📦 aidenai-io/aiden-firmware

Aiden Firmware: The AI Hardware That Controls Your Phone

Aiden Firmware turns a small Linux computer into a voice-controlled operator that physically drives your mobile phone. It solves the gap between cloud-based chatbots and local hardware by running a full agent loop directly on the device. The standout feature is its human handoff, which detects when the AI is stuck and passes control back to you seamlessly. This repo contains the entire C++ and Go source code needed to build this autonomous hardware. If you want to see how AI actually interacts with the physical world, this is your blueprint. Grab the code, flash the board, and let the machine do the tapping.

🆔 @hackernewsgithubprojects

📦 aetherlabsai/rsiagent

R S I Agent: How AI Learns Without Training

R S I Agent lets a computer figure out how to use new software without ever updating its brain. Instead of memorizing instructions through heavy training, three separate digital workers explore a fresh environment, test their actions, and save useful lessons into a shared notebook. This notebook stays fixed while the agent tackles real tasks, allowing it to improve performance by simply recalling past experiences. It works by first exploring broadly to gather general knowledge, then digging deeper into tricky details to solidify that memory. The result is an agent that gets better at using software just by thinking and trying, not by being retrained.

🆔 @hackernewsgithubprojects

📦 rsasaki0109/visloc-rs

The Rust Library for Drone Navigation Without GPS

This Rust library figures out exactly where a robot is by looking around, even when GPS signals are completely gone. It takes ordinary camera photos and motion sensor data to build a detailed three-dimensional map of the surroundings in real time, a process called simultaneous localization and mapping. Most tools for this job are slow or require expensive hardware, but this one runs entirely on standard computer processors with no special graphics cards needed. It also processes thousands of images faster than the industry standard, making it a powerful tool for developers building autonomous drones and ground robots.

🆔 @hackernewsgithubprojects

📦 iamkaleemsajjad-hue/aether

Aether: Run Any AI Model on Any Hardware

Compile an AI model once and run it on any hardware, from your phone to a massive data center server, without rewriting a single line of code. That is the core promise of Aether. It takes standard open-source models and converts them into a universal execution format that automatically adapts to whatever chip is available, whether it is a standard processor or a specialized graphics card. The surprising part is that this process happens entirely on your own machine without needing expensive cloud services or proprietary software. In rigorous tests against major industry standards, Aether delivered significantly faster response times and lower memory usage across the board.

🆔 @hackernewsgithubprojects

📦 haoruilee/awesome-agent-native-services

Awesome Agent-Native Services

One of the most surprising things about modern A.I. agents is that they can actually join online services using just a single sentence. The project called Awesome Agent-Native Services is a curated directory of tools built specifically for A.I. agents, not for humans. It covers everything from email to memory systems. The key feature here is called Url Onboarding. This means an agent can read a single link and automatically register itself for a service without any human help. This repository explains exactly how this works and lists the services that support it. It is a clear guide to the new world of A.I. infrastructure.

🆔 @hackernewsgithubprojects

📦 cosmosmind-ai/rsi-harness

How RSIH turns AI habits into code

RSIH is the agent harness tool that finally makes your custom AI setups versionable and shareable. It wraps the Pi coding agent with a configuration layer called Genome, turning your scattered prompts, tools, and rules into a single, portable folder. The coolest part is its GEE engine, which analyzes your actual past sessions to automatically generate a new harness based on what you really do, not what you think you want. You get a working setup that captures your specific workflow, ready to run locally or send to a friend. No more losing your perfect prompt tweaks when switching machines.

🆔 @hackernewsgithubprojects

📦 john-rocky/coreai-kit

CoreAIKit Runs AI Locally on Your Phone

A small language model that weighs less than a phone photo can now live entirely on your device, answering questions without a single data packet leaving the building. CoreAIKit is a Swift tool that lets developers drop these private models directly into iPhone and Mac apps, handling the heavy lifting of downloading and storing the files automatically. It solves the privacy headache of cloud services by keeping your chats, voice memos, and photos safe on the hardware you already own. You get real time intelligence for things like meeting notes or image searches, all running silently in the background.

