Overview
Paperclip AI is an agent orchestration platform that lets you deploy and manage AI coding agents from a single web interface.
This AMI is fully pre-configured on Ubuntu 24.04 LTS. Launch the instance, connect via SSH tunnel, and the onboarding wizard opens automatically in your browser at localhost:3100.
Pre-installed AI runtimes:
- Claude Code (Anthropic) - run claude to sync your account
- Codex (OpenAI) - run codex to sync your account
- OpenClaw - supports any LLM provider
- OpenCode - lightweight coding agent
Pre-installed infrastructure:
- Docker Engine with Compose and Buildx
- Google Chrome and Playwright for browser automation
- noVNC for visual browser access (port 6080)
- Caddy web server for automatic HTTPS with custom domains
- Tailscale for private networking and secure remote access
- Developer tools: GitHub CLI, jq, yq, ripgrep, fd-find, ffmpeg, tmux, htop
Getting started:
- Launch this AMI (t3.small or larger, 2GB+ RAM required)
- SSH with tunnel: ssh -L 3100:127.0.0.1:3100 ubuntu@your-instance-ip
- Open http://localhost:3100 in your browser
- Follow the onboarding wizard
Security: Paperclip runs on localhost only. Use SSH tunneling for access, or configure Caddy with your domain for HTTPS. Never expose port 3100 directly.
Minimum: 2GB RAM (t3.small). Recommended: 4GB+ RAM for running multiple agents.
Highlights
- Zero-config launch - onboarding starts on boot, just SSH tunnel in and open your browser
- 4 AI runtimes pre-installed - Claude Code, Codex, OpenCode, and OpenClaw ready to go
- Full dev stack - Docker, Playwright, Caddy auto-HTTPS, Tailscale VPN, and browser automation included
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Cost/hour |
|---|---|
t3a.medium Recommended | $0.03 |
m7i-flex.xlarge | $0.05 |
m8i.large | $0.04 |
t2.large | $0.04 |
m7i.4xlarge | $0.05 |
m8i-flex.xlarge | $0.05 |
t3a.2xlarge | $0.05 |
m5.xlarge | $0.05 |
m7i-flex.2xlarge | $0.05 |
t3a.xlarge | $0.05 |
Vendor refund policy
Standard AWS Refund policy
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Refresh release: Paperclip AI on Ubuntu 24.04 with current security updates, Node.js 22.22.2, pnpm, AWS CLI v2, GitHub CLI, jq, yq, tmux, and refreshed Paperclip source build. Pre-installed agent CLIs include OpenClaw, Claude Code, and Codex. Includes systemd user service and first-login setup guidance.
Additional details
Usage instructions
Getting started:
- Launch this AMI. Recommended instance: t3a.medium or larger.
- SSH into the instance: ssh ubuntu@<instance-ip>
- Configure Paperclip: cd ~/paperclip cp .env.example .env nano .env
- Add your AI provider API keys.
- Start Paperclip: systemctl --user enable --now paperclip
- Access the dashboard. Recommended secure access via SSH tunnel: ssh -L 3100:127.0.0.1:3100 ubuntu@<instance-ip> then open http://localhost:3100
Pre-installed agent CLIs:
- openclaw
- claude
- codex
Service commands:
- systemctl --user status paperclip
- systemctl --user restart paperclip
- journalctl --user -u paperclip -f
Ports: 22 (SSH). Only expose port 3100 if you intentionally want direct dashboard access; SSH tunnel or HTTPS reverse proxy is recommended.
Support
Vendor support
Community support via GitHub. For AMI-specific issues, contact the publisher through AWS Marketplace.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.