pramitsaha123

Laya Fast Router — AI skill for Claude Code

AI community

A lightweight decision routing model designed to replace slow, expensive LLMs for simple classification and context selection tasks.

How to install Laya Fast Router

This entry records only its repository, not the path inside it, so there is no exact command to give. Open pramitsaha123/laya-fast-router and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Laya Fast Router does

A lightweight decision routing model designed to replace slow, expensive LLMs for simple classification and context selection tasks. Drastically reduce your AI agent's latency and token costs by determining the exact bounded context before invoking heavy models like Claude or GPT.

Alternatives in AI

Browserwing — BrowserWing turns your browser actions into MCP commands Or Claude Skill, allowing AI agents to control browse 1.2k ★
Model Selection — Model Selection & Task Tool 1.1k ★
Graymatter — 30 sec to give your AI agents persistent memory 460 ★

README

Laya Router Demo

A minimal example of using the [Laya](https://huggingface.co/convaiinnovations/laya) decision engine to route a customer-support request.

What it does

The script in `test_laya.py`:

Creates a support request describing a duplicate charge.
Defines three questions for the router: a department choice, an urgency score, and a cancellation-risk check.
Calls Router.predict() and prints the result.

Requirements

Python 3.10 or later
The laya package (version 0.3.20 was used for this example)

Install the dependency in your active Python environment:

python -m pip install laya

Run

From this folder, run:

python .\test_laya.py

The prediction is printed to the console. The package may need to download model files the first time it runs, so an internet connection may be required.