nowfound

Alternatives

Products that do what I built TreeSnap – turn your code into a prompt ready bundle does

I built over 3-4 weeks to solve my own pain point, picking up rust along the way. It has a browser version that works online/offline and cross platform desktop as well. It was a pretty intense sprint. About TreeSnap, well it simplifies this preparation of sharing code with Chat LLMs. In my use case, making o3 via ChatGPT a lot more cost-effective to use for these tasks compared to Cursor: How it works: Select files/folders → generates a single text bundle + ASCII tree Instantly shows per-file and total token counts (list & treemap views) Quickly trim unnecessary files or folders to…

  1. 1
    MashuPack112

    Turn codebases into a clean file for Claude and ChatGPT

    May 2026

  2. 2CF

    Over this past month I had the idea to build a 100% open-source MIT-licensed tool to simplify sharing code with LLMs, without the vendor lock-in you get from most SDKs. Right now, it’s way too hard to export your data or work freely with models like o1 PRO or Grok 3, especially since they don’t even have API access. So I built OpenRepoPrompt, an open-source tool from wildberry-source that serializes files and folders into XML for LLMs. I coded/designed from 12PM -> 11PM on Saturday and 8AM -> 11PM on Sunday. There are still tons of features missing (I'm working on better file filtering…

    2025 · github.com

  3. 3TA

    Hi HN! This Christmas I made `tysm`, a rust crates which simplifies using ChatGPT with Structured Outputs. Essentially you just tell it the rust type you want the output to conform to, and it handles creating the JSON Schema, passing it to ChatGPT's chat-completions API, and deserializing the response. Structured Outputs are very useful because they guarantee that the response will conform to whatever type you expect. I'm already finding my crate very useful since I love using Structured Outputs but I hate writing JSON Schemas myself. Technical details for rust heads: To generate the JSON…

    2024 · github.com

  4. 4IB

    Hey HN, Like many of you, I’ve been using ChatGPT to brainstorm, debug code, and even plan projects. But as the number of conversations grew, I found myself scrolling endlessly trying to find old chats. It was frustrating and unproductive. So, I built PinFold – a Chrome extension to help manage and organize ChatGPT conversations. With PinFold, you can: Pin important chats for quick access. Organize conversations into folders (e.g., personal vs. work-related). Declutter your ChatGPT history and boost productivity. It's privacy-focused: no data is sent to external servers – everything is…

    2024 · pinfold.me

  5. 5MF

    Hey HN. I've just launched my very first webappp and would love your feedback. http://www.7bks.com It's a book list sharing website - kind of like playlists for bookworms. The site is built on pyton/appengine - and I learned to code in under 4 weeks to build the site. There's more details on the background of the site here: http://www.7bks.com/blog/179001 I've also published the full Python code for the site here: https://gist.github.com/670034 Feedback is really important to me and I want to work hard to make the site better so any and all suggestions are greatly appreciated. Contact…

    2010

  6. 6WA

    TLDR: Check out our documentation search here: https://xata.io/docs/overview Hello HN. I'm a designer over at Xata. We build a serverless database platform on top of Postgres and Elastic-like search that provides goodies like a native TypeScript client for type support in your IDE. Long story short, we're trying to bundle all the normal stuff you need out of a database along with branching, so you don't have to glue everything together. Today we added a new /ask/ endpoint to our search product that bundles in ChatGPT support into any stored data. Why would you…

    2023 · xata.io

  7. 7SP

    Hello HN. This is my first webapp. It works like a pastebin, in which you can visually keep track of the changes you and others make to it. I was a little reluctant about posting it here because I'm not sure it meets the HN quality standards, but, as a beginner, I would really appreciate to have some feedback and/or tips. The url is: http://srctree.net/ An example of usage: http://srctree.net/1 Thanks!

    2012

  8. 8IE

    Quick note on how it works and how I've done my batch embedding engine IgniteMS. The whole thing runs as one process using Rust, reading input, tokenizing, packing batches, keeping the queue full. TensorRT handles inference. Python is only as a wrapper. I built it this way because when you use more than couple of GPUs, the GPUs stop being the problem. CPU cannot feed them fast enough. One A100 can go through batches faster than Python can tokenize and feed, so the GPU just sits there idle waiting for work. Most of my time went into optimizing this. At 8 GPUs that was basically the entire…

    Jun 2026 · github.com

  9. 9NT

    I built a CLI tool that turns codebases and PRs into diagrams so you can quickly understand how things fit together. Originally made it because I couldn't follow my own AI-generated repos. Just shipped a big update: - Switched from D2 to Mermaid for rendering - Tree-sitter AST parsing + agentic flow instead of raw LLM calls. ~50x faster. - Works on any GitHub repo or PR, not just local - Dropped the web frontend, it's just a CLI now - Published as a pip package Still a ton to improve and I'm building fast. Feedback, issues, PRs all welcome.

    Feb 2026 · github.com

  10. 10KY

    Hey HN! I wanted to practice "vibe coding" and see how far and fast I can go by only prompting, without actual coding. I decided to make a simple CLI app that scrapes web docs into a single md file (I was annoyed that LLM keeps writing Tailwind 3 code for a Tailwind 4 project). In just a couple of hours, the CLI app was ready! Then iterated on arguments for another couple of hours. Result: https://github.com/vladstudio/web2llm Then I decided to go further and "productize" the CLI by making a web app for it. Another half-day, and the web app is ready!…

    2025 · web2llm.dev

  11. 11BY

    Hey HN! I spent the last year building a programming challenges site targeted at intermediate/advanced programmers [1]. Challenges follow the "Build your own X" format, where you learn about a popular open source tool by building a small version yourself (popularized by this Github repo [2]). The primary difference compared to other coding challenge websites like Codecademy, HackerRank, Exercism etc. is that we offer real-world programming challenges - no inverting binary trees here! I've posted about this multiple times here before, but haven't managed to gather much interest. Trying…

    2021

  12. 12IB

    After fine-tuning GPT for a personal project, I realized how tedious it is to write plain text in a massive JSON file. That's why I built this app for my own use, and I want to see if others could benefit from a tool like this as well ;)

    2024 · finetuna-ui.com

  13. 13IM

    I spent the past few weeks making an open source cloud code editing environment with an AI copilot and multiplayer collaboration! It's fully self-hostable in 5-10 minutes. There's a lot of minor improvements to be made, and some are already listed in the Github issues. Let me know what you think and feel free to try it out.

