Nanoclaw Ai Assistant
Skill by adisinghstudent
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/adisinghstudent/nanoclaw-ai-assistantWhat This Skill Does
NanoClaw AI Assistant is a high-performance, containerized agentic framework designed to bring Claude's reasoning capabilities directly into your daily messaging workflow. Unlike standard chatbot integrations, NanoClaw operates as a local orchestrator that runs agents within isolated Linux containers (via Docker or Apple Container). This ensures that every task performed is sandboxed, secure, and reproducible. The assistant supports multi-channel communication, allowing you to interface with WhatsApp, Telegram, Slack, Discord, and Gmail through a unified memory layer. Each conversation thread or group maintains its own persistent memory stored in CLAUDE.md files, enabling the agent to recall context, preferences, and long-term project goals across sessions. Built on Anthropic’s Agent SDK, it is modular, lightweight, and designed for users who value local control and deep customization.
Installation
To deploy NanoClaw, ensure you have Node.js 20+ and Claude Code installed. Begin by forking the official repository: gh repo fork qwibitai/nanoclaw --clone. Navigate into the project folder and trigger the automated installation via the Claude CLI command /setup. This process will automatically provision your containers and authenticate necessary services. For macOS users, running the environment-specific setup script curl -fsSL https://nanoclaw.dev/install-docker-sandboxes.sh | bash is highly recommended for optimal performance with Apple Silicon. Ensure your ANTHROPIC_API_KEY is correctly defined in your .env file before executing.
Use Cases
NanoClaw shines in cross-platform communication management. You can use it as an automated concierge for Discord groups, a scheduling assistant for Slack, or a summary tool for incoming Gmail threads. Because it utilizes SQLite for state management, it is perfect for users who need to track long-running projects across multiple platforms without losing data when the application restarts. The containerized nature makes it an excellent tool for developers who want to run autonomous tasks like local code testing or automated script execution without exposing their main host system to unnecessary risks.
Example Prompts
- "@Andy, read the latest messages in the project-alpha Slack channel and summarize them in my local CLAUDE.md file."
- "@Andy, create a scheduled task to check my Gmail for urgent emails every day at 9 AM and forward them to my Discord server."
- "@Andy, debug why my current Telegram channel isn't triggering responses and show me the last 5 logs from the container."
Tips & Limitations
To maximize the utility of NanoClaw, organize your projects into separate folders so that CLAUDE.md memory files remain relevant to specific contexts. Keep in mind that while the code is lightweight, the reliance on Docker means you should monitor local container resource usage if running complex agent tasks. Do not store sensitive credentials in your CLAUDE.md files or project history, as these are stored in plain text. Always ensure your environment variables are secured and never committed to version control.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-adisinghstudent-nanoclaw-ai-assistant": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, external-api, code-execution
Related Skills
Oh My Openagent Omo
Skill by adisinghstudent
Planning With Files Manus Workflow
Skill by adisinghstudent
mirofish-offline-simulation
Fully local multi-agent swarm intelligence simulation engine using Neo4j + Ollama for public opinion, market sentiment, and social dynamics prediction.
ghostling-libghostty-terminal
Build minimal terminal emulators using the libghostty-vt C API with Raylib for windowing and rendering
Obra Superpowers Agentic Workflow
Skill by adisinghstudent