized tools to progressively narrow down and isolate exactly where and when an action occurs. It dramatically reduces errors and boosts video understanding performance, making it a must-watch helper for building smarter video applications.

🆔 @hackernewsgithubprojects

📦 open-gsd/gsd-core

Gsd Core

The software development companion that actually gets your code out the door without the typical chaos, gsd-core is a framework designed to turn manual terminal work into structured, issue-driven developer workflows. Instead of jumping between endless AI tools, it uses specialized agents and built-in commands to coordinate everything from planning and code reviews to debugging and deployment. It acts like an automated project manager and quality assurance team living right inside your command line, verifying your code changes and updating your documentation dynamically as you work. Give it a spin on your next project to see how easy shipping code can really be.

🆔 @hackernewsgithubprojects

📦 danielmiessler/lifeos

lifeos

Build a personal digital command center that aligns your daily actions with your biggest life goals. This repository, called lifeos, provides the actual framework to run what it calls a personal AI infrastructure. Instead of juggling random productivity apps, it combines your goals, habits, and tasks into a single system powered by a local dashboard and a digital assistant. The core engine analyzes your current state, maps out where you want to go, and helps you take the next step. It is a fascinating way to use modern AI as a highly personalized coach that keeps you focused on what actually matters.

🆔 @hackernewsgithubprojects

📦 cloudflare/skills

Cloudflare Skills

AI coding assistants can now get direct, native instructions to build and manage full cloud applications on Cloudflare. The skills repository is a collection of pre-made capabilities designed for popular AI agents like Claude Code and Cursor. Instead of relying on outdated training data, this project equips your agent with specialized knowledge for databases, AI models, and secure code sandboxes. It even includes remote servers that let your AI browse live documentation and manage active deployments. It is a fantastic way to turn a generic coding assistant into a dedicated cloud engineer that gets things right the very first time.

🆔 @hackernewsgithubprojects

📦 mindmuxai/brain.md

brain.md

Keep your coding agents on the exact same page across every single session by giving them a shared, persistent memory. This zero-dependency command line tool scaffolds a plain markdown brain file directly inside your repository. Instead of losing critical decisions, project constraints, and architectural context the moment a chat ends, agents like Claude Code read and write to this local file to instantly recall why choices were made. By routing all memory updates through a simple command line interface, the project structurally prevents malformed edits, keeping your project's durable knowledge base clean, portable, and completely independent of any specific AI model.

📰 https://news.ycombinator.com/item?id=48717245

🆔 @hackernewsgithubprojects

📦 pelski/ytzero

YT Zero

YT Zero is the self-hosted YouTube subscription reader that finally lets you watch the channels you love completely on your own terms. It pulls public feeds directly into a local database, giving you a quiet inbox to filter, watch, and organize videos without a Google account, API keys, or an annoying algorithm dictating what you see. The coolest part is the smart watch-later bucket system, letting you sort videos into custom schedules like Tonight, Tomorrow, or Weekend so you can tackle your queue when you actually have time. It is an incredibly clean, distraction-free way to reclaim your subscription feed.

🆔 @hackernewsgithubprojects

📦 jeikeilim/tenet

Tenet

Supercharge your coding assistant into a relentless software engineer that builds entire features completely on autopilot. Tenet is a smart wrapper that orchestrates popular AI agents like Claude Code, keeping them on track for continuous twelve-hour development sessions without losing their minds. Instead of letting an AI make lazy assumptions, it interviews you, drafts a spec, visualizes the architecture, and breaks everything down into a dependency graph. The coolest part is the evaluation pipeline: it forces separate, independent AI critics to grill the code, tests, and user interface, rejecting any lazy shortcuts. It is the ultimate tool for turning fragile AI sessions into a robust, self-healing developer workflow.

🆔 @hackernewsgithubprojects

📦 dingwu1021/promsa

Promsa

Most visual assistants get stuck on hard questions because they use a rigid, one-shot search pipeline that cannot recover from a bad first guess. Promsa changes this by turning the AI into a budget-aware researcher that dynamically decides how to search. During a task, it analyzes the clues gathered so far and chooses whether to run a reverse-image search, perform a text query, or stop once it has enough evidence. This makes visual question answering incredibly flexible, letting the assistant chain multiple search steps and switch strategies on the fly until it finds the correct answer.

🆔 @hackernewsgithubprojects

📦 j-c-zhao/structsplat

StructSplat

Imagine creating a fully detailed three-dimensional digital scene from just a few smartphone photos, without even knowing the camera settings or angles. StructSplat does exactly that by predicting three-dimensional gaussians directly from uncalibrated, sparse images. Traditional methods require precise camera positions or heavy per-scene processing to stitch images together, but this system uses a clever structured approach. It separates texture, geometry, and semantic cues to keep everything highly accurate and globally consistent. It is a massive step forward for virtual reality and game design because it lets you reconstruct rich, complex spaces instantly from a handful of casual snapshots.

🆔 @hackernewsgithubprojects

📦 mat-mgm/kb-prolog

kb-prolog

You can now make complex statements about other statements and track their entire history like code using kb-prolog. This local-first knowledge base lets you build nested, hyper-relational graphs where a claim can easily describe another claim, such as recording that one person doubts what another person said. It combines a Prolog runtime with SQLite for storage, automatically saving and tracking version changes so you can travel back in time to see exactly how your data evolved. Plus, it features built-in file storage and an interactive graph visualizer to browse everything easily. It is a brilliant way to bring deep, logical relationships and version control to your local data.

📰 https://news.ycombinator.com/item?id=48697599

🆔 @hackernewsgithubprojects

📦 uw-syfi/tracelab

tracelab

Peek behind the scenes of real-world coding assistants by analyzing the exact logs they generate during development. Under the hood, tools like Claude Code emit highly complex event sequences, from tool calls to split-second timing events. This repository gives you a massive, pre-sanitized dataset of over three hundred thousand developer rounds alongside a local pipeline to clean and inspect your own assistant history. You can run prebuilt data experiments, reconstruct prompt-cache behavior, or drag logs directly into a web app to see interactive charts. It is a fantastic way to understand how agent infrastructure behaves under load, helping you build smarter, more predictable developer tools.

🆔 @hackernewsgithubprojects

📦 clawdbrunner/openclaw-graphiti-memory

openclaw-graphiti-memory

Multi-agent AI teams can now share a unified, evolving memory without running into constant file conflicts. The openclaw-graphiti-memory project introduces a clever three-layer memory system designed specifically for OpenClaw setups. It combines private local files for individual agent tasks, read-only shared files for stable team rosters, and a dynamic, temporal knowledge graph powered by Graphiti and Neo4j. This means agents can query a central brain to recall exactly when a decision was made or what another agent discovered, all while keeping their own working notes separate. It is a practical blueprint for building collaborative, well-coordinated digital workforces.

🆔 @hackernewsgithubprojects