📦 minimax-ai/mcode-stack

The Hidden Rules for Better AI Coding

Copy the exact daily habits the MiniMax Code team uses to keep their AI coding assistant sharp, straight into your own projects. It is not just a list of tips, but a set of ready-to-run checklists that tell your agent when to stop and think, how to keep long conversations from going stale, and exactly how to split up complex work. The coolest part is that you can install these specific routines in a single click, turning vague advice into concrete steps your code actually follows.

🆔 @hackernewsgithubprojects

📦 amiya-special/dynaflow

How to Make Your AI Hire a Team

DynaFlow lets a single large language model decide whether to answer a question on its own or spawn a team of specialized agents to handle the work. It solves the problem of rigid, pre-coded workflows by letting the AI dynamically figure out the best way to tackle complex tasks in real time. This is fascinating because it moves beyond simple chatbots into true autonomous orchestration, where the system builds its own problem-solving pipeline on the fly. It’s a glimpse into the future of software that adapts rather than following a fixed script.

🆔 @hackernewsgithubprojects

📦 gamesgamesgamesgamesgames/happyview

HappyView: Build Apps from Schemas

Build a fully functional server by simply uploading your data model. HappyView is a specialized tool for the AT Protocol that takes your schema definitions and automatically generates the necessary network endpoints, data storage, and security layers. Instead of spending weeks writing complex code to handle user logins, data syncing, and API routing, you describe your data once, and the system handles the heavy lifting instantly. This lets developers ship their applications much faster by focusing purely on their unique features rather than plumbing. If you are building on this network, this tool turns a massive infrastructure project into a simple configuration task.

🆔 @hackernewsgithubprojects

📦 apenwarr/atlogin

AtLogin: Sign into apps with your Bluesky account

Your Bluesky identity can now log you into almost any app. A project called AtLogin acts as a bridge, taking your decentralized handle and converting it into the standard login tokens that software like Tailscale or GitLab expects. No more creating new passwords; you just point your app to AtLogin, sign in with your Bluesky account, and you are in. It even offers a hosted option so you can skip the server setup entirely. It is a clever way to use the identity you already own everywhere. Just remember, it is still experimental, so test before trusting it with anything critical.

🆔 @hackernewsgithubprojects

📦 rzxvx/project-cascadia

Project Cascadia: Linux on the First iPad

Project Cascadia resurrects the original iPad mini by running native Linux directly on its A5 chip, a task no one has attempted before. The creator didn't just boot the kernel; they reverse-engineered Apple's obscure hardware to bring up Wi-Fi, touch controls, and even a working desktop environment. The real magic is in the debugging, where the developer found that the processor's second core was secretly powering itself off every time it idled, which was freezing the entire machine. By mimicking how Apple's own system handles that power state, they got both cores working together.

🆔 @hackernewsgithubprojects

📦 gammons/slk

slk: Your Terminal Slack

Your terminal just got a full Slack replacement that fits in under twenty megabytes. It’s called slk, and it’s a single, static binary that boots in milliseconds. Forget the sluggish desktop app eating a gigabyte of your memory. This one runs natively in your terminal, using only the keyboard. You get live messages, threads, and even inline images, all driven by vim-style shortcuts. It’s fast, tiny, and completely under your control. If you live in your terminal, this is your new daily driver.

🆔 @hackernewsgithubprojects

📦 google-deepmind/detectorscope

DetectorScope: AI Detectors That Show Their Work

Stop guessing why an AI detector flags your text. DetectorScope from Google DeepMind flips the script by making every decision fully transparent. Instead of a black box just saying yes, it breaks the verdict down into a simple list of specific traits, like repeated phrases or certain word patterns, and shows you exactly where they appear in your writing. This means you can finally see the actual evidence behind the prediction rather than just taking it on faith. It is a clever way to audit these models and understand exactly what triggers them.

📰 https://news.ycombinator.com/item?id=50222061

🆔 @hackernewsgithubprojects

📦 coretechr/picolab

PicoLab: The Pocket Debugging Lab

PicoLab is the open-source firmware that turns a tiny Raspberry Pi Pico into a full-featured debugging laboratory. It is the only tool that serves a complete graphical interface directly from the microcontroller itself, meaning you do not need to install a single driver or run heavy desktop software to get started. By creating a virtual network connection over the USB cable, the chip acts like a local web server, pushing live data from an oscilloscope, logic analyzer, and adjustable power supply straight to your browser.

🆔 @hackernewsgithubprojects

📦 shyftlabs/continuum

Continuum: Ship AI Agents That Actually Work

Stop bolting on memory and crash recovery with brittle glue code. Continuum gives you a single, type-safe place to build AI agents that remember things, route work to the cheapest smart model, and keep running even if your server dies. It handles the messy stuff like tracking every token and letting agents hand off jobs to each other without losing context. If you are tired of debugging why your bot forgot what you said ten minutes ago, this is your fix. It turns fragile prototypes into reliable, enterprise-grade tools that you can actually ship to production.

🆔 @hackernewsgithubprojects

📦 rightbrain-networks/mnemonic

How to Manage Your AI Coding Agents With Mnemonic

Keep track of what your AI coding agents actually do with Mnemonic, a self-hosted tool that stops temporary chat sessions from forgetting critical context. Instead of losing important decisions in messy scratch files, it stores every task and choice in a durable graph that survives restarts. The coolest part is that it lets you see exactly which code was built based on specific human decisions. If you change your mind later, you immediately know which parts of your project need updating. It is built for experienced engineers who want real control over their AI workflow. Stop letting your agents forget, and start building with actual memory.

