Pre-installed and security-hardened OpenClaw AI agent AMI. Launch an EC2 instance, add your credentials, and start using your agent. Ready to configure out of the box.
OpenClaw is an AI agent framework that turns an EC2 instance into a personal AI assistant. Connect it to the channels your users are already on and the AI providers you prefer. This AMI gives you a hardened, production-ready foundation. Add your credentials, configure your channels, and your agent is live. Your data stays on your instance, your keys stay in your account, and you control the infrastructure.
Channels: Telegram, Slack, Discord, WhatsApp, web, and more. Connect one or many. OpenClaw handles routing, conversation state, and memory across all of them.
AI providers: OpenAI, Anthropic, AWS Bedrock, Google Vertex AI, OpenRouter, and more. Bring your own keys, no vendor lock-in, no per-message fees from us.
What's pre-installed:
Ubuntu 24.04 LTS (Canonical official base)
Node.js v22 (LTS) via NodeSource
OpenClaw AI agent framework
4 GB swap file (prevents OOM on smaller instances)
Complete directory structure ready for configuration
Security hardening included:
UFW firewall: default deny inbound, SSH (22) and gateway port (18789) allowed
Fail2ban: bans IPs after 5 failed SSH attempts (1-hour ban)
SSH hardened: key-only authentication, no password login, no X11, max 3 auth tries
Kernel hardening: ICMP redirects disabled, IP forwarding disabled
Unattended upgrades: daily automatic security patches (no auto-reboot)
Log rotation: daily rotation with 7-day retention for OpenClaw logs
Getting started after launch:
SSH in as the ubuntu user: ssh -i your-key.pem ubuntu@
Run: openclaw onboard
Follow the onboard wizard to configure your AI provider, channels, and agent settings
Ready in minutes: SSH in, run "openclaw onboard", and follow the wizard. OpenClaw, Node.js v22, swap, firewall, and log rotation are all pre-configured. No manual config files needed, the onboard wizard walks you through AI provider, channels, and agent setup.
Security-hardened from the start: UFW firewall with default-deny policy, fail2ban SSH brute-force protection, key-only SSH authentication, kernel-level network hardening. No additional configuration needed. Hardening is baked into the AMI and active on first boot.
Works with your stack: connect to OpenAI, Anthropic, AWS Bedrock, Google Vertex AI, OpenRouter, or any compatible provider. Reach users on Telegram, Slack, Discord, WhatsApp, and more. Bring your own keys, no vendor lock-in, no per-message fees from us.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Try this product free for 5 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
If you are an AWS Free Tier customer with a free plan, you are eligible to subscribe to this offer. You can use free credits to cover the cost of eligible AWS infrastructure. See AWS Free Tier for more details. If you created an AWS account before July 15th, 2025, and qualify for the Legacy AWS Free Tier, Amazon EC2 charges for Micro instances are free for up to 750 hours per month. See Legacy AWS Free Tier for more details.
You pay for this product by the hour, and the hourly software rate depends on the EC2 instance type you launch. Each dimension matches one Amazon EC2 instance type, from small general-purpose sizes up to compute-, memory-, storage-, and GPU-optimized families. Larger or specialized instances carry higher hourly software rates. You choose the instance that fits your workload. Billing starts when the instance runs and stops when you stop it. AWS charges EC2, storage, and data transfer separately, and your AI provider bills its own usage.
Top-of-mind questions for buyers
What does one hour of the software charge cover, and what spec do I get?
Each dimension is one Amazon EC2 instance type. The hourly software rate buys the OpenClaw image running on that instance size. The recommended starting point is a t3.medium with 2 vCPU and 4 GB RAM, using the default 20 GB root volume. Larger instances give more compute, memory, storage, or GPU.
Am I charged the software rate when the instance is stopped?
No. The hourly software charge applies only while the instance runs. Stopping the instance stops that charge. To stop paying for the disk too, terminate the instance. AWS still bills storage and other resources while an instance is stopped but not terminated.
What costs sit outside the hourly software rate shown in the table?
AWS bills EC2 compute, EBS storage, and data transfer separately from the software rate. Your AI provider bills its own usage against the keys you supply. Messaging channel platforms may also charge for their services. You add all these credentials and accounts yourself after launch.
docs.softwaresushi.com+1
Helpful?
Vendor refund policy
We offer a full refund of software charges for the first 48 hours billing starts if the product does not perform as described. To request a refund, email info@softwaresushi.com with your EC2 instance ID and a description of the issue. AWS infrastructure costs (EC2, EBS, data transfer) are billed by AWS and are not eligible for refund by us.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
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
Updated OpenClaw to v2026.10.6.
OpenClaw AI agent framework updated from v2026.9.9 to v2026.10.6
All system packages updated to latest security patches (2026-10-24)
Additional details
Usage instructions
Connect via SSH using your EC2 key pair on port 22. Access the OpenClaw agent dashboard on port 18789.
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.
OpenClaw AI Agent Platform on Ubuntu 24.04 LTS is a preconfigured, production-ready deployment for building, managing, and running AI agents on AWS. Includes a web-based dashboard, automated startup, workspace management, and support for OpenAI and other compatible AI providers.
This is a repackaged software product with additional charges for support, maintenance, and pre-configuration by Tidal Media Inc. AI Workstation on OpenClaw Agent on Ubuntu 24.04 LTS is a pre-configured VM designed for scalable AI agent orchestration, offering a secure, optimized, and ready-to-deploy environment with additional support and maintenance by Tidal Media Inc.
Ready-to-use OpenClaw stack for executing automation workflows, system tasks, and AI-driven operations with flexible CPU/GPU deployment and support for both local and API-based models.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.