🆔 @hackernewsgithubprojects

📦 alchaincyf/huashu-report

The Science Behind High-End Reports

Huashu report is built on precise measurements taken from forty-one actual research documents produced by major institutions like McKinsey and the World Bank. Instead of guessing what makes a document look professional, this project reverse-engineers the exact typography, spacing, and data structures found in those successful examples. It turns those measurements into a reusable set of rules and automated tools that ensure every number has a clear source and every layout flaw is caught automatically. This solves the problem of inconsistent quality by providing a verified baseline for anyone producing high-stakes documents.

🆔 @hackernewsgithubprojects

📦 turanmahmudov/masume

Masume: Your Terminal Database Copilot

Masume is the terminal database client that finally lets you chat with your data directly from the command line. It is a keyboard-first tool for working with databases like PostgreSQL and MongoDB, but the coolest part is the built-in AI assistant. Instead of guessing at syntax or debugging errors alone, you can ask the AI to explain a complex query or help you fix a broken statement right inside your terminal. It even acts as a server for other AI tools, making your database accessible to external agents safely. This means you get a smart, interactive helper for your data work without leaving your favorite environment.

🆔 @hackernewsgithubprojects

📦 joshhhhhan/vista

VISTA: The AI Agent With Perfect Vision

VISTA, created by researchers at the Massachusetts Institute of Technology, lets artificial intelligence models see every single frame of a game they are playing, allowing them to look back at past evidence when they are stuck on a problem. This visual memory system is so effective that it achieved a perfect one hundred percent win rate on all twenty-five public games in the A R C A G I three benchmark. The project solves a major challenge in artificial intelligence where agents often forget what they saw earlier in a task, causing them to make poor decisions based on incomplete information.

🆔 @hackernewsgithubprojects

📦 hruiccc/ruic-card-skill

RuiC Card Skill: 3D Holographic Cards from One Sentence

RuiC Card Skill is the creative tool that turns a single sentence into a physical-feeling 3D holographic card. Instead of manually modeling complex materials, this system generates a fully interactive web page where your card floats in space. The most surprising part is that it gives you an actual editable Blender file, so you can adjust the lighting and layers yourself. It solves the problem of needing expensive software to create realistic, shimmering collectible cards. You get a live website where you can drag, tilt, and zoom the card to see the light shift across the surface.

🆔 @hackernewsgithubprojects

📦 stratcraftsai/nexusfix

NexusFix: The Engine That Never Allocates

NexusFix parses a single trading message without asking the computer for new memory even once. This C plus plus tool is built for high-frequency trading where every nanosecond of delay costs real money. It reads standard financial data directly from the network buffer without copying a single byte into a new spot. By doing the heavy lifting at compile time instead of runtime, it skips all the slow guesswork typical engines rely on. The result is a parser that runs three times faster than the industry standard. If you are building systems where speed is everything, this is the engine to watch.

📰 https://news.ycombinator.com/item?id=47520153

🆔 @hackernewsgithubprojects

📦 kevinnbass/metr-money-figure

The Invisible Money: METR Money Figure Explained

metr-money-figure is the data investigation that maps the hidden financial links between METR and Anthropic. It solves the problem of opaque funding in AI safety by tracing money flows that never appear in direct grant records. Instead of relying on simple donations, this project reveals how investors in Anthropic funnel funds to METR through parent organizations and shared partners. This matters because it exposes the structural ties between the organizations evaluating AI labs and the labs they are meant to judge. You will see exactly where the money goes and who benefits. This transparency is essential for anyone following the real independence of AI oversight.

