Show HN for October 24, 2025

The project is mainly for learning and experimentation, but I’d love feedback or ideas for improvement.

I built ImageConverter.dev because I got tired of “free” image converter sites that force uploads, or throttle conversions.

So I made a tool that runs 100% client-side — meaning your images never leave your device. It’s built for speed, simplicity, and privacy.

What it does

Convert images between JPG, PNG, WebP

Works offline once loaded (PWA support)

How it works

It uses the Canvas API and WebAssembly to handle conversions directly in the browser. There’s no upload, no tracking, no server costs, and it’s fast even on mid-range devices.

Why I built it

I wanted an instant, no-ads, privacy-safe way to handle images for my personal projects — something lightweight enough to replace desktop tools.

Try it

https://imageconverter.dev

Would love feedback from the community — especially on:

Performance on different browsers/devices

Thanks for reading!

Inspec lets interior designers create and manage FF&E schedules - basically spec sheets listing everything that goes in a room before the furniture: flooring, paint, countertops, lighting, fixtures, etc.

This process is currently exclusively done using Excel, and while this works to some degree, it comes with a lot of manual work and clunkiness. When Caitlin started working remotely, I watched her deal with these issues daily. So I spent the past 9 months building a better solution.

Key Features:

- Realtime collaboration

- Revision control (versioning)

- Professional PDF exports

- QR codes to print out on-site for contractors, builders etc. to always have the latest version

- Completely customisable fields and a familiar workflow to Excel to keep learning curve small

When we first started building this we thought it was completely unique, but turns out there are 2 competitors. I think our positioning is quite different though as we seek to only replace this document creation, rather than overhaul the entire project management and try to be a complete solution. So that’s helped to guide our focus, but also validated that interior designers are looking to modernise their software.

Tech stack:

I used my SaaS boilerplate which is just a modified T3 stack template with everything set up just how I like it. So Next.js with the pages router, TS, Trpc, Prisma + PostgreSQL, and TailwindCSS. I’ve also got Pusher for realtime collaboration, Redis and BullMQ for keeping a seperate background worker for PDF and web scraping jobs.

I can’t imagine many interior designers are on HN, but figured I would share this for anyone who wants to take a look :) feedback always welcome! The landing page is at https://inspec.design

I’ve been playing with Claude Skills and stumbled on a simple pattern for tiny, durable personal data systems:

* CLI: a small, self-contained executable

* SKILL.md: the operator guide (what to run, how to parse output, how to think about the system)

* SQLite: a local DB for persistent state

It’s nothing mind-blowing, but the ergonomics of this combo feel great.

If you define a process/flow, Claude can "turn the crank" by running the CLI, accumulating context, and animating the system to life over time.

They’re also easy to share: you can distribute System Skills via Claude Code’s `/plugin marketplace add <repo>`.

More details in the blog post and the toy Pomodoro System Skill reference implementation here:

Blog: https://www.shruggingface.com/blog/the-system-skill-pattern

Repo: https://github.com/jakedahn/pomodoro

--

Curious whether any of this resonates. Also excited to hear any interesting System Skill ideas worth exploring!

I plan to open source it sometime next year because I’ve got other projects to finish first. It's free until I deplete my cloud credits, then it will switch to a tier-based model with a free option.

So I stripped everything away. No abstractions. Just Python, HTTP requests, and the OpenAI/Anthropic APIs.

What I found was anticlimactic in the best way: there's almost nothing there.

  - "AI agents" are just functions the model tells you to call
  - "Memory" is literally just a list you append to and send back
  - "RAG" is search, concatenate to prompt, send it off
  - "Multi-agent systems" are just API calls in sequence

I created 7 modules showing the basics: API calls, conversation state, tool calling, RAG, streaming, prompt chaining. Each one is heavily commented, nothing fancy. Side-by-side examples for Claude and GPT so you can see they're fundamentally the same thing.

Now when I use frameworks, I actually know if I need them or if I'm just adding bloat.

Repo: https://github.com/jmedia65/learn-ai-right

pip install zpace

and find the big files consuming your disk space. Be it apps, virtual environments, machine learning models etc. Just run

zpace

Once you find one, that you can say "bye" to, just run

rm -rf /i_dont_need/this/file/right_now

to get rid of it.

It was born out of frustration while lack of disk space prevented me to use my laptop properly. It has been very useful to me so far. I hope that it can be useful to you as well. Feel free to check it out.

