Sold by: AppXen
Deployed on AWS
Self-hosted, multi-user AI chat powered by Amazon Bedrock, running in your own AWS account with auto-TLS and a hardened base.
Overview
A private, multi-user AI chat workspace that runs entirely in your own AWS account and talks to large language models through Amazon Bedrock. Production-hardened from first boot: automatic HTTPS, MongoDB persistence, full-text search, a firewall, and automatic security updates. Your conversations and data stay in your account - no per-seat fees and no third-party data sharing.
Inference runs on Amazon Bedrock using an IAM role you attach at launch (the included CloudFormation template sets this up), so there are no API keys to manage and no GPU to pay for - you are billed for Bedrock usage through your own AWS account. Requires Amazon Bedrock model access to be enabled in your account.
This is independent software packaged by AppXen and is not affiliated with or endorsed by the LibreChat project.
Highlights
- Multi-user AI chat with conversation history and full-text search, behind automatic TLS
- Amazon Bedrock models via an instance role - keyless, and no GPU required
- MongoDB persistence on a hardened Ubuntu 24.04 base
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04 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 |
|---|---|
t3.medium Recommended | $0.059 |
t3.large | $0.059 |
Dimensions summary
You pay an hourly software fee tied to the EC2 instance size you run. The two dimensions, t3.medium and t3.large, represent instance sizes you choose to host this self-hosted AI chat workspace. Pricing scales with the size you pick and the hours the instance runs. No GPU is required, since AI inference runs through Amazon Bedrock. You pay EC2 compute and Amazon Bedrock token usage separately through AWS. There are no per-user or per-seat charges, so cost does not change with the number of users.
Top-of-mind questions for buyers
Each dimension maps to the EC2 instance size that hosts the chat workspace. The vendor recommends t3.medium or larger, since no GPU is needed. Model inference runs through Amazon Bedrock, not the instance. You pick one size, and the software fee is billed per running hour on that instance.
The software fee meters running instance-hours. A stopped instance does not accrue the hourly software charge. Stopped instances may still incur AWS storage fees for attached volumes, billed separately by AWS. Amazon Bedrock token charges only apply when you actually generate responses.
Three charges appear separately. You pay the hourly software fee for your chosen instance size, the underlying EC2 compute cost, and Amazon Bedrock token usage. There are no per-seat charges, so total cost tracks instance hours and how many tokens your team actually generates.
appxen.ai
Helpful?
Vendor refund policy
Refunds are available on a case-by-case basis. To request a refund, email support@appxen.ai within 30 days of the charge; we typically respond within 1 business day.
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
Initial release. LibreChat on a hardened Ubuntu 24.04 base with automatic HTTPS, MongoDB, and keyless Amazon Bedrock via an instance role.
Additional details
Usage instructions
Attach an instance role with bedrock:InvokeModel at launch and enable Anthropic Claude model access in the Bedrock console (one-time, per region). Wait about 3 minutes for first boot, then browse to https://<public-ip>/ and create your account. See https://appxen.ai/appliances/librechat for the launch guide.
Support
Vendor support
Email support@appxen.ai for setup help and troubleshooting. Best-effort email support during business hours. Documentation and launch guide:
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
AppXen is managed MCP (Model Context Protocol) infrastructure for AI agents production-ready, pay-as-you-go, no ops required.
Connect AI models to your tools, data, and APIs through a fully managed MCP Gateway. Build multi-agent workflows in plain markdown. Add a knowledge layer with RAG Engine for grounded, context-aware responses. Bridge any existing REST API to MCP in minutes, no rebuilding required.
AppXen handles authentication, rate limiting, usage metering, and observability so you can focus on building agents, not infrastructure.
Integrations include: GitHub, Neon Postgres, Supabase, Zapier, AWS CloudWatch, and any REST API.
Deploy AI workflows that are composable, auditable, and production-hardened from day one.
By AppXen
Self-hosted n8n workflow automation, production-hardened with automatic HTTPS, PostgreSQL persistence, firewall, and automatic security updates. Own your automation data and execution end to end - no per-task fees, no execution caps.
By AppXen
Self-hosted Git service with repositories, issues, pull requests, and CI, production-hardened with auto-TLS, backups, and updates.
Self-hosted low-code platform to build internal tools, admin panels, and dashboards over your own databases and APIs, production-hardened with auto-TLS.
Self-hosted visual AI builder for chatbots, RAG, and agent workflows, powered by Amazon Bedrock and running in your own AWS account.
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.