🆔 @hackernewsgithubprojects

📦 ninnix/q36

Run AI on a $150 Computer

QuarkStar is the inference engine that turns a one-hundred-fifty-dollar computer into a local AI powerhouse. Instead of relying on cloud services or expensive workstations, it runs massive language models directly on your cheap hardware using a specialized Vulkan backend. The killer feature is how it streams model weights from your solid-state drive into a small cache, allowing you to run a huge, capable model on a machine with only sixteen gigs of memory. It even includes a built-in coding agent that works entirely offline, meaning your data never leaves your desk.

🆔 @hackernewsgithubprojects

📦 alchaincyf/3d-vibe-coding-handbook

3D Vibe Coding Handbook

3D Vibe Coding Handbook is the interactive companion that turns abstract coding concepts into tangible, spinning mechanical reality. It serves the official HTML version of the handbook alongside a gallery of working web demos, such as a fully functional four-stroke engine. The standout feature here is the engine simulation, which you can physically disassemble, rotate, and even reassemble in a strict, real-world order to truly understand how the parts interact. It is not just a static diagram, but a playable laboratory for spatial reasoning. Grab this repository to see exactly how code builds complex, interactive 3D systems that actually work.

🆔 @hackernewsgithubprojects

📦 ahernresearch/grava

How GRAVA Makes Self-Driving Cars Think

Self-driving cars can now show their work by linking what they see to the exact steering move they make. This new framework, called GRAVA, solves a major mystery in autonomous vehicles: why does the car brake or turn? Instead of just outputting a command, the system builds a clear connection between visible objects and the final driving action. It uses a single model to describe the scene and then directly generates the physical path the car will take. This transparency is critical for trust and safety. As the code and data roll out, we finally have a way to see the logic behind the wheel.

🆔 @hackernewsgithubprojects

📦 ziqin-h/3dway

3DWay: Turning 2D Images into 3D Robot Moves

A vision-language model now plans robot movements by predicting 2D waypoints in two camera views, then uses simple geometry to reconstruct a precise 3D path. This project, called 3DWay, solves the tricky problem of getting a language-based AI to control a physical robot arm without noisy depth sensors. By letting the AI reason in its native image space and letting math handle the 3D conversion, it creates reliable trajectories that work on real robots. It’s a clever way to bridge the gap between digital reasoning and physical action, making robot control more general and less dependent on specialized hardware.

🆔 @hackernewsgithubprojects

📦 omni-interaction-gander/omni-interaction-agent

Gander: Talk While It Works

Delegate a heavy task and keep talking, interrupting, or sharing your screen while the agent keeps working. Gander is an open-source voice assistant that doesn't pause to listen; it hears, sees, and thinks all at once. Most bots freeze while they process, but Gander lets you redirect it mid-sentence or show it your screen without stopping the job. It runs on a split brain, with one part handling real-time chat and another crunching the long, hard tasks in the background. You can just chat naturally, like a friend, while it figures out the details. It’s a cool look at how future assistants might actually behave.

🆔 @hackernewsgithubprojects

📦 vaderchen/yourdesk

YourDesk: The AI Remote Desktop

YourDesk lets an AI agent physically drive your computer. Built in Go for Mac and Windows, this cross-platform tool handles the heavy lifting of video streaming and screen input so your software assistant can click, type, and navigate just like a human. It is not a basic screen viewer; it is a direct control channel for your favorite AI models. Because the code is open and free to use for internal work, developers can build on it without licensing headaches. If you are building autonomous tools, this is the bridge between the language model and the actual machine. Give your AI hands, not just a brain.

🆔 @hackernewsgithubprojects

📦 keesan12/martin-loop

MartinLoop: The Safety Net for AI Coding Agents

MartinLoop stops AI coding agents from spiraling out of control. When an AI tries to fix code, it can accidentally run endless loops that burn through your money without finishing the job. This project wraps the agent in a safety net that sets a hard limit on spending and checks the work against real tests before calling it done. If the agent fails, the system rolls back the changes so your code stays safe. You get a clear receipt showing exactly what happened and why it stopped. It turns a risky guess into a proven, reviewable result.

📰 https://news.ycombinator.com/item?id=48098126

🆔 @hackernewsgithubprojects