Aller au contenu
TakoAPI
Retour aux skills

communicate

par kenblive

AI & LLMs
—Pas encore noté
Ta note

Résumé

Start using a local or Hugging Face model instantly, directly from chat.

Description

Ce que fait ce skill

ModelReady starts a local or Hugging Face model as an OpenAI-compatible endpoint and lets you chat with it directly from a conversation. It handles server startup, status checks, and teardown without switching tools.

It removes the manual steps of configuring vLLM, managing endpoints, and opening a separate chat interface.

Quand l'utiliser

  • Testing a newly downloaded Hugging Face model without writing server code
  • Running a quantized local LLM on a specific port during development
  • Chatting with a self-hosted model from the terminal
  • Switching between multiple model servers by port
  • Exposing a local model to other tools via OpenAI-compatible API

Exemple de workflow

ENTRÉE

User asks: start Qwen2.5-7B on port 8010 and send it a test message

AGENT
  1. 1

    Run /modelready start repo=Qwen/Qwen2.5-7B-Instruct port=8010

  2. 2

    Poll /modelready status port=8010 until the server reports ready

  3. 3

    Run /modelready chat port=8010 text="hello"

  4. 4

    Return the model response to the user

SORTIE

The locally running Qwen2.5-7B instance replies to the greeting

Prérequis

  • URL environment variable set to the target host address

Installation

clawhub install kenblive/communicate

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens