Sold by: CoreNova Intelligence Limited
Deployed on AWS
This product has charges associated with it for CoreNova hardening, AI stack packaging, maintenance, and seller support. Open WebUI + Ollama + vLLM Private AI Sandbox AMI packages Open WebUI, Ollama, vLLM, CUDA tooling, and HTTPS access for private LLM inference in your AWS account.
Overview
This is a repackaged open source software product wherein additional charges apply for CoreNova hardening, maintenance, validation notes, and seller support.
Open WebUI + Ollama + vLLM Private AI Sandbox AMI is a private AI sandbox AMI for running local LLM workflows inside your AWS account. It packages a hardened Ubuntu base with Open WebUI, Ollama, vLLM, Docker, NVIDIA runtime integration, and an HTTPS front end so teams can launch an isolated AI workspace faster.
Included AI stack
- Open WebUI for browser-based chat, RAG workflows, and administration.
- Ollama for local GGUF model serving; models are bring-your-own-model and are not bundled.
- vLLM as an optional high-throughput OpenAI-compatible inference server.
- Docker and NVIDIA container runtime integration for GPU instances.
- HTTPS access through Nginx, with self-signed TLS on first boot that buyers can replace with their own certificate.
First access
After launch, allow 5 to 10 minutes for initialization. Open https://YOUR_PUBLIC_IP/ and sign in with the seeded administrator account. Public signup is disabled by default. Change the administrator password after first login.
Security and privacy
- Prompts, uploaded documents, embeddings, and model files remain in the buyer's AWS account.
- Ollama and vLLM bind locally by default rather than exposing inference APIs directly to the internet.
- SSH hardening, firewall controls, fail2ban, auditd, and unattended security updates are included where supported.
- Optional secondary gp3 storage can be mounted at /mnt/models for model weights.
Best for
- Private AI demos and proof-of-concept deployments.
- Teams testing local inference before building a larger platform.
- Internal chat and RAG experiments where data should stay inside a VPC.
Related CoreNova listings
- Ubuntu 22.04 LTS Hardened GPU AMI CUDA Ready: https://aws.amazon.com/marketplace/pp/prodview-s3rsuk6sunlwq
- Ubuntu 22.04 LTS Hardened AMI: https://aws.amazon.com/marketplace/pp/prodview-u66ma5qrdkvtw
- CoreNovaLabs Cloud Forge Hardened App Runtime: https://aws.amazon.com/marketplace/pp/prodview-6hwhb4xi6kk4y
- Full CoreNova catalog: https://aws.amazon.com/marketplace/seller-profile?id=seller-kbf3ztbtbdc5o
Support
Email: support@corenovacloud.com Web: https://www.corenovacloud.com/
Include AWS Region, AMI ID, EC2 Instance ID, GPU instance type, browser error details, and steps to reproduce when opening a support request.
Highlights
- Private AI sandbox with Open WebUI, Ollama, vLLM, CUDA runtime integration, and HTTPS access.
- Designed for local LLM inference inside the buyer's AWS account with signup disabled by default.
- Hardened Ubuntu baseline with firewall controls, audit logging, fail2ban, and seller support.
Details
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 22.04 LTS
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
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 |
|---|---|
g6.xlarge Recommended | $0.08 |
p5.48xlarge | $0.08 |
g4dn.xlarge | $0.08 |
g5.12xlarge | $0.08 |
g5.xlarge | $0.08 |
g6.48xlarge | $0.08 |
g6.12xlarge | $0.08 |
Dimensions summary
You pay by the hour based on the GPU instance type you run. The seven dimensions map to specific EC2 GPU instances, not to software feature tiers. The g4dn, g5, and g6 families cover single-GPU options like g4dn.xlarge, g5.xlarge, and g6.xlarge, plus multi-GPU sizes like g5.12xlarge, g6.12xlarge, and g6.48xlarge. The p5.48xlarge serves larger GPU workloads. Your software cost scales with the size and count of GPUs in the instance you choose. AWS infrastructure charges for EC2, GPU, storage, and data transfer apply separately.
Top-of-mind questions for buyers
The software fee meters only running instance time. A fully stopped instance stops accruing the hourly software charge. Stopped instances may still incur separate AWS storage fees for the attached EBS volume. Those AWS infrastructure charges are billed by AWS, not part of the software fee.
Each dimension maps to one specific EC2 GPU instance type, billed per running hour. The software fee covers the pre-built sandbox image with Open WebUI, Ollama, and optional vLLM. EC2 compute, GPU, EBS storage, NAT Gateway, public IPv4, and data transfer are separate AWS charges.
Two charges apply at the same time on one invoice. The software fee is set by the instance type you pick, so larger or multi-GPU sizes carry a higher hourly software rate. Separately, AWS bills the underlying EC2 GPU compute. Both scale upward as you choose bigger instances.
www.corenovacloud.com
Helpful?
Vendor refund policy
30-day refund on AWS Marketplace software fees for this product. Email support@corenovacloud.com with your AWS account ID and purchase date. Software fees only; EC2 charges are not refundable by the seller. We reply within 5 business days. Free trial: no software charges during the trial.
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
Open WebUI + Ollama + vLLM Private AI Sandbox AMI
Version: v20260825
This release rebuilds the AMI with the standardized CoreNova builder-ami pipeline.
Stack:
- Ubuntu 22.04 LTS with latest upstream security updates at build time.
- SSH key-only access, root login disabled, auditd, rsyslog, chrony.
- UFW firewall baseline: SSH and HTTPS allowed; AI engine ports bound to localhost only.
- NVIDIA driver (LTS branch, currently 550) and CUDA 12.4 toolkit; DKMS modules load on GPU instance launch.
