📦 willibrandon/pixel-mcp

pixel-mcp

The model context protocol server that lets you paint custom retro pixel art and animations using plain text commands. By bridging your AI assistant directly to the Aseprite engine, pixel-mcp lets you describe what you want in simple English, and then automatically translates your words into precise drawing instructions. It goes way beyond basic shapes, enabling your favorite artificial intelligence client to apply complex dithering patterns, generate smooth color-quantized palettes, suggest smart antialiasing, and even compute three-dimensional light sources for automatic shading. You simply type your creative ideas, and the backend handles the heavy lifting, delivering beautifully exported spritesheets and animations.

🆔 @hackernewsgithubprojects

📦 noniv/snowflow_demo

Snowflow Demo

Snowflow_demo is the real-time graphics showcase that generates a stunning winter wilderness entirely on your graphics card without loading a single heavy 3D mesh or texture file. Built with WebGPU and BabylonJS, this clever project bakes procedurally generated terrain, character models, flowing water, and realistic physical snow deformation dynamically at runtime. As you move around, feet plant naturally, fabric folds simulate on the fly, and sliding across the ground carves a persistent trail that self-shadows and realistically drifts back in with the wind. It runs at blistering speeds with virtually zero loading overhead, proving how much detail you can squeeze out of pure code.

🆔 @hackernewsgithubprojects

📦 rengwu/chartr

Chartr Terminal Multiplexer

You can now drive your development projects to completion using a visual map that synchronizes directly with your local files. This tool acts as an agent multiplexer that turns your project folders, shell sessions, and command line helper tools into a single cohesive cockpit. When you launch a planning session, the tool draws a star map directly from your markdown files on disk. You simply pick an unblocked ticket off the frontier, choose a helper, and your terminal opens with the full context and history already loaded. It is a completely local, keyboard-friendly station for developers who want to organize their thoughts visually without any external cloud accounts.

📰 https://news.ycombinator.com/item?id=49094526

🆔 @hackernewsgithubprojects

📦 redential/redential-cli

Redential CLI

Your best work is probably locked away behind nondisclosure agreements, making it impossible to showcase on a traditional resume. Redential CLI solves this problem by analyzing your local git history and implementation patterns to detect your technical skills without ever letting a single line of code leave your computer. It runs entirely on your local machine, scanning your private repositories to find specific coding capabilities and languages used. It then translates these patterns into a secure, privacy-safe metadata profile that only includes high-level summaries and salted fingerprints. This means you can finally prove your real-world experience to employers with a verifiable profile they can trust, all while keeping your proprietary...

📰 https://news.ycombinator.com/item?id=49085044

🆔 @hackernewsgithubprojects

📦 openai/codex-security

Codex Security

Find, validate, and fix security vulnerabilities right inside your code using artificial intelligence. codex-security is an open-source command line tool and TypeScript software development kit from OpenAI that brings security scanning directly to your local workspace or continuous integration pipelines. By using smart AI models, it goes beyond simple pattern matching to perform deep security scans, analyze threat models, and even write patches for the bugs it finds. You can easily integrate it into your pre-commit hooks to block high-severity issues before they ever get pushed, keeping your repositories secure with minimal effort.

📰 https://news.ycombinator.com/item?id=49089755

🆔 @hackernewsgithubprojects

📦 infatoshi/netherite

Netherite: Bit-Verified Minecraft in C and CUDA

Run Minecraft seventy-two hundred times faster on a single graphics card by rebuilding the entire game from scratch. The netherite project is a complete C and CUDA reimplementation of Minecraft version one point eleven point two that is bit-verified against the original Java game. It solves the massive performance bottleneck of training artificial intelligence in complex environments by running thousands of independent, fully simulated game worlds in perfect lockstep directly on your GPU. It includes everything from world generation and physics to combat and dimension-hopping portals, all objectively tested to match the real game's pixels. Check out netherite to see how rewriting classic games for graphics chips is unlocking the...

🆔 @hackernewsgithubprojects

📦 off-grid-ai/ogad

ogad

You can now run a complete, private AI studio with text, vision, image generation, and voice capabilities entirely on your own computer without ever sending a single byte of data to the cloud. A clever open source project called ogad packs an entire suite of local artificial intelligence tools into one clean interface. It bundles lightweight engines to handle everything from speech-to-text to fast image generation, and it even exposes a local gateway compatible with standard OpenAI web requests. This means you can hook up your favorite third-party developer tools and apps directly to your own machine. It is the ultimate private sandbox for offline AI hacking.

