Alternatives
Products that do what Unsloth Studio - Local Fine-tuning, Chat UI does
Hey HN! We're excited to release Unsloth Studio - a culmination of many things we wanted to provide to the community - it includes: 1. A Chat UI which has auto healing tool calling, Python & bash code execution, web search, image, docs input + more! 2. Finetuning of audio, vision, LLMs with an Auto AI Assist data prep 3. Supports GGUFs, Mac, Windows, Linux + audio gen 4. Has SVG rendering in browser, exporting to GGUF 5. gpt-oss harmony rendering, all inference parameters are pre-set and recommended 6. Data designer + synthetic data generation 7. Fast parallel data prep + embedding…
- 1
- 2
- 3
- 4
- 5OS
Posted before, but wanted to share if you want an open source alternative to OpenAI fine-tuning, give Unsloth a try! Phi 3.5 was just released, and is distilled from GPT4. Unsloth makes finetuning 2x faster, uses 70% less VRAM + has no accuracy degradations. We rewrite all backprop steps and reduce FLOPs and write everything in Triton (JIT low level CUDA). If you want to own the weights after fine-tuning, give Unsloth a spin! I have free Colabs and Kaggle notebooks as well at https://github.com/unslothai/unsloth
2024 · colab.research.google.com
- 6
- 7CR
Hey HN, what I wanted to build here is a proper universal layer for persisted agentic sessions, that could be seamlessly interacted both via web and a messenger (Telegram). I really like what's done so far and would be nice to hear some feedback from you. The interesting thing is that I started to use Chatcode during its development as soon it was possible, so used this tool to build itself. I know that there could be trust/privacy concerns, because it relies on a gateway that you need to install on your machine in order to work, but: 1. You can use it on any machine, just have some…
Jun 2026 · chatcode.dev
- 8IM
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
- 9EE
Hey everyone on HN! We recently spent the past couple of weeks building out an end-to-end platform which can plug-in multiple models (both open/closed-source) to create voice driven conversational applications. We've tried to make the process simple & concise through documentation. Feel free to try it out and provide feedback. We will be launching a dashboard in the coming week for monitoring and analytics alongwith more open source models. Let us know what you all think. (if you want to contribute, we have tons of features planned - do let us know)
2023 · github.com
- 10GS
This weekend I finally shipped Gryt, a project I’ve been building since 2022 — an open-source, self-hostable Discord-style app focused on reliable voice chat + text. I’m the creator. I started it after getting fed up with Discord disconnects/paywalls and wanted something self-hosted and auditable. I started on this in 2022 and had an early proof-of-concept working back then (auth + friends list), but I quickly realized WebRTC voice isn’t something you can duct-tape together. I spent a big chunk of the next couple years learning the stack (ICE/DTLS-SRTP, NAT traversal, SFU design),…
Feb 2026 · gryt.chat
- 11IB
Hey HN, I built a website where you can train Llama 3.1 8b & 70b (4bit) on your data. I use unsloth in the backend and the training is done on H100s which I rent programmatically from Runpod. I'd love some feedback. If you would be interested in using it feel free to book a chat with me: cal.com/hamada/tunellama-intro Happy to give you free credits :) P.S. I'm also looking for a co-founder as I have big plans for this.
2024 · tunellama.com
- 12LA
Hi HN, I’m excited to share LocoStudio (http://locostudio.ai), a local-first AI chat app for Mac that lets you chat with AI models both locally and in the cloud—all in one place. Why I built it: I wanted a private, fast, and flexible way to use the latest AI models without sending my data to the cloud. Most AI chat apps are either cloud-only (raising privacy concerns) or have clunky interfaces for local models. LocoStudio aims to make local AI chat as easy and powerful as using ChatGPT, but with your data staying on your device. What it does: - Private, local-first: Run open models…
2025 · locostudio.ai
- 13LB
Howdy friends! Tell me if this is an atrociously terrible idea - I've been working on building a leetcode for clientside devs so we can practice React and Javascript interview questions in a more concise way, I call it clientside.dev I just finished a beta version of it yesterday and plan on releasing it with many more problems on Jan 1st but it's there if you wanna play with it open to any ideas / feedback however mean or nice it may be :)
2022 · vacation-call-335691.framer.app
- 14WO
Hey guys, I am think of building an open-source version of Perplexity to let devs play around with it. But with all the existing tools available what features would you want? Anything specific? What is missing? Currently working on - 1. Streaming text 2. Citations sources 3. Image and file upload 4. Chat history and storage 5. Temperature and custom instructions If you are in marketing or growth can anyone help me with what to focus on while building such an app? Also here is a very first version. Probably will break and most of the buttons also don’t work, built it in 3 days using Bing and…
2024 · omniplex.vercel.app
- 15IO
Hello so I finally released the new version of aidev.codes. It is extremely alpha, has not been thoroughly tested at this point. Its quite different from the previous version. The new aidev.codes: - is buggy but actually works (compared to the old version) - has a ChatGPT-style interface (and uses the chatgpt-turbo model which is actually better than the other models for code) - integrates the stability.ai API to automatically generate images - can create a simple but fully customized and interactive web page and instantly host it for you - can optionally host your page on a custom subdomain…
2023 · aidev.codes
- 16CO
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
- 17EL
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
- 18TA
I built TTSLab — a free, open-source tool for running text-to-speech and speech-to-text models directly in the browser using WebGPU and WASM. No API keys, no backend, no data leaves your machine. When you open the site, you'll hear it immediately — the landing page auto-generates speech from three different sentences right in your browser, no setup required. You can then try any model yourself: type text, hit generate, hear it instantly. Models download once and get cached locally. The most experimental feature: a fully in-browser Voice Agent. It chains speech-to-text → LLM → text-to-speech,…
Feb 2026 · ttslab.dev
- 19IB
Hey HN! Over the past few weeks, I’ve been working on DataBridge, an open-source solution for data ingestion and querying across text, PDFs, images, and videos. In our latest update, we’ve added a fully local deployment option: - No internet required – Runs entirely offline. - Customizable Models – Supports any LLM and embedding model via Ollama (with options for any other private providers) - Extensibility – You can plug in your own models or tools easily. This local-first approach ensures better privacy, security, and flexibility, especially for teams dealing with sensitive data. You can…
2025 · github.com
- 20IM
Hey HN! I made a completely open sourced alternative to Weights and Biases with (insert cringe) blazingly fast performance (yes we use rust and clickhouse) Weights and Biases is super unperformant, their logger blocks user code... logging should not be blocking, yet they got away with it. We do the right thing by being non blocking. Would love any thoughts / feedbacks / roasts etc
2025 · github.com
- 21CA
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
- 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
- 23C2
2021 · github.com
- 24AA
Hey y'all, So - the main idea of this is to make a WebAudio synthesis/sequencer tool which humans can use via the UI, but where the big unlock is for agents to drive with MCP It's semi decent as "make a groovy jazz track", especially for retro sounds - but the real use case is more like "make a jetpack whoosh effect I can control via code at runtime - where the sound changes based on character health or how much fuel is left" In other words, the target audience is not musicians (except maybe of the Max/MSP sort), but more like creative coders who want to shape the sound iteratively…
Jun 2026 · audio.awsm.fun
Ranked by how close each launch is in meaning, then by votes. Refine with a description →