Alternatives
Products that do what SmolCopilot – 360M LLM writing assistant in the browser does
Hey! I've been really intrigued about small, on device models recently. This project was to explore that a small base model running in the browser as a Co Pilot-like writing assistant. You can check out the demo here: smol-complete.vercel.app. Smal, on device models have a lot of advantages with low latency, cost, privacy (a big one), and being task specific. The demo will definitely repeat itself and hallucinate sometimes, but let me know what you think!
- 1SM
Apr 2026 · github.com
- 2
- 3GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
Jul 2026 · github.com
- 4IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
Apr 2026 · github.com
- 5
- 6TN
Kitten TTS (https://github.com/KittenML/KittenTTS) is an open-source series of tiny and expressive text-to-speech models for on-device applications. We had a thread last year here: https://news.ycombinator.com/item?id=44807868. Today we're releasing three new models with 80M, 40M and 14M parameters. The largest model (80M) has the highest quality. The 14M variant reaches new SOTA in expressivity among similar sized models, despite being <25MB in size. This release is a major upgrade from the previous one and supports English text-to-speech applications in…
Mar 2026 · github.com
- 7
- 8TV
May 2026 · github.com
- 9
- 10
Fast LLMs for low-latency and high-performance workflows
Jun 2026 · jetbrains.com
- 11
- 12
- 13
- 14IB
As a high school student, I love LLMs and the execution of Apple's Appel Intelligence Writing Tools, but was disappointed that nothing like that existed for Windows. So, I created Writing Tools, a better than Apple Intelligence open-source alternative that works system-wide on Windows! Key features: - Uses Google's Gemini 1.5 Flash model for superior AI-assisted writing (much better than the tiny 2B parameter Apple Intelligence model) - Works in any application with a customizable hotkey - Proofreads, rewrites, summarizes, and more - Free and privacy-focused (your API key stays local, no…
2024 · github.com
- 15SO
SmolVM is an open-source local sandbox for AI agents on macOS and Linux. I started building it because agent workflows need more than isolated code execution. They need a reusable environment: write files in one step, come back later, snapshot state, pause/resume, and increasingly interact with browsers or full desktop environments. Right now SmolVM is a Python SDK and CLI focused on local developer experience. Current features include: - local sandbox environments - macOS and Linux support - snapshotting - pause/resume - persistent environments across turns Install: ``` curl -sSL…
Apr 2026 · github.com
- 16SA
2019 · sosml.discourse.ps.uni-saarland.de
- 17
- 18LR
I built localLLLM: a small community project for running local models. Live: https://locallllm.fly.dev The goal is simple: if someone has model + OS + GPU + RAM, they should get steps that actually work (ideally one liner) I need help populating and validating guides. If you run local models, please submit one working recipe (or report what failed). Would love to hear general feedback as well!
Apr 2026 · locallllm.fly.dev
- 19AD
Hi all, I threw together a small prototype I am calling “Notepad.ai”. A new take on UIs for interacting with LLMs. While I enjoy using LLM’s in the chat format I wanted to see what it would be like to do it in a more long form style. It let’s you write in a pretty free form, much like Window’s Notepad, but you can choose to hit ctrl+[ to analyze the text with a preset prompt of your choosing. It has a few other small features. It’s WIP and very experimental. I would appreciate any feedback or thoughts. Video: https://youtu.be/ntdlgFmSxQY Live Demo:…
2024 · github.com
- 20
The smallest async RL trainer I could write: one loop that runs REINFORCE on CartPole on a laptop and async GRPO on a cluster (e.g. 8xH100 trainer, 8 vLLM workers, ran as a [SkyPilot job group](https://docs.skypilot.ai/en/latest/examples/job-groups.html) on k8s ). All without Ray or TRL or DeepSpeed etc., workers talk to the trainer over stdlib HTTP.
24d ago · github.com
- 21LG
Goal was to make it easy to jump from textbook learning into immersion. I wanted to play video games in Japanese, and started by using LLMs and a notebook, but figured it would be easier to streamline it all in an app. - You input a sentence in Japanese (easier on mobile where you can handwrite kanji you don't know) - App translates the sentence, explains the grammar, and gives you a list of flash cards - You choose some flash cards to save for studying later - You input a question about the explanation for more information - App explains some more and gives you more flash cards - Repeat And…
2024 · goginko.com
- 22IM
I've been running Pi using SmolVM to build SmolVM! SmolVM provides an abstraction over microVMs to easily create sandboxes for coding agents, OpenClaw, or just to build a custom harness. To use it, install using: curl -sSL https://celesto.ai/install.sh | bash and then run: smolvm pi start
May 2026 · github.com
- 23AG
I’ve been building LLM tooling for a small VC fund and found myself explaining the same mental model over and over to non-technical people around me: how a stateless LLM becomes a chatbot, how tool use works, what an agent is mechanically, and why context windows shape all of it. I never found a guide that covered that full chain at the level I wanted, so I wrote one. It’s nine short chapters, each building on the last. Deliberately simplified: the goal is a useful mental model, not a textbook. Feedback, corrections, and contributions welcome: github.com/ymyke/aiaiai
Apr 2026 · aiaiai.guide
- 24VA
2023 · sdk.vercel.ai
Ranked by how close each launch is in meaning, then by votes. Refine with a description →