Alternatives
Products that do what I Built a UI to finetune LLMs x100 faster does
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 ;)
- 1FL
I've been playing around with https://github.com/zphang/minimal-llama/ and https://github.com/tloen/alpaca-lora/blob/main/finetune.py, and wanted to create a simple UI where you can just paste text, tweak the parameters, and finetune the model quickly using a modern GPU. To prepare the data, simply separate your text with two blank lines. There's an inference tab, so you can test how the tuned model behaves. This is my first foray into the world of LLM finetuning, Python, Torch, Transformers, LoRA, PEFT, and Gradio. Enjoy!
2023 · github.com
- 2AB
All LLM user interfaces I've seen so far are somewhat frustrating: * ChatGPT web requires a lot of copy-paste, it rewrites whole document even if you need to update a part of it, etc. * Github Copilot completions are rather unreliable and do not leave an option to specify what you want; Copilot's chat sidebar is little more than ChatGPT integrated into the IDE * Google Docs have right UI for non-code text, but they use really dumb model (not Gemini 1.5 Pro). Also won't work for code. So... I wrote a Emacs Lisp function which calls LLM with contents of the buffer to generate text according to…
2024 · x.com
- 3PR
Hi HN, While building RAG agents, I noticed a lot of token budget was wasted on formatting overhead (HTML tags, JSON structure, whitespace). Existing solutions felt too heavy (often requiring torch/transformers), so I wrote this lightweight, zero-dependency library to solve it. It includes strategies for context packing, PII redaction, and tool output compression. Benchmarks show it can save ~15% of tokens with negligible latency overhead (<0.5ms). Happy to answer any questions!
Dec 2025 · github.com
- 4EL
Hey HN! I built Experiment to solve a common frustration in LLM development: the lack of proper tools for prompt engineering experimentation. Here's what makes it different: Key Features: - Load and edit chat completion logs from CSV files - Fork and modify specific conversation entries - Run inference via Anthropic, Mistral, and OpenAI - Define custom tools using JSONSchema format - Visual tool usage analysis with collapsible, sorted key-value pairs - Full mobile support and available as installable PWA Technical Highlights: - Built with React using custom isomorphic architecture -…
2025 · github.com
- 5NT
With the latest launch from Google I've added support for Gemma 3 270M, the speed for local LLM to TTS token time is incredible! This is an heavy obvious work in progress - any contributions or tips would be welcome. The idea is to have a fast moving edge model playground, and maybe have some utility (like the e reader) on the side.
2025 · github.com
- 6WA
After getting impatient with a "SwiftUI for Designers" course I decided to fuck around and find out. Just hours after asking my 1st question: "Are you familiar with SwiftUI?" the core functionality of this app (an exercise utility) was up and working. I've spent the past week tweaking the UI with small animations and features. It's a humble tool (local storage only) but I am nonetheless floored with how GPT has allowed me to completely skip the "learning syntax" part of development and ship something that I actually use. Not only did it lower the syntax bar virtually to 0... I've learned…
2023 · testflight.apple.com
- 7GL
Hey everyone! I made a Mac app for exploring large language models. It’s fast, small, has a tiny memory footprint. It’s immutable by design with both immediate time travel and automatic versioning as foundational elements. The app is written in Swift and a bit of Rust for the tokenizer. I used SwiftUI for structure and animations and Cocoa for advanced behavior. All storage is SQLite and local-only. You can go through the database as needed and backup it as well. The app has support for variants, which is the `n` parameter in the OpenAI chat completion API—equivalent to the drafts feature in…
2023 · thellm.app
- 8IW
Jul 2026 · aidekin.com
- 9BA
I've been specializing in UI for over a decade. Using code for UI is great but I always wished there was a more visual code to build apps and sites. So I went ahead and built it. Decided to build it with Compose Multiplatform since I work a lot with Kotlin. Currently exports to CMP as it was simpler due to the context switch. You can try it for free and export some apps
2025 · license.builtwithpaper.com
- 10OA
Thesys just open-sourced their generative UI rendering engine. Interesting timing given where Google a2ui and Vercel's json-render are headed. The difference worth noting: a2ui and json-render both treat JSONL as the contract between the LLM and the renderer. Thesys is betting that's the wrong primitive. Their engine uses a code-like syntax (OpenUI Lang) instead — LLM writes it, renderer executes it. The argument is that LLMs are fundamentally better at generating code than generating structured data, so you get cleaner output and ~67% fewer tokens. The broader vision seems to be a…
Mar 2026 · openui.com
- 11IM
- 12PU
After seeing a cool demo of a hack on Twitter, I built a cross platform version of it that works well and uses streaming. From anywhere on Mac and Linux, trigger Ollama and optionally feed it your clipboard. I built it yesterday and it's already very useful to me. I'm pretty excited about it and wanted to share!
