skills.rest
alexaundre
alexaundreCOMMUNITY
Explore all skills by this author →
GitHub

cc-lite

Run a local LLM home assistant controlling devices via voice and chat.

Updated Apr 2, 2026
Search Tags:#claude-code#ollama#smart-home#local-llm#memory-system#cc-lite#qwen2.5-3b
One-click install
npx skills add https://github.com/alexaundre/mycc_init --skill cc-lite
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cc-lite
Source: https://github.com/alexaundre/mycc_init/tree/main/.claude/skills/cc-lite
Command: npx skills add https://github.com/alexaundre/mycc_init --skill cc-lite

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

cc-lite provides a local intelligent home assistant built on Ollama and Qwen2.5-3B, reusing the MyCC memory system and rules to automate smart home tasks without relying on cloud access.

Core Features & Use Cases

  • Local AI home assistant for Beijing and Hangzhou homes.
  • Voice-triggered home automation and chat-style interactions for lights, switches, speakers, and TVs.
  • Extendable architecture through skills stored as SKILL.md in .claude/skills to add new capabilities.

Quick Start

In the terminal, run python3 cc_lite.py to start cc-lite and begin interacting with your local home-automation assistant.

Frequently Asked Questions about cc-lite

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a local smart home assistant with Ollama and a local LLM?▼

cc-lite runs a local LLM agent with Ollama and the Qwen2.5-3B model to control home devices via voice and chat without cloud access. It requires a local Ollama setup, a shared memory system, and a CLAUDE.md configuration to automate tasks offline.

Can I use a local LLM for home automation without relying on cloud access?▼

Yes, a local LLM enables offline home automation by running Ollama with the Qwen2.5-3B model. This setup provides voice-triggered control and chat-style interactions for lights, switches, speakers, and TVs without cloud access.

How do I add new skills to a local AI home assistant?▼

You extend the local AI home assistant by adding new SKILL.md files under the .claude/skills directory. This extendable architecture allows the assistant to grow new capabilities for controlling devices and handling additional tasks.

How does a local LLM memory system work for controlling devices across multiple homes?▼

A local LLM memory system shares context and rules to maintain consistent device control across multiple homes. This setup operates across two locations, using the shared memory to automate lights, switches, speakers, and TVs via local chat and voice interactions.

Do I need the Qwen2.5-3B model specifically to run a local home automation agent?▼

The Qwen2.5-3B model is the specified requirement for running this local home automation agent. Operational setup requires a local Ollama installation configured with Qwen2.5-3B alongside the shared memory system and CLAUDE.md configuration to function properly.

Related Skills

Explore More Software Engineering Skills→
marcusmarcus
3

ollama-python-streaming

Streams responses from a local Ollama LLM in Python using LiteLLM with async support, retry logic, and adjustable thinking levels.

Community
Advanced
phivhphivh

Create New Skills

Create new Agent Skills with SKILL.md structure and YAML frontmatter.

Community
Basic
benjaminshafiibenjaminshafii
10

home-assistant

Control Home Assistant devices via REST API with curl requests.

Community
Basic
tangzheng202202tangzheng202202
1

diy-smart-home-ai-companion

Design and deploy a local-first smart home with Home Assistant, Frigate, and Ollama.

Community
Advanced