← Back to the registry
Agent passport

Paperclip AI - Agent Orchestration Platform

Breaking IT · HR & Talent

No attestation published

Certification per AWS Marketplace.

Provenance reach4 of 12 layers traced

Evidence tier Source Confirmed · 4 captures on record

User ratingNot rated0 reviews on the listing
Runs onUnknownVirtual machine
ProvenanceUnknown44% of the provenance layers this product can disclose
Evidence riskHighSign in to see the basis for this band.

What the publisher says

As described on AWS Marketplace.

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.

Show the rest of the publisher’s description (19 more lines)

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

Highlighted by the publisher on AWS Marketplace.

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

Agent build and provenance

See the full provenance

The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.

Create a free account

Plans and pricing as listed

47 listed
t3a.medium
  • Hrs
$0.03
m7i-flex.xlarge
  • Hrs
$0.05
m8i.large
  • Hrs
$0.04
t2.large
  • Hrs
$0.04
m7i.4xlarge
  • Hrs
$0.05
m8i-flex.xlarge
  • Hrs
$0.05
t3a.2xlarge
  • Hrs
$0.05
m5.xlarge
  • Hrs
$0.05
m7i-flex.2xlarge
  • Hrs
$0.05
t3a.xlarge
  • Hrs
$0.05
t3a.large
  • Hrs
$0.04
m5.2xlarge
  • Hrs
$0.05
and 35 more plans on the listing

Refund terms

As stated by the publisher on AWS Marketplace.

Standard AWS Refund policy

Sources

Marketplace listingaws.amazon.com ↗Source
App certificationaws.amazon.com ↗Source
StandardEulaStandardEula ↗Source

Linked repositories

RepositoriesUnknownUnknown

Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.

Pricing
Paid
47 plans listed
Delivery
Virtual machine
Community support via GitHub. For AMI-specific issues, contact the publisher through AWS Marketplace.
Open the source listing ↗

Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.