Currently tested on MacOS only

Unlike traditional photogrammetry or AI mesh tools, Seed3D doesn’t fake geometry with normal maps — it reconstructs real surfaces, edges, and micro-details for simulation-grade accuracy and realism.

What it does

• Generates watertight polygonal meshes with crisp, true geometry

• Outputs full PBR texture sets (albedo, roughness, metalness, normal, AO)

• Delivers 6K textures that hold up in extreme close-ups

• Ensures physics-stable topology for simulations and collisions

• Exports USD/USDZ, FBX, and GLTF — compatible with Omniverse, Unity, and Unreal Engine

Who it’s for

• Embodied AI and robotics researchers

• Game, XR, and VFX developers

• Product visualization and digital twin creators

• Simulation and graphics educators

Try the Seed3D 3D model generator here: https://www.seed3d.xyz/

Would love feedback from the HN community — especially on fidelity, physics performance, and engine integration.

  Are you tired of busy backgrounds distracting from your subject? Still wasting hours on tedious manual cutouts? It’s time to revolutionize your image editing. Introducing WhiteBG—the completely free, AI-powered online tool designed to give your images a clean, professional look in seconds.

  WhiteBG is built for anyone who values speed and quality. Whether you're an e-commerce seller creating marketplace-ready listings for Amazon and Shopify, or a professional looking to polish your headshots, our tool makes it effortless. Simply upload any image, and our powerful AI instantly detects the subject, removes the background, and replaces it with a crisp, pure white canvas. The advanced algorithm delivers pixel-perfect precision, flawlessly handling complex edges like hair and fur to ensure your subject stands out.

  For photographers and designers, WhiteBG is the ultimate workflow accelerator. For marketers, it’s the secret to producing high-impact ad creative on the fly. We also take your privacy seriously; all uploaded images are automatically and permanently deleted from our servers one hour after processing.

  Best of all, it’s 100% free. No sign-up, no credit card, and no limits. Visit WhiteBG now to experience the future of image editing and give every photo a stunning, studio-quality finish.

This includes both basic spreadsheet functionality like `list_sheets`, `sheet_page` as well as useful features like recursive formula precedent/dependent tracing.

I built ResizeImage.dev that runs 100% client-side — nothing gets uploaded, and it’s instant.

What it does

Resize, crop, and optimize images directly in your browser

Supports JPG, PNG, WebP

Works offline (PWA-ready)

No tracking, no server, no data collection

How it works

It uses the Canvas API and WebAssembly codecs to process everything locally. All transformations happen in-memory, so no files ever leave your machine.

Why I built it

I needed a simple, no-BS way to resize images for web and social media — something fast, private.

Try it

https://resizeimage.dev

Feedback welcome

I’d love feedback from the HN community

Thanks for reading!

I wanted to share a website i've made.

It'a redesign of the UNV ( United Nations Volunteers ) Dashboard.

I quit my job lately to take some sort of a gap year.

I've been pondering between working in the non-profit sector, or trying to make my own little business.

This is a little step towards both ideas :)

I'm trying to get used to ship things, and also do things just to be useful.

The original UNV dashboard has pretty bad UX, so I hope my version can help make people finding a volunteering opportunity a less stressful endeavour.

It's not perfect, but I intend to keep making it better.

https://volunteerwiththeun.com/

cheers <3

Here is a Chrome extension that automatically detects OpenAPI files on any web page and lets you open them with one click in your favorite API tools like Swagger UI, ReDocly, etc.

Install - API Factory - Chrome Web Store

Pin the extension

Open any webpage containing OpenAPI - https://www.canva.dev/docs/connect/ or https://www.weather.gov/documentation/services-web-api

That's it. If the webpage contains an OpenAPI file, extension open opens a popup with all the tools. Launch the detected OpenAPI file in your favorite tool including Swagger UI, ReDocly, etc.

When texts grow longer, these relations form *sequences* — and from the infinite combinatorial space, *eight stable patterns (Σ₁–Σ₈)* emerge empirically. Each pattern correlates with a distinct *semantic and emotional field* — cathartic, heroic, meditative, humorous, and so on.

This allows us to instruct an LLM not through semantic prompts (“write a story about…”), but through *structural commands* — e.g., generate a narrative following sequence Σ₅ (Tragic Counterpoint). You can experiment with these archetypes directly here: [Narrative Generator](https://a2tg9zwayjuqzcpdznklve.streamlit.app/~/+/#narrative-...) or [via python](https://github.com/mihendr/Echoes-of-autonomy/blob/main/TEMA...)

