2026年1月2日 の Show HN

I’ve been working on a solution to the "Physical Oracle Problem" (trustless trading of physical goods) and just released the full Alpha implementation.

The Core Thesis: Existing decentralized marketplaces rely on reputation, which inevitably centralizes. Dealta replaces reputation with a Nash Equilibrium-based mechanism. We use staked, pseudo-randomly selected "Brokers" to physically verify goods. The protocol ensures that honesty is the dominant strategy for all actors via strict payoff matrices. It intended use is preferably trading of mid to high value goods. Nobody expecting a computer, want a box full of stones.

What we are releasing: a custom Layer-1 blockchain stack.

Full Node: Implements Hybrid Consensus (PoW + PBFT) for instant finality.

Integrated Wallet: Native key management and transaction construction for the custom trade opcodes.

DB Management: Custom indexing for trade states and dispute evidence.

The system is currently in Alpha. I am looking for feedback on the protocol design, the node architecture and collaborators.

Code needs polishing, which i will do if people like the project. However, the project runs, and a testnet will be launched if people take interest in the project.

Readme files will be updated as well. Currently they provide a simple guide on how to build the project.

Feel free to send an email. It can be found my in profile or in the paper.

Hello HN,

I’m Joseph, a solo developer. I built CustomPaste because I was frustrated by the binary choice standard clipboard tools give us: either keep all the messy formatting (background colors, huge fonts) or strip everything down to plain text.

We all know Ctrl+Shift+V (paste as plain text), but that is often too destructive, it kills hyperlinks, bolding, and lists when I usually just want to normalize the font family (e.g., force Arial 11pt) or remove background colors.

I wanted a tool that let me "strip exactly what I want, and keep exactly what I want."

The Solution: Instead of a single "paste" behavior, the app lets you create reusable "Recipes" to define exactly how your text should land in your editor. It intercepts the clipboard, processes the structure locally, and transforms it based on your rules.

It offers granular control over:

    Smart Preservation: You can strip or set specific font families and sizes but specifically preserve bold, italics, and hyperlinks.

Structure: You can preserve tables while stripping the images inside them.

Data Cleanup: It can instantly purge duplicate lines, sort lists alphabetically, or flatten extra blank lines.

Text Fixes: It cleans up AI-generated artifacts (like "smart quotes" or em-dashes) and enforces casing (Title Case, Sentence Case).

Privacy & Pricing: The app runs 100% locally on your machine, no cloud processing and no data harvesting. It is a one-time purchase (lifetime license), not a subscription. There is a free trial (first 100 pastes) so you can test if it fits your workflow.

I’d love to hear your feedback on the "Recipe" approach or any other edge cases you struggle with when pasting text!

Go 1.26 adds native SIMD via GOEXPERIMENT=simd. This library provides a portability layer so the same code runs on AVX2, AVX-512, or falls back to scalar.

Inspired by Google's Highway C++ library.

Includes vectorized math (exp, log, sin, tanh, sigmoid, erf) since those come up a lot in ML/scientific code and the stdlib doesn't have SIMD versions.

algo.SigmoidTransform(input, output)

Requires go1.26rc1. Feedback welcome.

HN has some of the best discussions on the internet, but I don’t love reading 100 comments to find 10 great insights.

This site analyzes top HN threads with LLMs and summarizes the key ideas, disagreements, and resources — while preserving links to the original discussion.

Useful for revisiting old threads as well.

Updated daily, manual-assisted for quality, no spam, fan project only.

Would love thoughts from the community.

https://hn-discussions.top

Hey HN! I'm Akshay, and I'm launching Seer - yet another AI workflow builder with granular OAuth scopes.

GitHub: https://github.com/seer-engg/seer Demo video: https://youtu.be/cmQvmla8sl0

The Problem: We've been building AI workflows for the past year and kept running into the same issue: existing platforms (n8n, Langflow, Flowise) require full access to your Google services even for read-only operations. Want to summarize emails? You're also granting send permissions. Want to read docs? You're also granting edit permissions. If you want granular scopes, the onus is on you to:

- Create your own OAuth app with Google (1-2 weeks approval time) - Modify source code to support read-only scopes

We saw this pattern repeated across Discord channels and GitHub issues - developers asking for better scope support, maintainers saying "you can configure it yourself."

Our Solution: Seer ships with read-only auth scopes as the default for common operations. It's self-hostable, so your data never leaves your infrastructure. The demo shows a simple email summarization workflow (Gmail + LLM API), but the principle applies to any integration.

