OpenHands - Hardened Self-Hosted AI Software Engineering Agent
Lynxroute · Cybersecurity & IT
Certification per AWS Marketplace.
Evidence tier Source Confirmed · 3 captures on record
What the publisher says
As described on AWS Marketplace.
This is a repackaged software product wherein additional charges apply for hardening, security configuration, and support.
WHAT IS OPENHANDS
Show the rest of the publisher’s description (21 more lines)
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
Highlighted by the publisher on AWS Marketplace.
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 - unlike bare OpenHands AMIs that ship without TLS, with the sandbox runtime not pre-pulled, and with the UI exposed without auth.
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.
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.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment · as of 2026-08-29
Plans and pricing as listed
4 listed- Hrs
- Hrs
- Hrs
- Hrs
Refund terms
As stated by the publisher on AWS Marketplace.
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.
Sources
Publisher resources
1 linkLinked repositories
1 repoUnknown 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.
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.