Show HN for July 20, 2025

Hi HN!

I built a custom MCP (Model Context Protocol) server that connects Blender to LLMs like ChatGPT, Claude, and any other llm supporting tool calling and mcps, enabling the AI to understand and control 3D scenes using natural language.

You can describe an entire environment like:

> “Create a small village with 5 huts arranged around a central bonfire, add a river flowing on the left, place a wooden bridge across it, and scatter trees randomly.”

And the system parses that, reasons about the scene, and builds it inside Blender — no manual modeling or scripting needed.

What it can do: - Generate multi-object scenes like villages, landscapes, from a single prompt - Understand spatial relations — e.g., “place the bridge over the river” or “add trees behind the huts” - Create camera animations and lighting setups: “orbit around the scene at sunset lighting” - Respond to iterative changes like: “replace all huts with stone houses” or “make the river narrower” - Maintain object hierarchy and labels for later editing

Tech Stack: - Blender Python scripting - Node.js server running MCP - LLM backend (OpenAI / Claude, easily swappable)

Demo: https://blender-mcp-psi.vercel.app/

GitHub: https://github.com/pranav-deshmukh/blender-mcp-demo/

Curious to hear thoughts from folks in 3D tooling, AI-assisted design, or dev interface design. Would you find this useful as a Blender plugin? I’m open to expanding it!

Please try it and give it a star on github

Show HN: Context42 - AI-powered style guide generator for your codebase

Hey HN,

I've been building Context42 to solve a problem that's been bugging me: getting AI to write code like me, and helping disseminate coding best practices.

The core insight is simple - your existing code is already your best style guide. Instead of debating tabs vs spaces or where to put your curly braces, Context42 analyzes your actual codebase and generates comprehensive style documentation using Google's Gemini AI.

Here's what makes it special:

1. *Language-aware analysis* - It groups files by language and generates specific style guides for each. Your TypeScript patterns won't bleed into your Python conventions.

2. *Dependency-smart processing* - It analyzes child directories before parents, building up context as it goes. This means it understands your module structure and can identify patterns that emerge across your architecture.

3. *Built for real codebases* - With configurable concurrency, resume capability, and automatic cleanup, it's designed to handle everything from small projects to massive monorepos. The terminal UI (built with Ink/React) gives you real-time progress on what's happening.

4. *Pragmatic over prescriptive* - Instead of enforcing arbitrary rules, it documents what you're already doing. This makes it easier to onboard new developers and maintain consistency without religious debates.

The technical approach is interesting too - it uses a worker pool pattern with abort controllers for graceful shutdown, SQLite for persistence (so you can resume failed runs), and a file registry system that guarantees cleanup even on crashes.

I built this because I believe the best documentation is the kind that reflects reality, not aspirations. Your code style isn't what you think it should be - it's what it actually is. And that's worth documenting.

You can check it out at: https://github.com/zenbase-ai/context42

Would love to hear your thoughts, especially if you've tackled similar problems in your teams. What's worked for you in maintaining code consistency at scale?

I wrote a simple web UX in Python/JavaScript that spawns a conversation with Google Gemini with MCP commands that let it work on a specific coding task that you specify: http://github.com/alefore/duende

The UX lets you observe the conversation and provide guidance (e.g. "don't implement Foo through Bar, that's suboptimal; instead …").

It supports a `--review` mode, where once the main conversation says "I'm done with the task", various "evaluation" conversations are spawned, each focusing on reviewing the change from a very specific angle (e.g. "does it introduce useless comments?"). In the future, I'm considering adding other workflows.

I've used it mostly to develop itself (I started with a super rudimentary manual implementation and then mostly used Duende to extend its own implementation) as well as (with moderate success) to add a few new features to [my C++ text editor](http://github.com/alefore/edge).

It's been a lot of fun. I'm still developing my intuitions for what works and what doesn't, but I've already had plenty of experiences where I've been WOW'ed by what LLMs can already accomplish (as well as, to be honest, plenty of very disappointing cases where it struggles significantly on tasks that I expected would have been trivial). It's a learning experience, seeing things like how to avoid hallucinations; developing an intuition for how much to break down large tasks into smaller ones; or knowing when to abort a conversation and restart it with an improved prompt (vs continue to steer it in the right direction).