Why This Matters: Security through least privilege isn't just best practice - it's essential when you're giving AI agents access to your production data. One compromised workflow shouldn't mean your entire Google Workspace is at risk.

Questions for HN: 1. How are you currently handling OAuth scopes in your AI automation workflows? 2. Would you find value in a scope validator that audits your existing workflows? 3. What other integrations would you want to see with granular permissions?

The only similar platform with granular scope support is Make.com, but it's closed-source. We think this should be the standard, not the exception.

Would love your feedback!

Hey HN! I built Gojju, a programming language that cherry-picks my favorite features from 5 languages:

- Python: List comprehensions, slicing

- Ruby: #{interpolation}, postfix if, blocks

- Haskell: |> pipe operator, lambdas \x -> x+1, Maybe/Either

- Perl: unless/until, regex literals

- JavaScript: Arrow functions =>, spread ...

Example:

  [1, 2, 3, 4, 5]
    |> filter(\x -> x % 2 == 0)
    |> map(\x -> x * 2)
    |> sum

Install: `pip install gojju`

The name "Gojju" (ಗೊಜ್ಜು) means "essence" or "secret ingredient" in Kannada.

Would love feedback on the syntax choices!

Hi HN,

I challenged myself to build a multiplayer game in just 1 hour. My goal was to experience the distributed processing capabilities of Elixir and Phoenix LiveView firsthand by creating a simple web app.

It allows everyone to see each other's cursors in real-time and fight a boss together. This is currently a beta version, and I plan to ship new features every week.

It's deployed on Koyeb. I'd love to hear your feedback on the performance!

Hi HN — I built Aurora-OS.js, a lightweight, embeddable OS-style desktop UI written in plain JavaScript. It’s intended for demos, in-browser desktop experiences, and learning OS/desktop concepts without a heavy framework. The future of this project is a fully playable hacking simulator to be released on Steam and other marketplaces.

Contributors & testers wanted!

Hey HN, and happy new year!

I'm Hampus Kraft [1], a 22-year-old software developer nearing completion of my BSc in Computer Engineering at KTH Royal Institute of Technology in Sweden. I've been working on Fluxer on and off for about 5 years, but recently decided to work on it full-time and see how far it could take me.

Fluxer is an open source [2] communication platform for friends, groups, and communities (text, voice, and video). It aims for "modern chat app" feature coverage with a familiar UX, while being developed in the open and staying FOSS (AGPLv3). The codebase is largely written in TypeScript and Erlang.

Try it now (no email or password required): https://fluxer.gg/fluxer-hq – this creates an "unclaimed account" (date of birth only) so you can explore the platform. Unclaimed accounts can create/join communities but have some limitations. You can claim your account with email + password later if you want.

I've developed this solo, with limited capital from some early supporters and testers. Please keep this in mind if you find what I offer today lacking; I know it is! I'm sharing this now to find contributors and early supporters who want to help shape this into the chat app you actually want.

~~~

Fluxer is not currently end-to-end encrypted, nor is it decentralised or federated. I'm open to implementing E2EE and federation in the future, but they're complex features, and I didn't want to end up like other community chat apps [3] that get criticised for broken core functionality and missing expected features while chasing those goals.

I'm most confident on the backend and web app, so that's where I've focused. After some frustrating attempts with React Native, I'm sticking with a mobile PWA for now (including push notification support) while looking into Skip [4] for a true native app. If someone with more experience in native dev has any thoughts, let me know!

Many tech-related communities that would benefit from not locking information into walled gardens still choose Discord or Slack over forum software because of the convenience these platforms bring, a choice that is often criticised [5][6][7]. I will not only work on adding forums and threads, but also enable opt-in publishing of forums to the open web, including RSS/Atom feeds, to give you the best of both worlds.

~~~

I don't intend to license any part of the software under anything but the AGPLv3, limit the number of messages [8], or have an SSO tax [9]. Business-oriented features like SSO will be prioritised on the roadmap with your support. You'd only pay for support and optionally for sponsored features or fixes you'd like prioritised. I don't currently plan on SaaS, but I'm open to support and maintenance contracts.

~~~

I want Fluxer to become an easy-to-deploy, fully FOSS Discord/Slack-like platform for companies, communities, and individuals who want to own their chat infrastructure, or who wish to support an independent and bootstrapped hosted alternative. But I need early adopters and financial support to keep working on it full-time.

I'm also very interested in code contributors since this is a challenging project to work on solo. My email is [email protected].

