A tiny LFM2.5 fine-tune that drives a storefront entirely in-browser with tool calls and RAG - trained on interaction patterns, not domain facts
TL;DR: I fine-tuned LiquidAI's LFM2.5 (230M and 350M) into a generic front-end agent that runs entirely in the browser - no server, no API key, no cloud costs.
It doesn't just chat; it calls real tools to browse a catalog, answers grounded questions, and manages a cart.
The trick: it's trained on interaction patterns, not domain facts, so the same weights drive a coffee store, an absurdist emporium, or a corner grocer - with zero retraining.
Live demo on Github pages.
Why?
Liquid AI's LFM2.5-230M is a 230M-parameter open-weight on-device model for fast tool use and large-scale data extraction.
Most "AI chat widget" tutorials assume you're calling out to an LLM API. This post is about the...
For months, we’ve treated LLMs like fancy autocomplete engines. You prompt, you wait, you copy-paste...
This is the first post of series Building TinyAgent where we are going to build a small agent from...
Open-source agent-first Chromium browser: compact observations, stable refs, MCP server. ~98% fewer tokens than raw HTML.
Introduction Part 3 of the Zero Dollar personal AI Assistant series, running Local LLMs on...
