HowToDeploy Team
Lead Engineer @ howtodeploy

Nanoclaw is a lightweight Claude agent that runs as a single process — container-isolated, with built-in integrations for WhatsApp, Telegram, Discord, Slack, and Signal. It also supports scheduled tasks and agent swarms, making it one of the most capable yet minimal AI agent frameworks available.
Setting it up manually means provisioning a server, cloning the repo, configuring API keys, and managing the process. With HowToDeploy, you can skip all of that and have Nanoclaw running in minutes.
Before you start, you'll need:
Go to Settings → Cloud Providers and paste your API key. Any supported provider works.
Tip: Nanoclaw needs just 1GB RAM. You can run it on the cheapest tier of any provider — typically $4-6/month.
Head to the Dashboard and find Nanoclaw in the AI Agents section. Click the card to open the deploy form.
You only need one field:
Server size, region, and everything else are pre-configured with sensible defaults.
Expand Advanced Settings to connect your preferred channels:
You can add WhatsApp and Signal later through the server config file. No need to set everything up before deploying.
Once deployment completes, your Nanoclaw agent is live. If you connected a messaging channel, send it a message and it'll respond instantly.
Want to set up scheduled tasks or agent swarms? SSH into your server and edit the Nanoclaw config file — full documentation is in the GitHub repo.
Every Nanoclaw deployment includes:
You pay your cloud provider directly for the server (as low as $4-6/month for the smallest tier). HowToDeploy charges a small monthly management fee for monitoring and support.
Start with a 7-day free trial — no credit card required.
Ready to run your own Claude agent? Deploy Nanoclaw now →

Step-by-step guide to deploying NemoClaw, NVIDIA's agentic AI framework with GPU-accelerated inference, multi-modal reasoning, and retrieval-augmented generation.

A step-by-step guide to deploying Perplexica, an open-source AI-powered answering engine that combines web search with LLMs to deliver accurate, cited answers while keeping your searches private.

A step-by-step guide to deploying Agent Orchestrator, an agentic orchestrator that spawns parallel coding agents in isolated git worktrees and autonomously handles CI fixes, merge conflicts, and code reviews.