2024 · github.com
- 13E
Hello everyone, A couple of months ago I was introduced to Excalidraw and fell in love with it instantly. The only thing I didn't like was that I couldn't easily save my whiteboards and had to put everything in one whiteboard which started to lag my PC after a while. So I made ExcaliHub. It's exactly as it sounds: a hub for Excalidraw. It's free, open source, and I aim to keep it that way. Thanks in advance for any feedback!
2024 · excalihub.dev
- 14IM
Hi HN! In the last couple of weeks I've been working on Cranki: Cranki = Crosswords + Anki. (It's a stupid name tbh, haha) I like doing crosswords in Spanish (to learn vocab) but none of the apps out there allowed me to use my own list of words that I come across. So I built one instead. It's entirely client-side. No server, no database, no accounts, etc. Your words and stats are stored in local storage. I built this for myself but let me know if you like it!
Apr 2026 · cranki.app
- 15IM
Try it at: ssh krnl.duetbrowser.com No sign up, totally free - no download. Let me know what you think. Prior art exists (brow.sh) but I wasn't satisfied with their graphical take. I wanted the raw, old skool terminal days of the early internet - BBS, and old green phosphor library comptuers - but running the modern web, with all the bells and jingle jangle whistles (JavaScript, etc). No funding, no VC, just 100% raw terminal fun. Not sure how long the demo will last, but try it out.
Jul 2026
- 16TL
Little tool that I made to understand how (un)reasonable my prompts are.
Jan 2026 · github.com
- 17GB
Hey HN, We’re excited to share PySpur, an open-source tool that provides a graph-based interface for building, debugging, and evaluating LLM workflows. Why we built this: Before this, we built several LLM-powered applications that collectively served thousands of users. The biggest challenge we faced was ensuring reliability: making sure the workflows were robust enough to handle edge cases and deliver consistent results. In practice, achieving this reliability meant repeatedly: 1. Breaking down complex goals into simpler steps: Composing prompts, tool calls, parsing steps, and branching…
2024 · github.com
- 18AG
Put this together this afternoon. I've been after something to quickly jot down the odd piece of information that I can access later in the day when browsing the web. Hopefully you find it useful. Criticism/thoughts/ideas greatly appreciated. I should add, since all the hard work here lies in the work of others here — garlic.js is a great plugin for handling localstorage. Cheers Jason
2012 · a5.gg
- 19IB
hey hn, I built an open-source Perplexity clone that can run local LLMs and cloud LLMs. It's fully self-hostable through Docker and uses ollama to support local LLMs. The demo video in the repository shows me running it locally with llama3 on my M1 Macbook Pro. I'm open to any suggestions or feedback, thanks!
2024 · github.com
- 20
Token-efficiency linter for LLM prompts and payloads - ritenv/tokensift
8d ago · github.com
- 21IM
Live demo here: http://fonctionlabs.com:8000 Similarly to aka_sh (guess we were working parallelly on similar topics), I created with my brother a chainlit-based webapp, which summarizes Youtube videos in order to gain time. It works as an RAG-based LLM, and is very light in the sense that it does not use RAG libraries like langchain or llamaindex. You can use it with your own OpenAI API key. It also supports local models like Mistral, or Llamma. It is ofc open-source, and you can deploy with Docker if you choose. Some of the next steps are: - using whisper to be able to compute a…
2024 · github.com
- 22IB
I had 14,000 photos sitting on a drive and wanted an excuse to play with local vision models and Elixir/Phoenix. I originally tried to get LLaVA to tell me if a photo was 'good' or matched my style, but quickly learned that LLMs have terrible taste. I ended up demoting the LLM to just extract metadata, and built a custom CLIP/Ridge Regression pipeline to actually learn my preferences based on how I rate things. The stack is Phoenix/Oban on the orchestrator side, and Python/FastAPI/Instructor for the AI workers. Happy to answer any questions about the architecture,…
Apr 2026 · qwelian.com
- 23GH
I've never used .NET, know nothing about .NET or vb, or anything outside vc++ & MFC. Recently I gave GPT a try, guiding it step by step, and asking it to help me rebuild a tool I originally wrote in MFC. To my surprise, it worked: a full Excel-to-PDF automation app, done in 30 minutes; including a small algorithm I thought would be too tricky for AI to handle. I didn't understand even a single line of the code, I just kept asking, copying, and running. It felt amazing… but also terrifying.If AI can do this now, what happens 5 years from now? Here's a 5-min video I made showing the full…
2025
Ranked by how close each launch is in meaning, then by votes. Refine with a description →