I think investing up-front in setting up a good context (e.g., good validation logic, useful constant contexts, a good set of "review evaluators" that can push-back against sloppy code) can go a long way to increase the odds of success.

It has changed my perception on the applicability of AI for developing software. While I've reviewed all the outputs (and often rewrite parts of them manually), I'm already incorporating it into (some parts) of my development life-cycle.

I have many ideas for improvements, but figured I'd share this early and ask for feedback. Hopefully others find it interesting; would love to hear your thoughts.

Sifaka is an open-source framework that adds reflection and reliability to large language model (LLM) applications.

Hi everyone,

Just wanted to share a use case where local LLMs are genuinely helpful for daily workflows: file organization.

I've been working on a C++ desktop app called AI File Sorter – it uses local LLMs via `llama.cpp` to help organize messy folders like `Downloads` or `Desktop`. Not sort files into folders solely based on extension or filename patterns, but based on what each file actually is supposed to do or does. Basically: what would normally take me a great deal of time for dragging and sorting can now be done in a few.

It's cross-platform (Windows/macOS/Linux), and fully open-source.

[GitHub repo](https://github.com/hyperfield/ai-file-sorter)

[Screenshot 1](https://i.imgur.com/HlEer13.png) - LLM selection and download

[Screenshot 2](https://i.imgur.com/KCxk6Io.png) - Select a folder to scan

[Screenshot 3](https://i.imgur.com/QTUG5KB.png) - Review, edit and confirm or continue later

You can download the installer for Windows in [Releases](https://github.com/hyperfield/ai-file-sorter/releases) or the Standalone ZIP from the [app's website](https://filesorter.app/download/).

Installers for Linux and macOS are coming up. You can, however, easily [build the app from source](https://github.com/hyperfield/ai-file-sorter/blob/main/READM...) for Linux or macOS.

---

### How it works

1. You choose which model you want the app to interface with. The app will download the model for you. You can switch models later on.

2. You point the app at a folder, and it feeds a prompt to the model.

3. It then suggests folder categories like `Operating Systems / Linux distributions`, `Programming / Scripts`, `Images / Logos`, etc.

You can review and approve before anything is moved, and you can continue the same sorting session later from where you left off.

Models tested: - LLaMa 3 (3B) - Mistral (7B) - With CUDA / OpenCL / OpenBLAS support - Other GPU back-ends can also be enabled on `llama.cpp` compile

--- ### Try it out

* Windows: [SourceForge](https://sourceforge.net/projects/ai-file-sorter/) or [GitHub Releases](https://github.com/hyperfield/ai-file-sorter/releases) * Linux/macOS: build from source (instructions in the [README](https://github.com/hyperfield/ai-file-sorter/blob/main/READM...))

---

I’d love feedback from others using local models, especially around: - Speed and accuracy in categorizing files - Model suggestions that might be more efficient than Mistral/LLaMa - Any totally different way to approach this problem? - Is this local LLM use case actually useful to you or people like you, or should the app shift its focus?

Thanks for reading!

Hi HN

I built EasyFAQ, a free tool that helps you generate and embed SEO-friendly FAQ pages. It’s aimed at making structured content easy to publish, especially for small sites, blogs, and landing pages.

The generated FAQs include proper schema markup (JSON-LD), so they’re optimized for Google’s rich results and easier for large language models like ChatGPT to interpret accurately.

I made this after noticing how much well-structured FAQs can improve site clarity and search visibility. The tool requires no login, and you can export or embed the generated FAQs directly.

Would love feedback from the HN community — especially around UX, SEO usefulness, or other feature ideas.

link: https://easyfaq.io

Thanks!

I am an audiobook addict that coded this https://github.com/cpttripzz/Chatterblez. I am using it all the time and it works nice. I have only bothered to get it working on windows but it should be cross-platform as it uses pyqt, I would be happy for contributors to help get it working on macos and linux and also ATI and other video cards.

