Show HN: Building AI agents client-side JavaScript

A developer has launched Buttercup, an open-source project demonstrating AI agents built entirely in client-side JavaScript that run in the browser, aiming to reduce infrastructure costs by eliminating server-side proxies and API calls. The project supports offline models via ollama/vLLM and embedded WebLLM, and will publish a weekly guide starting mid-September covering in-browser loops, multimodal vision, remote agent access, and multi-agent coordination.

Hey HN, most agent systems default to server-side Python inside containers and chain frameworks. I wanted to see how far we could push agent in the browser with vanilla JavaScript https://buttercup.sh https://buttercup.sh The reason this is interesting is because agent loops in the browser keeps infrastructure costs low. No need for proxy or API calls. And ollama/vLLM can be used for 100% offline. Also WebLLM for embedded. We need to consider CORS, API keys for remote models, access to visual state, and handling remote tool calls. I am working on a guide with references in vanilla JS. This is a short-lived guide starting mid-September with weekly topics. Draft topics starting mid-September: In-Browser Loops: Function calling, and deterministic multi-turn loops running purely in the browser runtime. Vision Multimodal : Capturing viewport screenshots using browser APIs. Remote Agent Access & Transports: Connecting the in-browser agent to remote agents. Multi-Agent Coordination: Lightweight client-side agent, specialist delegation, and running concurrent sub-agents without locking the browser UI thread. Everything is open source, zero-install, and runnable directly in the browser. Would love feedback from the HN community on agents running in browsers. Comments URL: https://news.ycombinator.com/item?id=49557409 https://news.ycombinator.com/item?id=49557409 Points: 1 Comments: 0