🆔 @hackernewsgithubprojects

📦 twalichiewicz/hnewhere

HNewhere

Read Hacker News comments directly on whatever article you are browsing, without having to switch tabs. This clever userscript called HNewhere instantly checks if the webpage you are reading has been submitted to Hacker News. If it has, a clean, resizable sidebar slides out with the entire discussion right there. You can collapse comment threads, see highlighted new comments since your last visit, and even spot the author of the post. It saves you from constantly bouncing back and forth to look up discussions. It is like having a smart, opinionated companion along for your daily reading.

📰 https://news.ycombinator.com/item?id=49090607

🆔 @hackernewsgithubprojects

📦 clay-good/openlore

OpenLore

OpenLore is the local memory system that gives artificial intelligence coding agents instant context without constantly burning expensive API tokens. When artificial intelligence tools edit large codebases, they often lose track of how things connect or trigger endless loops of errors. Instead of relying on a slow, expensive language model to figure things out, this project runs a fast, deterministic engine directly on your machine. It analyzes your code structure, tracks real-time changes, and enforces safety guardrails locally. It is a smarter, faster way to keep coding agents grounded, keeping your development workflows safe and highly efficient.

📰 https://news.ycombinator.com/item?id=49104253

🆔 @hackernewsgithubprojects

📦 amirmushichge/tea-leaf-scroll-world

tea-leaf-scroll-world

Take your users on a beautiful, quiet ride through the mountains just by having them scroll down your web page. Tea leaf scroll world uses sleek scroll-driven animations to tell the story of a single tea leaf, from the misty peaks where it is harvested to the moment it is brewed in a cup. Built with modern React and Next, the project ties your scrolling speed to video playback, making you feel like you are actively moving the story forward. It is a brilliant example of how to make web storytelling feel tactile and immersive. Grab the code and build your own interactive journey today.

🆔 @hackernewsgithubprojects

📦 calf-ai/calfkit-sdk

calfkit-sdk

Software agents can now dynamically discover each other and collaborate at runtime without you having to write any complex wiring or orchestrators. That is the magic behind calfkit-sdk, a clever framework for building decentralized, event-driven multi-agent systems. Instead of hardcoding how your agents talk to one another, you plug them into a shared communication mesh. Once they are live, a general assistant agent can automatically find a specialized finance agent and hand off tasks on the fly. It is completely decentralized, runs on Kafka-compatible streaming infrastructure, and lets you build fluid, reactive agent teams that scale independently.

🆔 @hackernewsgithubprojects

📦 jakubkrehel/skills

Skills

Instantly level up your AI agents so they can critique and polish your web designs like a seasoned pro. The skills repository is a collection of drop-in guidelines and plugins for Claude Code and Codex that turn your AI assistant into a sharp design engineer. Instead of giving vague advice, it helps the AI review your projects for precise CSS spacing, focus states, and color contrast. It covers everything from making sure screen readers work properly to picking the right mobile keyboards. Just run one quick terminal command to install these rules, and your AI is ready to audit your code.

🆔 @hackernewsgithubprojects

📦 wutishummus/truedeck

TrueDeck

Run multiple AI coding agents side-by-side in real terminal interfaces without any of the exhausting setup. TrueDeck lets you load Grok, Codex, Claude, and Cursor onto the exact same project codebase simultaneously, arranging them into split-pane terminal views. Instead of babysitting markdown files, configuring memory dashboards, or dealing with complex Docker environments, this smart terminal hub automatically syncs shared project context and memory behind the scenes. You get to interact directly with the authentic developer command-line interfaces while it handles the plumbing, giving you a powerful, unified cockpit to build software alongside your favorite digital assistants.

