HowToDeploy Team
Lead Engineer @ howtodeploy

Tinyclaw is a multi-agent, multi-team AI assistant framework. Unlike single-agent setups, Tinyclaw lets you run parallel agent teams that coordinate through a shared SQLite task queue. It comes with TinyOffice — a built-in web dashboard for managing your agents — plus Discord, Telegram, and WhatsApp integrations.
If you need more than a single chatbot — think coordinated research, content pipelines, or parallel task execution — Tinyclaw is built for that.
Before you start, you'll need:
Go to Settings → Cloud Providers and paste your API key.
Tip: Tinyclaw's multi-agent teams benefit from a bit more headroom. The default 2GB RAM server handles most workloads, but you can scale up in Advanced Settings if you're running many agents in parallel.
Head to the Dashboard and find Tinyclaw in the AI Agents section. Click the card to open the deploy form.
Fill in two fields:
Server size, region, and dependencies are pre-configured.
Expand Advanced Settings to configure:
agents.example.com)If you add a custom domain, we'll show you the server IP after deployment. Point an A record to it, click Verify DNS, and Caddy will automatically issue an SSL certificate.
Once deployment completes, click the URL to open the TinyOffice dashboard. Sign in with the password you set, and you'll see:
From the dashboard, you can create new agents, assign them to teams, and start building multi-agent workflows.
Every Tinyclaw deployment includes:
You pay your cloud provider directly for the server (typically $6-12/month). HowToDeploy charges a small monthly management fee for monitoring and support.
Start with a 7-day free trial — no credit card required.
Ready to build your AI agent team? Deploy Tinyclaw 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.