Show HN за 21 марта 2026 г.

I’ve been building termcraft, a terminal-first 2D sandbox survival game in Rust.

The idea is to take the classic early survival progression and adapt it to a side-on terminal format instead of a tile or pixel-art engine.

Current build includes: - procedural Overworld, Nether, and End generation - mining, placement, crafting, furnaces, brewing, and boats - hostile and passive mobs - villages, dungeons, strongholds, Nether fortresses, and dragon progression

This is still early alpha, but it’s already playable.

Project: https://github.com/pagel-s/termcraft

Docs: https://pagel-s.github.io/termcraft/

Demo: https://youtu.be/kR986Xqzj7E

I finally built this app after many years of being sick of unlocking my phone every goddamn time I need to take or view my notes. It particularly sucks when I'm doing my grocery and going down the list.

I started building last year June. This is a native app written in Kotlin. And since I'm a 100% Web dev guy, I gotta say this wouldn't have been possible without this AI to assist me. So this isn't "vibe-coded". I simply used the chat interface in Gemini website, manually copy paste codes to build and integrate every single thing in the app! I used gemini to build it just because I was piggybacking on my last company's enterprise subscription. I personally didn't subscribe to any AI (and still don't cuz the free quota seems enough for me :)

So I certainly have learnt alot about Android development, architecture patterns, Kotlin syntax, and obeying Google's whims. Can't say I love it all, but for the sake of this app, I will :)

Anyway, I finally have the app I wish existed, and I'm using it everyday. It not only does the main thing I needed it to do, but there's also all this stuff:

- Make your notes private if you don't want to show them on lock screen. - Create check/to-do lists. - Set one time or recurring reminders. - Full-text search your notes in the app. - Speech-to-text. - Organize your notes with custom or color labels. - Pin the app as a widget on your home screen. - You can auto backup and restore your notes on new install or Android device. - Works offline. - And no funny business happening in the background https://joonote.com/privacy

It's 30-day trial, then a one-time $9.99 to go Pro forever.

I would love you all to check it out, FWIW.

Ok thanks!

Short answer: yes.

The Emotion Engine has 32 MB of RAM total, so the trick is streaming weights from CD-ROM one matrix at a time during the forward pass — only activations, KV cache and embeddings live in RAM. This means models bigger than the RAM can still run, they just read more from disc.

Had to build a custom quantized format (PSNT), hack endianness, write a tokenizer pipeline, and most of the PS2 SDK from scratch (releasing that separately). The model itself is also custom — a 10M param Llama-style architecture I trained specifically for this.

And it works. On real hardware.

I built an open-source repo template that brings structure to AI-assisted software development, starting from the pre-coding phases: objectives, user stories, requirements, architecture decisions.

It's designed around Claude Code but the ideas are tool-agnostic. I've been a computer science researcher and full-stack software engineer for 25 years, working mainly in startups. I've been using this approach on my personal projects for a while, then, when I decided to package it up as scaffold for more easy reuse, I figured it might be useful to others too. I published it under Apache 2.0, fork it and make it yours.

You can easily try it out: follow the instructions in the README to start using it.

The problem it solves:

AI coding agents are great at writing code, but they work much better when they have clear context about what to build and why. Most projects jump straight to implementation. This scaffold provides a structured workflow for the pre-coding phases, and organizes the output so that agents can navigate it efficiently across sessions.

How it works:

Everything lives in the repo alongside source code. The AI guidance is split into three layers, each optimized for context-window usage:

1. Instruction files (CLAUDE.md, CLAUDE.<phase>.md): always loaded, kept small. They are organized hierarchically, describe repo structure, maintain artifact indexes, and define cross-phase rules like traceability invariants.

2. Skills (.claude/skills/SDLC-*): loaded on demand. Step-by-step procedures for each SDLC activity: eliciting requirements, gap analysis, drafting architecture, decomposing into components, planning tasks, implementation.

3. Project artifacts: structured markdown files that accumulate as work progresses: stakeholders, goals, user stories, requirements, assumptions, constraints, decisions, architecture, data model, API design, task tracking. Accessed selectively through indexes.

This separation matters because instruction files stay in the context window permanently and must be lean, skills can be detailed since they're loaded only when invoked, and artifacts scale with the project but are navigated via indexed tables rather than read in full.

Key design choices:

Context-window efficiency: artifact collections use markdown index tables (one-line description and trigger conditions) so the agent can locate what it needs without reading everything.

Decision capture: decisions made during AI reasoning and human feedback are persisted as a structured artifact, to make them reviewable, traceable, and consistently applied across sessions.

Waterfall-ish flow: sequential phases with defined outputs. Tedious for human teams, but AI agents don't mind the overhead, and the explicit structure prevents the unconstrained "just start vibecoding" failure mode.

How I use it:

Short, focused sessions. Each session invokes one skill, produces its output, and ends. The knowledge organization means the next session picks up without losing context. I've found that free-form prompting between skills is usually a sign the workflow is missing a piece.

