Stop Hiring, Start Orchestrating: Running an AI Agent Company with Paperclip on DigitalOcean

The idea of a one-person company isn't new. What's new though is the idea of a one-person company where the person isn't doing most of the actual work. AI agents are. You set the direction, define the roles and budgets, and the agents handle the execution. Traditional human tasks - writing, researching, analysing, reporting - are executed autonomously by agents like OpenClaw, Claude, Hermes, and others. And tools like Paperclip are making it easy to get started.

What is Paperclip?

Paperclip describes itself as "the human control plane for AI labor." You define a company - give it a mission, a budget, a set of agent personas - and Paperclip runs it. Agents get heartbeats on a schedule, pick up open tasks, call their assigned large language model (LLM), and post results back as issue comments. It's effectively a project management tool for teams, where every team member is an AI agent.

Paperclip started as an experiment in running fully autonomous agentic operations at scale i.e. "open-source orchestration for zero-human companies". It's evolving into something broader: a full agent orchestration platform for building companies that run on autonomous agents rather than headcount. The pivot is still in motion, but the core idea is already compelling enough to deploy and explore.

The unit of organisation is a company. Inside a company you have agents (personas with roles, adapters, and heartbeat schedules), projects, and issues (tasks). An agent wakes up when its heartbeat fires, looks at what's assigned to it, does the work, and goes back to sleep. The idea of a pre-built company is quite powerful, and the ecosystem is slowly growing around companies.sh - pre-built company definitions you can import into Paperclip with a single command. Imagine an external penetration testing team, a content agency, or a software development shop, fully staffed with AI agents, importable in seconds.

To make it concrete, here's what a lean content agency could looks like:

Agent	Role	Heartbeat
Editor in Chief	Reviews briefs, assigns stories, sets editorial direction	Daily
Research Analyst	Monitors sources, surfaces stories, drafts research notes	Every 6h
Writer	Drafts posts from research notes and briefs	On demand
SEO Analyst	Reviews drafts for keyword coverage and structure	On demand
Publisher	Formats and schedules final output	Daily

Every agent is backed by an LLM of your choice. The Editor in Chief might run on Claude for judgment-heavy decisions; the Research Analyst on Gemini Flash for speed and cost. Each agent has its own adapter, its own system prompt, its own task queue. Paperclip keeps them coordinated.

Deploying Paperclip on DigitalOcean

This section covers the deployment of Paperclip on a DigitalOcean droplet with Docker, embedded PostgreSQL, and Caddy for automatic HTTPS. A single script handles everything from provisioning to first login. If you are new to DigitalOcean, you can sign up with this link for $200 in free credits.

Prerequisites: doctl installed and authenticated, an SSH key uploaded to your DigitalOcean account, a valid API key from at least one LLM provider, and a domain or subdomain pointed at your droplet.

First, run the following commands at your terminal post authentication.

git clone https://github.com/alphasecio/paperclip.git
cd paperclip/digitalocean
chmod +x deploy.sh
./deploy.sh

The script prompts for three things - domain name, LLM provider, API key - then takes over. It creates the droplet, waits for SSH, installs Docker, builds the image, starts Paperclip and Caddy, and polls until the admin invite URL is ready. The whole process takes around five minutes.

A custom entrypoint.sh wraps the official Paperclip docker image. On first boot, it writes config.json from environment variables, then hands off to pnpm paperclipai run. No interactive setup, no manual config editing.

Paperclip uses embedded PostgreSQL by default - no separate database service needed. Set DATABASE_URL to switch to an external Postgres instance; the entrypoint detects it and adjusts the config automatically. The script provisions a 2-vCPU, 4GB RAM Droplet running Ubuntu 24.04 — enough headroom for Paperclip, its embedded database, and a handful of active agents.

Caddy runs alongside as a Docker service and handles Let's Encrypt certificate provisioning automatically. It only activates when CADDY_DOMAIN is set; skip the domain prompt and Paperclip is accessible directly on port 3100 instead.

Post-Deployment Setup and Connection

When the script finishes, it prints the admin invite URL to the terminal:

=========================================
  Paperclip deployed
=========================================
  URL:        https://paperclip.yourdomain.com
  Invite URL: https://paperclip.yourdomain.com/invite/pcp_bootstrap_...
=========================================

Open the invite URL, create your admin account through Paperclip's native setup screen, then lock down registration (recommended for single-user deployments):

ssh root@<your-droplet-ip> 'echo PAPERCLIP_AUTH_DISABLE_SIGN_UP=true >> /opt/paperclip/.env && cd /opt/paperclip && docker compose up -d'

A couple of adapters work out of the box with environment variables — no interactive login required.

Provider	Adapter in Paperclip	Environment Variable
Anthropic	claude_local	ANTHROPIC_API_KEY
OpenAI	opencode_local	OPENAI_API_KEY
Gemini	opencode_local	GEMINI_API_KEY

For Gemini, select opencode_local as the adapter and choose your model (e.g. gemini-2.5-flash) in the agent settings. The gemini_local adapter requires interactive OAuth and won't work headless.

All configuration lives in /opt/paperclip/.env on the droplet. Edit and run docker compose up -d to apply changes.

What's Next

The deployment covered here is just the start — Paperclip running cleanly, agents wired up, ready to receive tasks. The real interesting (and fun) part lies in what you build on top of it. The GitHub repo also includes a railway/ folder for a one-click deployment on Railway if you'd prefer a serverless option. I'm fascinated by the companies.sh concept, and I'm exploring a purpose-built agent company - a threat intelligence team that monitors security advisories, extracts IOCs and TTPs, and generates detection rules - as a follow up. If that sounds exciting, it'll be next.