If you are stuck without a video card I recommend using https://github.com/cpttripzz/audiblez it can generate an audiobook in around 4 hours with a decent CPU

Hey there, hope this package helps!

Hi HN!

I built Bookhead because I used to work as a bookseller and I wasn't happy with the software options when I decided to sell my own collection online (with the hopes of one day growing so I can open my own brick & mortar). So I decided to make my own bookselling app...a classic hacker distraction.

Bookhead has two main parts: 1. an inventory management app that allows a bookseller to list their books anywhere they want to sell books (like Squarespace, Biblio, eBay, Shopify (coming soon!), etc) 2. an e-commerce platform with a CMS for selling books and letting a store control their online brand

I have a very exciting roadmap that I'm not ready to fully reveal, but it's all based on books. I'm building a sorta Zapier-like platform for independent booksellers. Everything is so fragmented and disconnected, which makes it hard for booksellers to do their work. I'm hoping to change that. I have a blog post that lays out my vision here: https://bookhead.net/blog/fragmented/

The current iteration is like "data engineering as a service for books." A book is a powerful thing. I'm hoping to give a bookstore everything they need to sell books online. Inventory, e-commerce, marketing, etc. It's a crowded market but I've had fun making the bookselling app that I believe should exist.

If you know any booksellers, please let them know about this! I'm onboarding my first customer right now and the biggest bottleneck is the other bookselling software providers, despite my intention to collaborate instead of compete. It's frustrating to wait for two weeks for a point of sale provider to setup an integration. It's almost like they don't care about their customers. Some providers even require ethernet cables for their software...still partying like it's 1999. Perfect for early-adopter booksellers frustrated with current tech who understand the power of automation.

I'm currently looking for funding so I can focus on this full-time. My biggest problem right now is time (aka money) because I have to sell my time to make rent etc, and can't focus on this project like I need to. I've gotten good validation from booksellers and other technically savvy folks in the industry (I've heard from two different companies that they've considered building something like this), so I believe I have something valuable. I'm not interested in funding from somebody who doesn't share my love for books or doesn't support my mission: help people use technology to promote literature. I believe that literature is one of humanity’s most prized creations, and we can use technology as a tool to keep this gift alive.

Please email me at [email protected] if you know of booksellers who might want to be an early adopter, or know of any funding opportunities that might be a good fit.

I built an automation with n8n that fetches new PubMed studies, filters them using a predefined longevity keyword set, and removes those that lack actionable outcomes or clear relevance to daily health routines.

Each remaining study is parsed for key findings, methodology, and practical applicability. The output is turned into a short script and recorded as an audio episode. The idea is to save time for people who want to follow longevity research without reading dozens of papers per week.

Hi HN

I built SuppFlow.com – an AI assistant that helps you manage and respond to customer support emails automatically.

It reads incoming emails, drafts helpful replies, and saves hours of manual work for solo founders and small teams. The goal is to reduce response time and keep support quality high – without hiring more agents.

It's currently just a landing page while I validate demand. Would love any feedback – especially from folks handling support daily!

Octomailer is a powerful, universal Node.js library for sending transactional emails. It provides a single, unified API to interact with multiple email service providers, allowing you to switch between them effortlessly and implement sophisticated sending strategies.

It monitors battery health, CPU, and memory usage with <1% CPU overhead and <50MB memory footprint. Uses direct IOKit/mach calls and adaptive refresh rates.

MembershipFeatures: - 6 desktop widget styles - Built with SwiftUI, zero dependencies - Works on macOS 11.0+ (Intel + Apple Silicon)

It's open source and I'd love your feedback!

Download: https://microverse.ashwch.com GitHub: https://github.com/ashwch/microverse

Calligro is an open source tool for generating bitmap fonts. It uses the same specification as AngelCode's BMFont but unlike other similar programs it's designed specifically to work with characters you draw yourself.

Basically, you export a template, draw your characters in it with any graphics editor, and then import it back to Calligro and generate a bitmap font.

It has both online and offline version. I just released version 2.0 with completely revamped UI.