Wool Ball – Decentralizing AI with Distributed Browsers
Hi HN, I recently launched Wool Ball (https://woolball.xyz), a project designed to test the concept of paying people to enable their devices to process AI tasks through their browsers. The idea revolves around “browser as a service” or “browser as a server,” leveraging idle browser resources to create a decentralized, scalable, and cost-effective way to run AI workloads. We’re still in the early stages, and I’d love to hear your feedback on the concept and the product we’re building. Overview: https://woolball.xyz/Guide What do you think of this approach to…
What it does
In the maker’s words, at launch
Hi HN, I recently launched Wool Ball (https://woolball.xyz), a project designed to test the concept of paying people to enable their devices to process AI tasks through their browsers. The idea revolves around “browser as a service” or “browser as a server,” leveraging idle browser resources to create a decentralized, scalable, and cost-effective way to run AI workloads. We’re still in the early stages, and I’d love to hear your feedback on the concept and the product we’re building. Overview: https://woolball.xyz/Guide What do you think of this approach to decentralizing AI?
Does the same job
all alternatives →- MAMeatshields – An in-browser turn-based strategy game2017 · ▲113
A few months ago (82 days to be exact!) I posted a link on HN to my game, Meatshields. A bunch of you commented and played my game and gave me some wonderful feedback. Over the last few months I've been playing with many of you and implementing the best of everybody's suggestions. So, thank you, HN for all your help! I feel this is an extreme overhaul I couldn't have done without your input. Since then, I have: Dramatically improved our hosting platform (So it HOPEFULLY won't go down this time (oops.)), Added two new units, Rebalanced all existing units, Added many more maps, Improved the…
- MWmy weekend project, a "framework" for IRC apps/bots2011 · ▲24
This is a little project I've been working on for a while in order to better learn Python. Although IRC may not exactly be the most exciting medium, I still find it to be fun and useful, this interest lead me to writing a bot. In doing this I realized that what would actually be more interesting would be if I had a framework. There may already be such a thing, certainly there are IRC libraries, but I don't know if they're well-suited to deploying bots. At any rate if for no other reason than the fact that I am relatively new to programming and eager to learn I decided to build a framework.…
- BABrowser4 – an open-source browser engine for agents and concurrencyDec 2025 · github.com · ▲7
Hi HN, I’d like to share an open-source project we’ve been working on for a while: Browser4. The motivation came from a recurring frustration: most browser automation tools (Playwright, Selenium, Puppeteer) are excellent for human-written scripts, but start to show friction when used as a core execution layer for AI agents or at very high concurrency. So instead of building “another wrapper around Playwright”, we experimented with a different direction: designing a browser engine where AI agents are first-class citizens. ### What Browser4 is Browser4 is a browser automation engine built on…
Maritime, a platform for running AI agents for $1 a month18d ago · maritime.sh · ▲8Hi HN, my name is Maria, and I’m a co-founder of Maritime. We started Maritime at MIT to build infrastructure for companies that need to run thousands of isolated AI agents for their customers. Imagine you set up an agent like OpenClaw, or a personal assistant agent with a custom framework, and want to give a separate version of it to every customer/friend. Each customer needs their own agent running in an isolated microVM, with persistent state, secrets, triggers, and sleep/wake behavior. Building such scalable and secure infra will take you months and will cost hundreds of…
- AMA multiplayer game to discover NFT artists, built with WebAssembly2022 · play.moonlightmuseum.io · ▲9
Hi everyone! I'm one of the developers behind this project. I wrote it with my two brothers, Daniel and Ricardo. For years the three of us have been curious about how multiplayer games work, which is why we decided to work on this project. Our goal was to gain a deep understanding of how different players can share the same 3D space, which is why we wrote our own tiny game engine instead of using something like Unity. We wrote the engine using C++ and OpenGL, and we then compiled it to WebAssembly using Emscripten so that it would run effortlessly on web browsers. We are really excited about…
- HOHive – open-source Marketplace for AI2024 · hivenetwork.ai · ▲9
gm gm, We’re excited to show our project, Hive Network, a new frontier for decentralized AI agents that operate both on-chain and off-chain. Our mission is to make AI more powerful and transparent, and we’re inviting you to join us in this revolution. What is Hive Network AI? -- Hive Network AI is a platform where developers can create, deploy, and manage AI agents that function autonomously across blockchain and traditional networks. Our system addresses significant issues in the AI space, such as the lack of transparency, difficulty in monetizing models, and insufficient research funding.…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