🆔 @hackernewsgithubprojects

📦 majiayu000/awesome-grok-bot

Awesome Grok Bot: The Ultimate Directory for AI Agents

Awesome Grok Bot is the curated directory that turns scattered agent shares into a searchable library of real digital coworkers. It catalogs thousands of live configurations for Grok Bot, an always-on AI teammate that operates a shared cloud computer. The standout feature is its field cases section, which documents how real people actually deploy these agents for specific tasks like inbox management and research. This approach distinguishes the catalog from generic prompt dumps by showcasing verified workflows. You can browse by job category to find a pre-built setup, preview it, and add it to your own account in seconds.

🆔 @hackernewsgithubprojects

📦 licoy/strokemouse

StrokeMouse: The Mac Mouse Gesture Hack

Your Mac mouse button is now a secret remote control for your entire computer. StrokeMouse is a tiny menu bar app for Mac that turns the physical act of drawing shapes with your mouse into instant shortcuts. Hold down your right mouse button and scribble a simple curve, like an up arrow or a circle, and the app instantly recognizes that shape to trigger commands like opening Safari, minimizing windows, or running custom scripts. It’s like adding a hidden layer of automation to your hardware without any new buttons. The coolest part is that it feels like you’re hacking your own system.

🆔 @hackernewsgithubprojects

📦 lambdahumanoid/openlambda

Openlambda: Teaching Robots by Watching Humans

Openlambda turns everyday human video into a foundation model for humanoid robots that learn to walk and grab objects. Instead of expensive robot-only demos, it trains on first-person footage of people moving, using a three-stage learning process to map human motion to robot actions. This solves the data bottleneck for generalist humanoid control, letting machines learn real-world skills from cheap, open-world human experience. The result is a versatile base for building robots that can adapt to new tasks without starting from scratch. It’s a practical step toward robots that learn like we do.

🆔 @hackernewsgithubprojects

📦 oosexgang/hakios-xnu-kernel

HakiOS: The XNU Kernel Running on Android

HakiOS is the experimental setup that actually boots real iOS on an Android phone. It takes the open-source XNU kernel, adds a custom boot loader, and runs the standard iOS user space on a Qualcomm chip. The coolest part is that it does not flash anything to your device. Everything lives in memory during the session, so a simple reboot returns the phone to its normal Android state. This makes it a perfect research bench rather than a risky permanent change. You get to see the lock screen and apps working on hardware that was never meant for them.

🆔 @hackernewsgithubprojects

📦 sheltercosmo/rilldex-rl-studio

How to See Inside an AI Agent

Rilldex RL Studio is the observability suite that finally shows you how an AI agent actually works during training. It stops the mystery of the black box by turning raw training data into clear visual maps of every action, retry, and decision your model makes. You can watch exactly where the agent gets stuck or goes off track, linking those behaviors directly to the performance metrics from your training run. This connects the dots between the numbers and the actual work, helping you fix problems much faster than staring at loss curves ever could. It turns invisible machine learning processes into a clear, inspectable story you can actually read.

🆔 @hackernewsgithubprojects

📦 leggedrobotics/defm

DeFM: Depth Foundation Model

A neural network now learns to understand the three-dimensional world purely from depth sensors, skipping the usual need for colored photos entirely. DeFM is a vision model trained on sixty million depth images that teaches computers to recognize objects and navigate spaces using only distance data. This is huge for robotics because it allows machines to perceive their environment accurately in any lighting condition, even total darkness, without needing a separate camera for every task. It essentially gives robots a universal sense of space that works across different sensors and real-world settings.

🆔 @hackernewsgithubprojects

📦 diffuspace/clover-35b-a3b-preview

Clover: The Diffusion Model Breakthrough

Clover is the open-source language model that generates text using a completely different engine. While standard A.I. predicts words one after another, this model paints the whole sentence in blocks, refining it like a picture until it makes sense. That is a massive shift in how machines create language. It packs thirty-five billion parameters but only activates three billion per token, making it efficient enough to run on a single graphics card. If you have ever wondered what text diffusion actually looks like in practice, this is your chance to see it. It is fast, it is open, and it is built to be tinkered with.

🆔 @hackernewsgithubprojects

📦 datalab-to/omni_parse_bench

Omni Parse Bench: The Truth About Your Document Parser

Your fancy AI document parser just choked on a single spreadsheet. That’s exactly what Omni Parse Bench is built to catch. This project stops us from guessing how well these tools actually work by slapping over sixteen thousand specific yes-or-no checks onto nearly three thousand real pages. It doesn’t just ask if the text is there. It verifies if the table structure survived, if the math holds up, and if the layout stayed sane. You get one clear number per system that tells you exactly where it fails and what that failure costs you in real dollars.

🆔 @hackernewsgithubprojects

📦 emanuele-em/kanzo

Kanzo: The Kanban Board for AI Agents

Kanzo is the self-hosted kanban board that finally lets your coding agents work alongside you. It is a single four megabyte binary that runs on your own computer, meaning no servers and no accounts to manage. The coolest part is that it acts as a bridge between you and your AI tools. Your coding agents can grab tasks, move them to doing, and even comment on their progress directly on the board. You can watch them work in real time from your browser. It’s like having a shared to-do list where humans and robots actually collaborate.

🆔 @hackernewsgithubprojects

📦 typetheoryforall/fvjobs

FVjobs: The Job Board for Formal Verification

FVjobs tracks seventeen open roles in formal verification, a niche field where the most surprising fact is that it specifically records which proof stack each job uses, like Lean or Isabelle, so you know exactly if your skills match. The project solves a real problem: formal verification jobs are usually scattered across academic lists and general boards that have no idea what a theorem prover is. This board collects them in one place, telling you the proof tools required and whether you are legally allowed to take the role from your location. It is useful because it removes the guesswork from applying to a specialized job.

🆔 @hackernewsgithubprojects