    2024 · github.com

  14. 14CA

    Just finished the first draft of my weekend project. Sadly my industry is far away from all the exciting machine learning developments happening right now, so I wrote this project as my first exploration into the world of LLMs. It's not perfect, but I'm excited to see where the project goes from here! https://github.com/clarkmcc/chitchat My main motivations were: - Easy-of-use: Many models are supported out-of-the-box so users don't have to figure out how to download, where to save, etc. - Intuitive: A clean interface - Cross platform: The project is written in Rust and…

    2023 · clarkmccauley.com

  15. 15BA

    I built CodinIT because I wanted that "Bolt-like" experience, but on my own terms. 100% Open Source The core idea: You should be able to prompt a full-stack application into existence, but the environment should be local, the models should be swappable (Ollama/LM Studio support was a priority), and the output should be standard code you actually own. A few things I focused on: Context Management: One of the hardest parts was figuring out how to feed the right file context back to the LLM without blowing out the token limit. I’ve implemented a custom indexing approach to keep the "vibe…

    Dec 2025 · github.com

  16. 16AL

    Hi HN! I wanted to share my freshly finished open-source project. It is similar to ChatGPT Code Interpreter, but the interpreter runs locally and it can use open-source models like Llama 2. It allows you to work with sensitive data without uploading it to the cloud. Either you use a local LLM (like Llama 2), or an API (like GPT-4). For the latter case, there is an approval mechanism in the UI, which separates your local data from the remote services. I would be very interested in your valuable feedback!

    2023 · github.com

  17. 17RC

    I'm learning Rust and put this together from sample code over a few days. Rust is incredibly fun (I normally work with Go and Swift). My goal is to see if I can put the client on a development board running xBSD and use a touchscreen for input. Client https://github.com/zkirill/thor Server https://github.com/zkirill/odin You need Rust 1.7.0 and Cargo 0.9.0 to compile. The package for FreeBSD doesn't currently go that high so you need to use a port (instructions at https://gist.github.com/zkirill/4fb42b4ba4b7cc58c4f0) Packages of…

    2016

  18. 18IM

    Hey HN. I've made a tool that parses RSS feeds and creates ready-to-post Tweets with ChatGPT.

    2024 · rsstotweet.xyz

  19. 19AB

    Hey! Alexis and Tobi here. We built a native macOS client for ChatGPT API that is free to use (macOS Ventura). https://www.jamgpt.app/ We built and fine-tuned it to scratch our own specific text-processing itches, so we just wanted to share this with the community. If you work with a lot of text or code like we do, check it out. Its core features include: - Instantly talk to ChatGPT from anywhere on your Mac by pressing a keyboard shortcut. - Avoid typing out repetitive prompts by saving prompts and accessing them quickly. - Just download and start typing as you would with…

    2023

  20. 20CO

    We have been using GPT to write code since playground days. This UI avoids logins, gpt-4 throttling and is also cheaper to use than ChatGPT Premium. We also have various features to minimize costs and speed up iteration. Furthermore html & mermaid previews are a taste of the kind of features help-yourself opensource model enables vs official UI. For backstory see our blog posts: https://blog.humphd.org/chatcraft-org/ https://taras.glek.net/post/chatcraft.org-opensourcechatgpt-...

    2023 · chatcraft.org

  21. 21IB

    Fully leaned into vibe coding this time around. Started on v0, at some point ejected into running locally (getting v0's exported folder to run locally was a challenge), then iterated with Cursor over the course of a few hours. Really neat how much can be accomplished just conversationally these days.

    2025 · macrodata-refinement.arjit.me

  22. 22OS

    Hi friends! I've been waiting for ChatGPT Code Interpreter access for so long that I decided to just build my own. I figured maybe some of you are in the same boat so decided to do it as an Open Source project.

    2023 · ricklamers.io

  23. 23AC

    For the past couple of months, I’ve been building a tool that enables natural language search over large codebases using Tree-Sitter for syntax parsing and Qdrant for vector-based retrieval. https://app.repogram.com ### How It Works - Tree-Sitter is used to parse syntax trees and extract high-quality vector embeddings of code. - These embeddings are stored in Qdrant, enabling fast similarity search across your entire repo. - A combination of re-ranking processes refine search results, producing highly relevant answers to code-related questions. The results have been incredibly…

    2025 · app.repogram.com

  24. 24IB

    Hey Guys, I created GithubReader.org (open-source, non-profit, most of the code is written by ChatGPT). My motivation: I wanted an easy way to keep a list of repositories I want to learn from and access them quickly. So, I built a search page where I can find repositories by name, like Google. Also, I wanted a nicer way to read Markdown files on my laptop without the GitHub UI, like reading a book. So, I made a custom UI with a back button that takes you to the previous state without jumping pages. The markdown links are sharable, e.g.…

    2024 · githubreader.org

Ranked by how close each launch is in meaning, then by votes. Refine with a description →