Interestingly, there appears to be a parallel between these textual progressions and *musical harmony*. For example, if A–E are mapped to harmonic functions (I, IV, V, vi, ii), the narrative sequences behave like emotional “chord progressions” — where meaning flows, modulates, and resolves.

Coherence in the generated text arises not only from syntax, but from the *associative field* that the LLM constructs around these shifting relations. When asked to “switch subjects,” it spontaneously moves from Poet to Writer, preserving aesthetic continuity rather than randomness.

It might even hint at how *children acquire language*: by first sensing the melody of structural transitions, before mapping them to concepts and emotions. Such a method could eventually apply to *training neural systems*, where meaning is learned as flow — not as fixed representation. [Full text](https://medium.com/@mihend_80107/%CF%83-manifold-manifest-e3...)

So I built Pensive, a bookmarking solution that saves the full page content and makes it searchable with full-text search. You can add pages using a browser extension or a Telegram bot (for saving on mobile).

It is written in Go with PostgreSQL, all Dockerized on a $5 Hetzner server, and the front end is built with HTMX.

I have also added embeddings (using Gemini Flash Lite) to let LLMs interact with your bookmarks contextually.

It is stable enough that I now use it daily. I’m considering publishing it as open source, but first I want to have a proper version ready. Feel free to email me if you’re interested in helping out or if you have prior experience with open source.

Feel free to try it at https://getpensive.com

What to expect during this phase

Affordable entry: Generating videos now comes at reduced prices to encourage experimentation and rapid content production across campaigns and experiments.

Risk-free trial: The platform prioritizes a low-barrier experience, making it easy to try different concepts without heavy upfront commitments.

Free first-generation credit: New users receive a one-time free video generation, enabling immediate hands-on evaluation of capabilities and output quality.

Billing and policies you should know

Low-cost testing: The current stage prioritizes accessibility; pricing is designed to be favorable for early adopters while feedback is gathered.

Failed generations: If a generation attempt fails to produce a usable result, charges are not applied, aligning with a forgiving testing policy.

Ongoing terms: As the service evolves, pricing and terms may adjust; staying informed helps plan future productions.

How to get involved

Sign up during the promotional window to access the introductory pricing and the free generation credit.

Submit prompts or visuals to gauge quality, then refine inputs for desired tone and style.

Share feedback to help improve the platform during this early deployment.

Join ai-video-gen.org now to explore AI video creation at a very approachable price during the launch phase, and help shape the product with your feedback.

We’ve just opened Convert2PDF API (Beta) — a developer-focused API suite for working with PDFs and images.

We built it to simplify document conversion workflows (without dealing with headless browsers or Ghostscript setups).

Current API features:

- Remove Metadata from PDF - Covert PDF to Doc - Convert Web Page → PDF - Convert Documents (DOCX, ODT) → PDF - Merge, Split, and Compress PDFs - Conver Images to PDF - Compress Images - and many more...

Try it instantly

We’ve made a Playground to test all APIs without writing code or creating an account.

https://convert2pdfapi.com?utm_source=hackernews&utm_medium=...

Why we built it

While working on a client project, we needed an API to convert reports from HTML and URLs to PDF.

Most existing tools were either too limited, expensive, or required browser setups.

So we built a lightweight, hosted alternative that’s easy to integrate into SaaS apps and automation workflows.

Feedback

We’re still in beta and would love feedback — especially from devs who’ve dealt with PDF generation or automation before.

Also curious what kind of pricing or usage model feels right for such an API.

Thanks for checking it out!

I’ve built Meds, a high-performance Linux firewall written in Golang, integrating with Netfilter NFQUEUE. It inspects inbound packets in user space and blocks malicious traffic in real time — completely lock-free and built for speed.

Key features:

- NFQUEUE-based packet interception

- Lock-free packet pipeline using atomic ops only

- Per-IP token bucket rate limiting

- TLS SNI & JA3 fingerprint filtering

- Blacklist/whitelist (FireHOL, Spamhaus, Abuse.ch, StevenBlack)

- Prometheus metrics ready

- HTTP API for runtime configuration (add/remove IPs/domains)

Repo: https://github.com/cnaize/meds

Any feedback is very welcome!