~~~

There’s a lot more to be said; I’ll be around in the comments to answer questions and fix things quickly if you run into issues. Thank you, and wishing you all the best in the new year!

[1] https://www.linkedin.com/in/hampuskraft

[2] https://github.com/fluxerapp/fluxer

[3] https://news.ycombinator.com/item?id=46376201

[4] https://skip.tools/

[5] https://news.ycombinator.com/item?id=40533484

[6] https://news.ycombinator.com/item?id=37502258

[7] https://news.ycombinator.com/item?id=39569843

[8] https://news.ycombinator.com/item?id=46383675

[9] https://sso.tax/

Hi everyone,

I built a UI for the new open-source Hunyuan Motion model to generate 3D animations from text: https://hy-motion.ai

It generates BVH files instantly. I'm trying to bridge the gap between "cool AI demo" and "useful game dev tool".

Question for 3D devs/animators:

If you were to use this in production, what is the single biggest missing feature?

1. Export Pipeline: Auto-conversion to FBX for Unity/Unreal? 2. Motion Fusion: Blending multiple prompts into one long sequence? 3. Rig Variety: Support for non-humanoid skeletons?

Feedback is much appreciated.

I built a task/goal tracker where the entire UI is one input field.

The idea: your goals live in four quadrants (daily, weekly, monthly, yearly). Everything happens through commands. The app docks to the side of your screen.

Adding a goal:

/d 50 pushups

Chain them:

/d 50 pushups /w 3 gym sessions /m finish project /y learn piano

Updating progress:

Create an alias with /alias p pushups, then just type 25 p to add 25. Three characters.

Review your week with /review 7d. Rename goals, change targets, convert between quadrants—all through commands.

Each quadrant auto-resets at the right interval (daily at midnight, weekly on Monday, etc). You don't manage anything.

Why I built it this way: I kept bouncing between productivity apps looking for something faster. Nothing stuck because they all wanted me to click through menus and organise things. I just wanted to type and move on.

So I made something deliberately constrained. One input. Four quadrants. No settings screen. No integrations. The lack of features is the point.

Curious what the HN crowd thinks—especially if the command syntax feels intuitive or too obscure. Still iterating.

I built a minimal opensource CMS, I use it myself for my blog and for other SaaS.

l love blogging, and sometimes I post random thoughts on my blog. The only thing is, I always did it with .md files, which is fine too

However, I was excited about the idea of using a CMS that was very minimal and avoiding the option of connecting something like WordPress or other big platforms.

Open source (if you want to fork it or contribute) and free to use (unless I see you have a million views haha).

Star the repo if you like it!

I built this because I often need clean Markdown from PDFs for writing, documentation, and LLM workflows.

Most existing tools either flatten everything into text or rely purely on OCR. I wanted something that preserves structure and is actually usable in Markdown.

Feedback welcome.

Hi HN

I’ve been building *Mini Apps Builder*, a small no-code tool to help people create Telegram mini apps and simple web apps without writing code.

The idea came from experimenting with Telegram mini apps — they’re powerful, but the tooling can be difficult unless you’re already a developer.

This project aims to simplify that with templates, basic payments, and quick deployment, so people can focus more on the idea than on setup.

I’d really appreciate feedback from anyone who has built Telegram bots or mini apps, or thoughts on whether this solves a real problem.

Happy to answer questions or learn from your feedback.

Hi HN, I’m the developer behind CryDecoder. I built this after too many nights at 3am staring at a crying infant, completely exhausted, trying to guess whether it was hunger, gas, or just general fussiness.

I realized I was essentially running a mental decision tree on very little sleep, so I decided to see if I could automate some of that signal processing.

What it does: CryDecoder analyzes short audio clips of a baby’s cry and classifies them into categories like hunger, discomfort/gas, tiredness, or general fussiness.

How it works: • Tech: On-device audio feature extraction paired with a lightweight ML model trained on labeled cry patterns. • Performance: Inference runs locally on the phone, which keeps latency low and avoids sending audio off-device. Results come back quickly enough to feel near real-time. • Philosophy: This isn’t meant to replace parental judgment. It’s intended as an extra data point — a sanity check when you’re tired and not sure what to try next.

The business side: The app currently uses a paid model with a preview. I’m an engineer first and still iterating on pricing and paywall placement.

I’d appreciate feedback on: 1. The technical approach and responsiveness 2. Whether the paywall timing feels reasonable for a utility like this

Thanks for taking a look.