📰 https://news.ycombinator.com/item?id=49092280

🆔 @hackernewsgithubprojects

📦 konghayao/peri

Peri Code

This single Rust binary runs a complete artificial intelligence programming agent using only thirteen megabytes of space and fifty megabytes of memory. Called peri, it is a lightning-fast, resource-friendly terminal companion that is fully compatible with Claude Code configurations while letting you bring your own keys for DeepSeek, Qwen, or Anthropic on the fly. It features auto-compacting memory management to keep long coding sessions cheap, alongside seven specialized background sub-agents that collaborate on complex tasks. You get a gorgeous terminal interface with live markdown streaming and cross-platform support. It is the ultimate lightweight coding harness that respects your machine.

📰 https://news.ycombinator.com/item?id=49105673

🆔 @hackernewsgithubprojects

📦 perplexityai/numbat

Numbat

Numbat is the endpoint monitoring tool that finally gives you complete visibility into what AI agents are doing on your local machines. Instead of letting terminal assistants or coding agents run wild in the background, this tool hooks directly into their local processes to watch every action they take in real time. It normalizes all agent behavior into a single, clean event stream and evaluates it against smart local rules. You can use it to scan past session logs, generate clear activity timelines, and even set up custom guardrails to block risky network requests or file changes before they happen. It runs entirely on device, keeping your sensitive prompts and...

📰 https://news.ycombinator.com/item?id=49105621

🆔 @hackernewsgithubprojects

📦 fractera/agent-engineering-infrastructure

agent-engineering-infrastructure

The self-hosted deployment engine that lets you run a complete online business on your own private server using nothing but chat. Instead of paying hefty fees to cloud platforms, agent-engineering-infrastructure sets up your operating system, secure web routing, and databases on a private server in just ten minutes. From there, it coordinates a collaborative team of digital helpers to handle coding, marketing, and sales tasks. The coolest part is a clever built-in optimizer that cuts token costs by up to ninety percent, stopping your context windows from ballooning. It is the perfect setup to build and manage projects privately without cloud vendor lock-in.

🆔 @hackernewsgithubprojects

📦 alibaba-nlp/qqr

Train Smart AI Agents with Tournaments

Even the best artificial intelligence agents get stuck when standard scoring systems stop giving useful feedback, causing their progress to stall on complex tasks. That is where qqr comes in, an clever reinforcement learning framework that trains agents through competitive tournaments instead of static scores. By pairing agents up to battle in swiss-system or double-elimination brackets, qqr evaluates them based on relative performance, keeping the learning curve steep even in open-ended domains like deep research and travel planning. It is lightweight, integrates with standard tool environments, and offers a brilliant way to keep your agents evolving. Check it out and let your models compete their way to the top.

🆔 @hackernewsgithubprojects

📦 h-embodvis/turbovla

TurboVLA

Most robotic brain models require massive, power-hungry language processors to translate what they see into physical movement, but turbovla runs in real time at over thirty hertz on a single consumer graphics card while sipping less than one gigabyte of video memory. Instead of routing camera feeds through a giant language model to predict actions, this clever system bypasses the middleman entirely. It independently processes visual inputs and text commands, lets them talk directly to each other through lightweight interaction, and spits out smooth robotic movements. It is an incredibly smart bypass that delivers high-end dexterity without needing a room full of server racks.

🆔 @hackernewsgithubprojects

📦 evolvent-ai/rsibench-data

RSI Bench Data

Test the real-world coding and reasoning skills of artificial intelligence models in isolated sandbox environments. This project gathers rigorous test sets, including math competitions and complex software engineering problems, and evaluates how systems perform when given direct tasks. Instead of relying on simple multiple-choice questions, it runs model outputs inside safe, virtual containers to see if their code actually works and solves the problem. It is a practical playground for testing next-generation machine reasoning. Explore these datasets to see how modern models handle genuine software bugs and logical challenges, and start building more reliable systems today.

🆔 @hackernewsgithubprojects

📦 zju-real/relay-opd

Relay-OPD

Relay-OPD is the open-source machine learning tool that prevents reasoning models from wandering off-track during training. When a student model starts making a logical mistake, standard training usually lets it spin out of control, wasting massive amounts of computer processing power. Relay-OPD fixes this by introducing a clever handoff trigger that detects exactly when a student model is starting to fail. A larger teacher model then briefly steps in like a relay runner to correct the path before handing control right back. This simple relay intervention cuts total training data length in half while dramatically boosting the final model's mathematical accuracy.

🆔 @hackernewsgithubprojects