Sold by: Lynxroute
Deployed on AWS
Free Trial
This is a repackaged open source software product wherein additional charges apply for hardening, security configuration, and setup support.
OpenHands is a self-hosted autonomous AI agent that writes code, runs commands and uses a browser inside isolated sandbox containers, controlled from a web IDE. It works with any LLM provider - operators bring their own key. This Lynxroute build is hardened and ready out of the box: HTTPS via Nginx with HTTP basic auth, sandbox runtime image baked in and SHA-pinned, agent container bound to loopback, on a CIS Level 1 hardened Ubuntu 24.04 LTS base.
MIT license - fully auditable, no vendor lock-in.
Overview
This is a repackaged open source software product wherein additional charges apply for hardening, security configuration, and setup support.
WHAT IS OPENHANDS
OpenHands (formerly OpenDevin) is an open-source autonomous AI software engineering agent. The agent runs in a sandbox container with full read-write access to a workspace, executes shell commands, edits files, and drives a headless browser - controlled from a web IDE that streams live agent events over WebSocket. It works with any LLM provider through a configurable backend: Anthropic Claude, OpenAI GPT, AWS Bedrock, Azure OpenAI, Google Vertex AI, Cohere, Mistral, Groq, DeepSeek, Ollama, vLLM, LiteLLM, and more. Operators choose the provider in the web UI's Settings menu and paste their API key - no provider keys are baked into the AMI. The agent's CodeAct loop combines reasoning, tool use, and shell execution to perform real software engineering tasks: implementing features, debugging, refactoring, running tests, browsing documentation, and more. MIT license, no vendor lock-in.
WHAT THIS AMI ADDS
Security hardening:
- HTTP basic auth (admin / EC2 Instance ID) gates the entire app via Nginx - without this layer the OpenHands web UI is openly callable
- OpenHands container bound to 127.0.0.1:3000 - reachable only through the Nginx reverse proxy with TLS
- Sandbox agent-server runtime image pre-pulled and pinned by SHA-256 digest - reproducible builds, first conversation does not block on a 3-5 GB Docker pull
- Both images (openhands main + agent-server runtime) pinned by sha256 in /etc/openhands/openhands.env
- Nginx reverse proxy with TLS, HTTP-to-HTTPS redirect, WebSocket support for live agent events, security headers, large-body and long-timeout tuning for agent tasks
- No provider API keys baked in - operator configures their LLM provider through the OpenHands UI Settings after first login
- UFW firewall pre-configured - only TCP 22, 80, 443 are exposed
- fail2ban, AppArmor
- CVE scan - every image is scanned for vulnerabilities before release
OS hardening (CIS Level 1):
- CIS Ubuntu 24.04 LTS Level 1 benchmark applied via ansible-lockdown
- auditd, SSH hardening, kernel hardening, IMDSv2 enforced
Compliance artifacts:
- SBOM - CycloneDX 1.6 at /etc/lynxroute/sbom.json
- CIS Conformance Report at /etc/lynxroute/cis-report.html
- CIS Tailored Profile at /usr/share/doc/lynxroute/CIS_TAILORED_PROFILE.md
ARCHITECTURE NOTES
OpenHands spawns a sandbox container per conversation via /var/run/docker.sock mounted into the OpenHands container. This is required by the upstream design and gives the agent root-equivalent access to the host docker daemon. The AMI is therefore intended for single-tenant use - do not expose it to untrusted users. State, settings, and conversation history persist at /opt/openhands/state across container restarts and instance reboots. The agent's working files persist at /opt/openhands/workspace - operators can attach an EBS volume there for a larger or independently managed workspace.
Highlights
- Security baked in: HTTPS via Nginx, HTTP basic auth gating the agent UI (admin / EC2 Instance ID), container bound to 127.0.0.1:3000, agent-server runtime image baked in and SHA-pinned.
- CIS Level 1 hardened Ubuntu 24.04 LTS: auditd, fail2ban, AppArmor, SSH key-only, IMDSv2 enforced. CVE-scanned before every release. SBOM (CycloneDX) and CIS Conformance Report included.
- One agent UI for any LLM provider: Anthropic, OpenAI, AWS Bedrock, Azure OpenAI, Google Vertex, Cohere, Mistral, Groq, DeepSeek, Ollama, vLLM, LiteLLM. Provider keys are configured through the OpenHands UI Settings - never baked into the image. MIT license - fully auditable, no vendor lock-in, ever.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
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.
Pricing
Free trial
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.