Current limitations:

I haven't found a good way to integrate Figma MCP for importing existing UI/UX designs into the workflow. Suggestions welcome.

Feedback, criticism, and contributions are very welcome!

Hi HN,

I’m working on Skillware, an open-source framework that treats AI capabilities as installable, self-contained modules.

I just added a "Prompt Token Rewriter" skill. It’s an offline heuristic middleware that strips conversational filler and redundant context from long agentic loops before they hit the LLM. It saves significant token costs and inference time, and it's 100% deterministic (no extra model calls).

We're building a registry of "Agentic Know-How" (Logic + Cognition + Governance). If you have a specialized tool for LLMs or want to see what a "standard" skill looks like, I'd love your feedback or a PR:

https://github.com/ARPAHLS/skillware

In this release you can now filter by categories. As the vast majority of apps do not specify categories, I will progressively add them manually.

Classic Video Poker (CVP) is a lightweight, browser-based retro video poker game which originally hit the front page of HN on Oct 4, 2023: https://news.ycombinator.com/item?id=37763098

I've finally managed to release version 2. The delay was mostly due to fear of upsetting the user base with breaking changes.

Version 2 includes:

- Frictionless accounts: added registration so you can save progress but no personal info or email.

- Deep play stats: Track lifetime RTP (Return to player), max win/loss streaks, winning hand counts and more.

- Leaderboards & Cash out: Cash out wins above the free play level, feeding into leaderboards for bank balance, RTP% (after 50 hands of play), and leaderboards that reward grinders

- Mobile stability - I've completely rewritten the communications routines both on server/client side. Mobile can be flaky, so the client handles silent auto-retries in the background without interrupting gameplay.

- Updated UI: New crisp graphics for playing cards

Obligatory tech stack info: serverside PHP / MySQL & client is coded in Godot 3.5.

I'd love to hear your feedback & I hope you all enjoy the new version!

Play it here: https://www.classicvideopoker.com/classicvideopokerv2/

A lightweight, terminal-based voice recorder written in Python with pause/resume, live preview, trash/recycle bin, quality presets and basic file management — no GUI, no bloat. Just a fun project. Nothing serious.

https://github.com/chistev/voice-recorder

I am diagnostic radiologist with over 40 years experience. In diagnostic testing, many terms are used to describe how well the test detects the disease or disorder. Examples are “sensitivity”, “specificity”, “predictive values”, “odds ratio”, “likelihood ratios” and numerous others. In the literature and medical presentations there is often not much consistency in their use; as a physician listening to or reading research, I was perpetually unclear on how these terms “fit together”. My solution was to invent the visual 2 by 2 diagram, or truth diagram, as a graphical alternative to the standard contingency table used in diagnostic testing (Johnson 1999). The concepts listed above, and many others, are represented graphically, and their inter-relationships can be clearly visualized. Instead of four numbers in a grid, a single rectangle on a coordinate system encodes all four cells of the 2×2 table through its position and shape. Each hemi-axis corresponds to one cell (see below). The vertical height corresponds to the number of subjects with the disorder, and the horizontal width corresponds to the number of subjects without the disorder. A low, wide box represents a low prevalence of the disorder; a high narrow box represents a high prevalence. The diagram makes it possible to see statistics like sensitivity, specificity, PPV, NPV, likelihood ratios, and even Bayes’ theorem as geometric relationships — lengths, areas, slopes, and proportions — rather than abstract formulas. Drag or resize the box to see how the cell values change. The other lessons in this app explain each of the terms and how they appear on the diagram. Any of these screens can be saved for presentation and publication purposes.

Please take a look and feel free to give me feedback.

REFERENCES

Johnson KM. The two by two diagram: a graphical truth table. J Clin Epidemiol. 1999;52(11):1073-82. [PubMed] [ResearchGate] Johnson KM, Johnson BK. Visual presentation of statistical concepts in diagnostic testing: the 2×2 diagram. AJR Am J Roentgenol. 2014;203(1):W14-20. [PubMed] [ResearchGate] Johnson KM. Using Bayes’ rule in diagnostic testing: a graphical explanation. Diagnosis (Berl). 2017;4(3):159-67. [PubMed] [ResearchGate]

Goodreads Buddy Extension, it works on Chrome, Firefox, and Edge browsers and is free.

It enhances your Goodreads experience by bringing ratings from Google Books, Amazon, Open Library & StoryGraph. directly onto the book page , making comparison fast, seamless, and efficiently .

Plus click on it to view the same book on that site !

pls give any feedback, it is appreciated !

