📦 patlux/pi-commandcode-provider

Pi Command Code Provider

You can plug eighteen different AI models, including Claude, GPT, and DeepSeek, directly into your Pi coding agent using a single plugin. Pi Command Code Provider acts as a bridge, letting you pick any model from the Command Code API without managing separate keys or complicated setup. It handles the connection automatically, so you can swap between different thinking styles on the fly. This is perfect for developers who want flexibility without the headache of juggling multiple subscriptions. If you use Pi, this is the easiest way to access top-tier models right in your terminal.

🆔 @hackernewsgithubprojects

📦 mindbox77/zxdesk

A Full Desktop for a 1982 Computer

A full graphical desktop with draggable windows, menus, and a working calendar fits inside forty-eight kilobytes of RAM on a computer from 1982. This project, called ZX Desk, proves that a machine with a three and a half megahertz processor can handle overlapping windows and a file manager. The author wrote this in Z80 assembly to recreate the feel of a classic desktop environment, but without emulators. It runs on real hardware, meaning every single byte of memory is accounted for. The real magic here is the engineering required to make dragging a window smooth on such slow hardware.

📰 https://news.ycombinator.com/item?id=49766676

🆔 @hackernewsgithubprojects

📦 ganyuanran/aegis

Aegis: The Safety Net for AI Coding

Your AI coding agent just stopped guessing at your code and started proving it works. Aegis is a method pack that turns your coding assistant into a disciplined engineer, ensuring it checks your project’s real baseline before making changes and only marking work complete when it has fresh evidence. In rigorous tests, this simple rule reduced unsafe outcomes from thirteen percent to zero. It doesn’t force heavy process on simple tasks, but for complex work, it demands proof before saying done. If you want to stop babysitting your agent and start trusting its results, this is the safety net you need.

🆔 @hackernewsgithubprojects

📦 amal-david/awesome-jev

Awesome Jev: The Curated Hub for Typed AI Decisions

Discover forty-four real-world projects built with Jev, a tool that answers questions about data with yes or no probabilities instead of writing text. This curated collection solves the problem of finding out what people are actually using this unique technology for. It is useful because it links directly to the source code and includes a gallery of demos. You can see Jev choosing browser actions, scoring log entries, or even playing chess against a shared board. The repository helps you understand where a dedicated classifier fits better than a large language model. It is a great starting point for anyone curious about how structured decision-making works in modern applications.

📰 https://news.ycombinator.com/item?id=49802160

🆔 @hackernewsgithubprojects

📦 learnprompt/awesome-seedance

Awesome Seedance: 463 Verified Video Prompts

Four hundred and sixty-three AI video prompts, every single one traced back to the exact post where the creator first shared it, and then stress tested across different models to prove they actually work. That is the core promise of Awesome Seedance, a library built specifically for Seedance video generation. Most prompt collections are just recycled text you find in forums, but this repository only accepts entries where the original media matches the prompt exactly, and if a prompt fails when re run, that failure is logged publicly. You get a verified source rather than a guess.

🆔 @hackernewsgithubprojects

📦 stepfun-ai/step-code

Step Code: The Terminal Agent That Publishes Websites

Hand off a complex coding goal to Step Code and walk away. This open-source tool lives in your terminal, reading your code, writing changes, and running tests all at once. The coolest part? It doesn't just build your app; it publishes your local project as a live, shareable website with a single command. It handles the whole loop from development to delivery right in your command line. If you want an AI assistant that actually ships finished work, not just snippets, Step Code is built for that. It turns your terminal into a complete, autonomous development studio.

📰 https://news.ycombinator.com/item?id=49817387

🆔 @hackernewsgithubprojects

📦 amd-agi/hyperloom

Hyperloom: The AI Tuner for AMD GPUs

Hyperloom acts like an automated performance tuner that watches your AI models run on AMD graphics cards to find and fix slow spots before they become bottlenecks. Instead of you manually tweaking complex settings, the system analyzes the workload and applies optimizations on its own to make everything run faster. It is essentially a tireless assistant that constantly refines how your data flows through the hardware, saving you hours of tedious debugging. If you are running large language models and want them to fly without spending your weekend on manual tuning, this tool does the heavy lifting for you.