- Docker Engine with the NVIDIA container toolkit and GPU runtime preconfigured.
- Open WebUI and Ollama start automatically on first boot via Docker Compose; optional vLLM profile included.
- nginx TLS endpoint (self-signed certificate; buyers can replace /opt/corenova/ai/certs).
- Amazon CloudWatch Agent installed and enabled (requires an instance profile with CloudWatch Logs permissions).
- First-boot bootstrap seeds the Open WebUI admin account (admin@local.host , password = EC2 Instance ID).
- Optional models EBS volume is mounted at /mnt/models on first boot.
- Cloud-init cleaned before image capture.
- Marketplace checks require unencrypted EBS snapshots and no existing product codes.
Architecture: x86_64 Storage layout: ext4 Filesystem: ext4 Source AMI: ami-06e78a71af43ef21a (us-east-1) AMI: ami-0475b08ef7dc97427 (us-east-1)
Security note: The AMI contains no hardcoded passwords, private keys, AWS credentials, or model artifacts. The admin password is derived from the buyer's own EC2 Instance ID at first boot.
Additional details
Usage instructions
Overview
Open WebUI + Ollama + vLLM Private AI Sandbox AMI - security-hardened AI inference AMI for Ubuntu 22.04 LTS (x86_64) built by CoreNova Intelligence Limited. Open WebUI and Ollama start automatically on first boot via Docker Compose behind an nginx TLS endpoint; an optional vLLM profile is included.
Recommended instance type: g6.xlarge. AMI: ami-0475b08ef7dc97427 (us-east-1).
Launch checklist
- Subscribe in AWS Marketplace, then launch in us-east-1.
- Instance type: g6.xlarge, g5.xlarge, g4dn.xlarge, or another NVIDIA GPU instance type.
- Key pair: select your EC2 SSH key. Password login is disabled.
- Security group: allow inbound TCP 22 (admin) and TCP 443 (Open WebUI) from trusted ranges only.
- Optional: attach an extra EBS volume for model storage; it is mounted at /mnt/models on first boot.
- Optional: attach an IAM instance profile with CloudWatch Logs permissions to enable the preinstalled CloudWatch Agent.
First connection
ssh -i your-key.pem ubuntu@YOUR_PUBLIC_IP
First login to Open WebUI
Browse to https://YOUR_PUBLIC_IP (self-signed certificate; replace the files under /opt/corenova/ai/certs with your own). User: admin@local.host Password: your EC2 Instance ID.
Post-launch verification
nvidia-smi systemctl is-active auditd chrony rsyslog sudo systemctl is-active ufw sudo systemctl is-active docker sudo docker ps Expected: containers corenova-ollama and corenova-open-webui running (images download on first boot).
Sensitive data and credentials
The AMI does not include hardcoded passwords, private keys, AWS credentials, or model artifacts. The Open WebUI admin password is derived from the buyer's own EC2 Instance ID at first boot. AI engine ports (8080, 11434, 8000) are bound to localhost and denied by UFW; only the nginx HTTPS endpoint is reachable.
Encryption
The Marketplace source AMI uses unencrypted EBS snapshots as required for AWS Marketplace AMI ingestion. Buyers can launch or copy the AMI with encrypted EBS volumes according to their own AWS account policy.
Support
Email: support@corenovacloud.com Web: https://www.corenovacloud.com/
Include AWS Region, AMI ID, EC2 Instance ID, instance type, and steps to reproduce.
Resources
Vendor resources
Support
Vendor support
Email: support@corenovacloud.com
Web: https://www.corenovacloud.com/
CoreNova supports launch, SSH access, baseline service checks, Marketplace AMI metadata, and documented hardening behavior. Include AWS Region, AMI ID, EC2 Instance ID, instance type, and steps to reproduce.
Refund: 30-day refund on Marketplace software fees for verified technical issues. AWS infrastructure charges are billed by AWS and are not refundable by the seller.
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
This product has charges associated with it for seller support. This image comes with a prebuilt Ubuntu 26.04 AMI for private local LLM experimentation on EC2 with Ollama, Open WebUI, and a small preloaded validation model.
This is a repackaged open source software product wherein additional charges apply for hardening, security configuration, and setup support.
vLLM is a high-throughput OpenAI-compatible inference server for open-source LLMs (Python + PyTorch CPU build), bundled with Open WebUI as a browser chat front end. This Lynxroute build is secured and ready out of the box: a random 32-byte API key generated at first boot, Bearer-token auth enforced on every /v1 request, vLLM and Open WebUI bound to loopback behind Nginx TLS, a default tiny model (facebook/opt-125m) preloaded so the API and chat work immediately, UFW firewall pre-configured, and a CIS Level 1 hardened Ubuntu 24.04 LTS base.
vLLM is Apache-2.0 licensed; Open WebUI uses a source-available license (see Long Description for details).
Deploy Open WebUI instantly with a preconfigured AMI for self hosted AI chat, LLM interaction, and collaborative AI workflows. This platform provides a modern web interface for large language models with secure access, customizable deployment, and scalable infrastructure for teams and developers.
This is a repackaged open source software product wherein additional charges apply for hardening, security configuration, and setup support.
Ollama + Open WebUI is a complete private AI stack - run Llama, Mistral, Gemma, and 100+ LLMs locally with a ChatGPT-like interface. No OpenAI subscription, no data leaving your VPC. Authentication enabled, Nginx TLS proxy, Ollama API localhost-only, and CIS Level 1 hardened Ubuntu 24.04 LTS base. Built and maintained by Lynxroute.
Models are not pre-loaded - pull via Web UI or CLI after launch. For GPU inference use g4dn.xlarge or g5.xlarge.
Ollama is MIT-licensed; Open WebUI uses a source-available license (see Long Description for details).
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.