Chrome Extension to See Rating from ratings from Google Books, Amazon, Open Library & StoryGraph directly on Goodreads!

actually, nothing special about this implementation. just another event loop written in rust for educational purposes and joy

in tests it shows seamless migration from uvloop for my scraping framework https://github.com/BitingSnakes/silkworm

with APIs (fastapi) it shows only one advantage: better p99, uvloop is faster about 10-20% in the synthetic run

currently, i am forking on the win branch to give it windows support that uvloop lacks

I'm Tyler - the solo operator of Quanta Intellect based in Portland, Oregon. I recently participated in Nous Research's Hermes Agent Hackathon, which is where this project was born.

I've used agents extensively in my workflows for the better part of the last year - the biggest pain point was always the browser. Every tool out there assumes a human operator with automation bolted on. I wanted to flip that - make the agent the primary driver and give the human a supervisory role.

Enter: Vessel Browser - an Electron-based browser with 40+ MCP-native tools, persistent sessions that survive restarts, semantic page context (agents get structured meaning, not raw HTML), and a supervisor sidepanel where you can watch and control exactly what the agent is doing.

It works as an MCP server with any compatible harness, or use the built-in assistant with integrated chat and BYOK to 8+ providers including custom OAI compatible endpoints.

Install with: npm i @quanta-intellect/vessel-browser

I use points and miles for most of my travel. Every booking comes down to the same decision: use points or pay cash? To answer that, you need award availability across multiple programs, cash prices, your current balances, transfer partner ratios, and the math to compare them. I got tired of doing it manually across a dozen tabs.

This toolkit teaches Claude Code and OpenCode how to do it. 7 skills (markdown files with API docs and curl examples) and 6 MCP servers (real-time tools the AI calls directly).

It searches award flights across 25+ mileage programs (Seats.aero), compares cash prices (Google Flights, Skiplagged, Kiwi.com, Duffel), pulls your loyalty balances (AwardWallet), searches hotels (Trivago, LiteAPI, Airbnb, Booking.com), finds ferry routes across 33 countries, and looks up weird hidden gems near your destination (Atlas Obscura).

Reference data is included: transfer partner ratios for Chase UR, Amex MR, Bilt, Capital One, and Citi TY. Point valuations sourced from TPG, Upgraded Points, OMAAT, and View From The Wing. Alliance membership, sweet spot redemptions, booking windows, hotel chain brand lookups.

5 of the 6 MCP servers need zero API keys. Clone, run setup.sh, start searching.

Skills are, as usual, plain markdown. They work in OpenCode and Claude Code automatically (I added a tiny setup script), and they'll work in anything else that supports skills.

PRs welcome! Help me expand the toolkit! :)

https://github.com/borski/travel-hacking-toolkit

I'm pretty confident I can run the 397B-A17B next.

I wanted to share a solution that I made initially for myself for OpenClaw, that helps control what your ai agents can reach when you let it do stuff without impacting its power, I hope it's useful to you.

Basically the solution lets you experiment freely with your agent within safe boundaries.

It's deterministic on purpose (doesn't include any Al layer) which means the solution follows clear and already defined rules, to maximize safety/security and predictability.

Rules are heavily tested on detecting prompt injection attempts and other security cases (explained in detail in the docs).

Everything is local and lives on your computer including the docs site.

It gives you a control panel to monitor and control boundaries. When boundaries are about to get crossed you receive an approval request which lets you see what your openclaw was trying to do.

It also (currently) supports Tailscale, so you can connect your Tailscale IP address and receive everything on your phone and you can also chat normally, approve or deny requests. It lets access the control panel via your tailscale IP address (a private one is recommended) from anywhere. Currently only Telegram Channel is supported.

Only supports linux os for now and Opencode Claude Code & OpenClaw runners.

The things you need to get started are explained in the readme, also include quick demo/showcase images so you can see how it looks.

I'll be happy to hear feedback from you guys, especially having it tested against prompt injections to see how it handles it, don't hesitate to open a ticket on the GitHub for any issue that you found, I'll do my best to fix them.

Link here: https://github.com/steadeepanda/agent-ruler/

Thank you for reading. I'll be happy to discuss about it.

One of my favorite ways to find and discover music these days is the radio station KEXP. It’s a public, independent radio station in Seattle where I grew up and they have DJs doing awesome shows all day and night. They play a ton of great music.

They have an official iOS app, but don’t have an official MacOS app or anything. I wrote myself an unofficial one that sits in the menubar though and displays current song info and has a few nice features around pause behavior/stream resumption and airplay. I borrowed a bunch of the logos/assets from the iOS app.

I’d love beta testers and any feedback people have!

Hi everyone, second Submission, first SaaS, longtime HN reader.

TL;DR: This is a LinkedIn post generator.

If you are active on LinkedIn or other heavily text-based social media platforms, then you might find this interesting.

Bleeding edge technical highlights: - AI-SEO, or, "GEO": We use a so-called "grounding page" for presenting facts and non-facts about the website to help non-human readers "ground" themselves in the truth of the matter.

What I learned: - Agent-based coding is a massive boost and accelerator if you take the time to properly review results and keep everything on track.

Let me know what you think!

Build a startup. Make the tough calls. See if you can reach IPO.