📰 https://news.ycombinator.com/item?id=49817617

🆔 @hackernewsgithubprojects

📦 smartcomputer-ai/lightspeed

Lightspeed: The Agent Harness That Actually Scales

Lightspeed is the deterministic agent harness that finally lets you run thousands of A.I. agents on a single machine without the cost blowing up. Most agent setups trap the brain inside a full operating system, meaning you have to spin up a whole virtual machine for every single task, even if it only needs three seconds. That is slow, expensive, and hard to secure. Lightspeed flips this by separating the agent's core logic from the actual compute. The thinking runs as a lightweight, durable workflow that survives restarts and stays cheap when idle.

📰 https://news.ycombinator.com/item?id=49817634

🆔 @hackernewsgithubprojects

📦 netease-youdao/confucius4-r2t2

The Speech Model That Never Backtracks

Confucius Four R-two-Two writes down words as they are spoken, then locks them in place, meaning the text never flickers or changes later. Most live captioning systems constantly rewrite what they just said, which feels janky and makes it impossible to feed that text into other tools instantly. This model from NetEase solves that by committing to its output, giving you a clean, stable stream of text with almost no delay. It’s built for people who need real-time subtitles or live translation that actually works without constant corrections. It’s fast, accurate, and open, making it a surprisingly solid choice for anyone building real-time audio apps.

🆔 @hackernewsgithubprojects

📦 prismorsec/prismor

Prismor: The Security Guard for AI Agents

Prismor intercepts AI agent tool calls in real time to block dangerous actions like secret leaks or prompt injections before they execute. It acts as a self-hosted control plane that sits between your coding agent and your machine, inspecting every command to catch malicious redirects or destructive mistakes. The project is agent-agnostic, meaning it works with Claude, OpenAI, and LangChain without needing you to rewrite your entire workflow. It runs a local dashboard where you can switch between just watching the agent or actively blocking it, giving you the power to audit what your AI is actually doing.

🆔 @hackernewsgithubprojects

📦 netease-youdao/confucius4-t3po

Confucius4-T3PO: Real-Time Translation Without Waiting

Confucius4-T3PO translates text the instant it appears, rather than waiting for a full sentence to finish. It works like a live interpreter, deciding for every tiny chunk of input whether to pause for more context or immediately output a translation. This model uses a clever reinforcement learning trick to balance speed and accuracy, so you get high-quality results without the lag of traditional tools. It is built for real-time apps where waiting is not an option, and it even keeps its general smartness intact for future upgrades. If you are building live translation features, this is the engine that makes it feel instant and natural.

🆔 @hackernewsgithubprojects

📦 colingpt9/clips-studio

Clips Kitty: AI Clipping on Your PC

Clips Kitty is the open-source clip generator that keeps your footage on your own computer. Instead of uploading long streams to a cloud server to find highlights, this app runs a local artificial intelligence model directly on your machine. It scans your videos to find the best moments, automatically crops them to a vertical format, and even tracks who is speaking to keep them centered in the frame. This means you can turn hours of content into ready-to-post shorts without paying any subscription fees or uploading sensitive data. It is built specifically for creators who want full control and no hidden costs.

📰 https://news.ycombinator.com/item?id=49504646

🆔 @hackernewsgithubprojects

📦 qiz029/dscode

DS Code: Agents that talk to each other

DS Code flips the usual coding agent script by letting multiple sessions on your machine see and talk to each other. Instead of working in isolation, one agent can hand a task to another, share results, or have an independent reviewer check its work before you approve it. This means complex jobs get split up and verified automatically, while you keep full control over what actually gets done. It is a powerful way to manage heavy coding tasks without losing track of the details, making your workflow smarter and more collaborative than any single chatbot could offer.

