This is a repackaged open source software product wherein additional charges apply for independent AMI packaging, maintenance and setup documentation. Run an authenticated LibreChat chat workspace with your own TLS MongoDB database and Amazon Bedrock Nova Lite. Includes guided owner setup, saved conversations and static artifact previews.
This is a repackaged open source software product wherein additional charges apply for independent AMI packaging, maintenance and setup documentation.
Software Sushi packages LibreChat 0.8.8 on Ubuntu 24.04 x86_64 with a browser chat interface, administrator-created accounts and saved conversations in your own external MongoDB application database. Configure the database and first owner after launch, then sign in through a Session Manager tunnel. Public registration is disabled.
The supplied configuration uses Amazon Bedrock Amazon Nova Lite (amazon.nova-lite-v1:0) in us-east-1 through your EC2 instance role. You supply database hosting, authenticated TLS connectivity and the required Bedrock access. No MongoDB server, search/RAG service, Redis or provider account is included.
This package uses static artifact previews. HTML, SVG, Markdown and Office previews display sanitized markup; React, JSX and TSX artifacts expose editable, copyable and downloadable source. Mermaid diagrams retain their native renderer. Sandpack and Nodebox interactive JavaScript preview execution, artifact scripts, remote resources and preview link navigation are unavailable. Downloads retain the source or original attachment.
Choose t3.large with 8 GiB RAM and at least a 40 GiB root volume. Access application port 3080 through Session Manager port forwarding from your workstation; no inbound application rule is needed. Software costs USD 0.03 per running instance-hour. EC2, EBS, data transfer, external MongoDB and Bedrock model usage are billed separately.
Includes post-launch configuration commands, owner provisioning, saved-chat verification and restart guidance. Software Sushi is an independent packager and claims no upstream or AWS endorsement. LibreChat is licensed under MIT. Bundled dependencies retain their own licenses and notices.
Highlights
Authenticated browser chat with first-owner provisioning and saved conversations in your customer-managed TLS MongoDB database.
Native Amazon Bedrock Nova Lite configuration in us-east-1 using your EC2 instance role; no static AWS keys are baked.
Static sanitized artifact previews, source editing and downloads, with Session Manager access and documented backup and recovery paths.
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.
This listing uses one usage-based dimension billed hourly on a t3.large EC2 instance. You pay the per-hour software charge for each hour the instance runs, so your cost scales with runtime. There are no tiers or quantity commitments to choose between. The chat workspace runs in your own AWS account, and you connect your own TLS MongoDB and model provider after launch. AWS infrastructure like EC2, storage, and data transfer bills separately from this software charge, and any third-party model or database services carry their own costs.
Top-of-mind questions for buyers
What compute does the t3.large hourly rate cover, and what else do I pay for separately?
The software charge covers the LibreChat workspace running on a t3.large EC2 instance in your account. AWS bills EC2 compute, EBS storage, and data transfer separately. The external MongoDB and your chosen model provider carry their own charges, since no database server is bundled.
Am I charged the software rate when the instance is stopped?
The hourly software charge applies for each hour the t3.large instance runs. A fully stopped instance does not accrue the software charge. Stopped instances may still incur AWS storage fees for attached volumes, which AWS bills separately from this software charge.
Does the hourly rate include a MongoDB database or any model-provider credits?
No. This listing packages the chat workspace only, with no database server included. You bring your own TLS MongoDB and connect your own model provider after launch. Those services run under your own accounts and bill their usage independently of the hourly software charge.
softwaresushi.com
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 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
LibreChat 0.8.8 on Ubuntu 24.04 with a customer-managed external MongoDB database, authenticated browser chat, native Bedrock Nova Lite configuration and static artifact previews. Includes first-owner setup, browser-led saved-chat verification and prior-result readback. Verified version: 0.1.1 (LibreChat 0.8.8). Source AMI: ami-00527f59df8666a00.
Additional details
Usage instructions
Launch t3.large with at least 40 GiB encrypted gp3 root storage, IMDSv2, outbound HTTPS and an EC2 role with Session Manager and the documented Bedrock Nova Lite permissions in us-east-1. EC2, EBS, data transfer, your database and model usage are separate charges.
Connect using Session Manager, wait for cloud-init, and follow the public guide to configure your own authenticated TLS MongoDB application database and first administrator. Keep credential input files private with mode 0600. No database server or search service is supplied.
Run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh. It creates a fresh challenge and exits 3 while waiting for the browser step; this is incomplete rather than a successful demo. Forward application port 3080 through Session Manager from your workstation; no inbound application rule is required.
Sign in normally in the actual browser UI, choose the configured Bedrock Nova Lite endpoint, send the displayed challenge once in a new non-temporary conversation and wait for generation to complete.
Software Sushi provides AMI packaging and setup guidance. Contact info@softwaresushi.com for installation questions. Support coverage requires a separate agreement; this offer does not include upstream project support.
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.
Ask a question and get an AI-written answer that cites the web pages it used. This Ubuntu 24.04 AMI runs Vane with a pinned SearxNG metasearch engine and calls the OpenAI-compatible chat and embedding models you configure, giving teams a private answer engine in their own AWS account.
General-purpose reranker with instruction following optimized for both latency and quality. Context length: 32K for queries & documents (8K for queries).
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.