Hey everyone! Happy New Year! Cheers to all!

I've been working on CheerAd, a simple widget that lets website visitors "cheer" for you by paying to leave a featured message on your site.

The Problem: - Traditional ad networks need tens of thounsands pageviews and take forever to pay - Sponsorship platforms require pitching brands - Most solutions aren't designed for small creators

The Solution: CheerAd lets YOUR audience become your advertisers. They pay to leave a cheerful message, or their project's promotion. Then you approve it, and it appears on your site. You get paid instantly via Stripe.

Features: - 5-minute setup with simple embed code - You control the price (min $1.50) - 90% goes to you (10% platform fee + Stripe fees) - AI moderation option - No minimum traffic required - Instant payouts to your Stripe account

https://cheerad.com

Detailed info: https://cheerad.com/pages/how-to-use.html

Currently in beta - would love your feedback! What features would you want to see?Hey everyone!

Upload any face pic → AI turns it into a Charlie Kirk-style meme in seconds. No account, no watermarks, privacy-focused (we don’t save your images). Exports in platform-optimized sizes (TikTok/IG/Twitter). Try it: http://kirkifiedai.com/ Feedback welcome!

hey guys what's up, happy new year to all of you!

so basically the link above is a fork of the chromiumoxide crate but with stealth patches implemented using rebrowser as a reference. it plugs runtime.enable and common automation flags, enforces some hardware consistency through profiles and has some convenience features and it's still early but for starters it can pass most of the common detection tests

i prefer writing my applications in compiled languages but recently been needing to go into browser automation more and more and always felt that the space for rust didn't have much of the variety that the node/python counterparts had, so this is my attempt to give some life to it, well to solve my needs at least, but i hope someone else finds it useful too!

i needed a stealth browser in rust because my need was mostly around captcha solving, so there's a turnstile solver here too and yeah i know there's a lot of them around but having it in rust allows me to integrate it into my application so much better and avoid the mess of so many external services

and yeah my use case required not only cloudflare but geetest too so i ported xkiann's python solver to rust too, with some modifications to make it deobfuscate automatically and added support for multi turn verification and user_info parameters for sites that need it

both solvers have C FFI bindings for integration with other languages!

https://github.com/ccheshirecat/chaser-oxide - chromiumoxide stealth fork https://github.com/ccheshirecat/chaser-cf - cloudflare solver https://github.com/ccheshirecat/chaser-gt - geetest solver

more details on the github repo, im falling asleep so goodnight HN and happy new year again much love to you all!

I've had this idea sitting in a file for years but until I just got Claude Code at Christmas time, never had to time to actually implement it. It seemed like a good test for Claude Code and with 2x christmas usage, why not?

The goal was aggregating different travel warnings from multiple government sources to get a sense of how safe a country was to visit. It aggregates from US, Canada, Ireland, New Zealand and UK (Australia scraper didn't go so well). I was shocked how effectively it was able to accomplish that, so I added some more data I thought might be useful if I were considering traveling to a country and pulled government/UN/edu data about things like water/food safety, healthcare/vaccines/diseases, emergency numbers, natural disaster risks, women's safety, lgbtq safety.

Throw in a nice map visualization and ability to compare, I'm pretty shocked and happy how well I think it came out. I wanted to share it with the community, maybe folks find it helpful and/or have ideas for ways to improve it.

https://videoCalling.app is a online free video calls with no registration, no downloads.

I’m sharing an open-source Kubernetes runtime compliance reference implementation built on Endpoint State Policy (ESP).

It treats compliance as policy as data: you declare what you want to check and what compliant state looks like, and the system continuously evaluates live cluster state instead of running point-in-time scans.

Key ideas: • Agent-based runtime state collection in Kubernetes • Deterministic policy evaluation (no SCAP XML) • Results emitted as time-bound attestations, not snapshots • Framework-agnostic (STIG, NIST, SSDF, etc.)

The repo is ready to build and test: • Dockerfiles and Helm charts included • Starter policy library with basic coverage • End-to-end reference architecture (agent → evaluator → result sink)

This is aimed at people doing platform security, DevSecOps, or compliance in regulated environments where snapshot evidence doesn’t hold up.

Upload any static pic → AI turns it into a dynamic motion poster in seconds. No account, no watermarks, supports 16:9/9:16/1:1 export sizes for socials. Try it: https://aimotionposter.app/ Feedback welcome!