🆔 @hackernewsgithubprojects

📦 offgridpete/fieldwatch

Fieldwatch: Your Phone's Hidden Radar

Turn your Android phone into a passive scanner for the invisible radio signals cluttering your environment. Fieldwatch listens to Wi-Fi and Bluetooth broadcasts without ever sending data back to a server, giving you complete control over what you detect. The coolest part is the signature engine, which identifies specific devices like roadside cameras or drone controllers by matching their unique digital fingerprints. It is a totally offline tool for anyone curious about what is actually broadcasting around them, whether for privacy checks or just pure technical curiosity. No accounts, no cloud, just your phone and the airwaves.

🆔 @hackernewsgithubprojects

📦 dat999zx/knowl

Knowl: The Self-Cleaning Memory for AI

Knowl solves the one thing that makes AI coding assistants feel like they have amnesia: they forget everything you told them once the chat window closes. Instead of stuffing every fact into a growing file that eventually contradicts itself, Knowl stores facts in a local database and automatically retires the old ones when new information arrives. So when you switch databases, the tool quietly deletes the outdated decision and keeps only the current truth. It runs entirely on your machine with zero cloud dependency, meaning your code and context never leave your computer.

📰 https://news.ycombinator.com/item?id=49399942

🆔 @hackernewsgithubprojects

📦 shhivv/third-hand

Third Hand: The macOS Assistant That Actually Works

Third Hand is the Mac menu bar tool that finally lets you talk to your computer like a person. It sits quietly in your top bar, ready to snap into action with a simple keyboard shortcut. Once triggered, it reads the buttons and text currently visible on your screen to figure out exactly what to do next. It can type, click, and verify its own work, turning vague requests into specific actions. It uses a smart decision model to pick the right moves, all without needing heavy local hardware.

🆔 @hackernewsgithubprojects

📦 display-dev/visualize

visualize

AI coding agents can now generate HTML artifacts that look exactly like the brand you specify. The visualize project solves a common annoyance where machine generated web pages often feel generic or lack a specific aesthetic identity. It works by feeding the agent a library of design systems, which are essentially style guides describing how a particular company like Stripe or Apple designs their interfaces. This allows the AI to match fonts, colors, and layouts to a specific brand identity rather than just making a functional page. It is a clever way to add visual consistency to automated workflows.

🆔 @hackernewsgithubprojects

📦 qunqin24/pulse

Pulse: The Floating AI Usage Monitor

Pulse is a small floating app that sits quietly on your Mac screen and shows exactly how much of your AI coding subscriptions you have left. If you use tools like Claude Code or Codex, you probably know the anxiety of not knowing if your limit is about to run out. Pulse solves this by creating little rings on your screen that change color as you use more, turning red when you are close to the limit. It reads the data directly from your existing logins, so you don't need to set up new accounts or enter API keys.

🆔 @hackernewsgithubprojects

📦 fajarhide/omni

Omni: Stop Paying for Duplicate Data

Stop making your AI pay for data it has already read. Omni solves a sneaky problem: every time your agent checks a file it has seen before, it burns tokens on that exact same text again. This tool intercepts those repeated reads and swaps them for a tiny, unique tag. If the model needs the full details later, it simply asks for them back. The result? A massive drop in token usage without losing any context. It is not magic; it is just smart memory management that keeps your bills low. Your code stays safe, your context stays clean, and you stop wasting money on repetition.

🆔 @hackernewsgithubprojects

📦 bidthedog/throng

The Terminal Workspace That Won't Die When You Close It

This app keeps your command line sessions running even after you close the window. It is called throng, and it was built to stop developers from drowning in a dozen different terminal windows and scattered files. You open a project, and throng gives you a single workspace where you can dock terminals, split them up, and drag them around like tabs in a browser. The magic is that those terminals run on a background process that stays alive. So, if you accidentally close the app, your work is not lost. When you reopen it, everything is exactly where you left it, still running and still waiting for your input.

🆔 @hackernewsgithubprojects