Dimension | Cost/hour |
|---|---|
t3.large Recommended | $0.05 |
m6i.large | $0.05 |
m6i.xlarge | $0.05 |
t3.medium | $0.05 |
Dimensions summary
You pay by the hour for the EC2 instance size you run this hardened image on. The four options map to different compute and memory sizes. The t3.medium and t3.large are burstable instances, while the m6i.large and m6i.xlarge are general-purpose instances with fixed performance. Larger sizes carry more vCPUs and memory, so your hourly rate rises with the capacity you select. You choose one instance type based on your workload. Billing runs through AWS Marketplace on usage, with no upfront commitment or fixed term.
Top-of-mind questions for buyers
The t3.medium and t3.large are burstable instances that accumulate CPU credits during low activity and spend them during spikes. The m6i.large and m6i.xlarge are general-purpose instances with steady, fixed CPU performance. Within each family, moving up a size adds vCPUs and memory, so choose based on your workload's compute needs.
Software charges meter running instance-hours. When you stop the instance, hourly software billing stops accruing. Underlying AWS storage fees for the attached volume may still apply while the instance is stopped, but those are separate from the software charge and billed by AWS.
All billing runs through AWS Marketplace on usage, with no upfront commitment or fixed term. The vendor does not process payment details and receives only aggregate usage data from the marketplace. The deployed image runs entirely in your own cloud account with no telemetry or call-home functionality.
lynxroute.com
Helpful?
Vendor refund policy
We do not offer refunds for this product. AWS infrastructure charges (EC2, EBS, data transfer) are billed separately by AWS and are not refundable by us.
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.
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
OpenHands 1.10.0
- Updated OpenHands to 1.10.0
- Sandbox runtime updated to the matching agent-server 1.33.0 build, pre-pulled into the image so the first conversation starts without a multi-gigabyte download
- Both container images are pinned by digest, so the image that ships is the image that runs
- Certbot pre-installed - enable HTTPS with one command: sudo certbot --nginx -d yourdomain.com
- Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base
Additional details
Usage instructions
- Launch instance (t3.medium minimum, t3.large recommended for production load)
- Open Security Group - allow TCP 443 from your IP
- SSH: ssh -i key.pem ubuntu@<PUBLIC_IP>
- Read credentials: sudo cat /root/openhands-credentials.txt
- Open https://<PUBLIC_IP>/ in your browser - accept the self-signed certificate warning
- Authenticate with HTTP Basic Auth: user "admin", password = EC2 Instance ID
- In the OpenHands UI click Settings -> LLM and configure your preferred provider (Anthropic, OpenAI, AWS Bedrock, Azure OpenAI, Google Vertex, Ollama, etc.) with your API key
- Start a new conversation - the agent will spawn a sandbox container and begin working
Admin password (HTTP Basic Auth) equals the EC2 Instance ID. Credentials are saved to /root/openhands-credentials.txt at first boot. Certbot is pre-installed - enable HTTPS with a CA-signed certificate in one command: sudo certbot --nginx -d your.domain.com
Each instance is single-tenant - the agent runs commands and edits files inside sandbox containers spawned via Docker; do not expose this AMI to untrusted users.
Resources
Vendor resources
Support
Vendor support
Visit us online: https://lynxroute.com
For OpenHands documentation: https://docs.openhands.dev For OpenHands upstream issues: https://github.com/OpenHands/OpenHands/issues For AWS infrastructure issues:
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.
Similar products
ChipAgents is an AI agent purpose-built for hardware engineering teams. Unlike general-purpose coding assistants, it natively understands SystemVerilog, Verilog, VHDL, UVM testbenches, EDA toolchains, waveforms, and industry protocols like AXI, AMBA, and PCIe. Deploy self-hosted in your AWS environment to accelerate RTL development, verification, and debugging while keeping your IP fully within your infrastructure.
Enterprise features include hierarchical configuration (global, team, and user-level), seat management and organization-level API key controls, sandboxed execution to isolate agent actions, and a Python SDK for workflow integration and automation.
Ona (formerly known as Gitpod) is a platform for AI-powered background agents that function as an AI software engineering workforce. The company enables organizations to run teams of AI software engineers in the cloud, autonomously and continuously, to execute software development tasks end-to-end, from task intake to pull request delivery. What Ona does: Ona orchestrates AI agents that operate in fully provisioned cloud development environments with access to tools, network, and scoped credentials. Users set the direction; Ona handles the execution.
Self-hosted environments for agentic software development.
Pre-configured Hermes Agent AI with browser automation, Docker, Tailscale, Caddy, and developer tools. SSH in, run hermes setup, start building with AI.
Customer reviews
No customer reviews yet
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.