Overview

Product video
AI Search with Citations combines live web search with a language model: it searches the public web through SearxNG, reads the results and writes an answer with links to its sources. It is for researchers, analysts and developers who want private AI search with cited sources in their own AWS account, using a model they choose.
What you get: Vane 1.12.2 with a pinned SearxNG, an API on port 3000 reached through Session Manager port forwarding, and an access file created on first boot. No model, GPU or model key is included; after launch you configure an OpenAI-compatible chat and embedding endpoint in a mode 0600 file. The walkthrough checks automatic startup and confirms that unauthenticated calls are rejected.
Getting started: launch t3.large (8 GiB RAM) with a 40 GiB encrypted gp3 root volume, IMDSv2, an instance profile for Session Manager and outbound HTTPS. Do not open an inbound application port. Run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh, then forward port 3000 and configure your model endpoint with the guide.
Good to know: search engines may rate-limit results, answer quality depends on your model and this image does not provide anonymity. Open each cited page before relying on a fact.
This is a repackaged open source software product wherein additional charges apply for independent AWS packaging, validation, maintenance and setup documentation. ItzCrazyKns publishes Vane under the MIT license and SearxNG is included under AGPL-3.0-or-later, so the image license is MIT AND AGPL-3.0-or-later. Software Sushi claims no Vane, SearxNG or AWS endorsement. The software fee is USD 0.03 per running t3.large instance-hour; EC2, EBS, data transfer and model-provider charges are separate.
Highlights
- Answers to your questions with citations to the web pages used, from live web search.
- Bring your own OpenAI-compatible chat and embedding models; no model or key is bundled.
- Private API on port 3000 reached through Session Manager, with a per-instance access file.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Free trial
Dimension | Cost/hour |
|---|---|
t3.large Recommended | $0.03 |
Dimensions summary
Top-of-mind questions for buyers
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) and any third-party service charges are not eligible for refund by us.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
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
Vane 1.12.2 with pinned SearxNG on Ubuntu 24.04. Rebuilt the host Brotli packages and application payload for AWS Marketplace CVE-2026-111497. The installed demo passed a fresh EC2 smoke test. Configure your own OpenAI-compatible endpoint after launch; no model key is included. Broader raw scan findings remain in private evidence; full Software Sushi security qualification is not claimed.
Additional details
Usage instructions
- Launch t3.large with at least 8 GiB RAM, an encrypted gp3 root volume of at least 40 GiB, IMDSv2, an instance profile with AmazonSSMManagedInstanceCore, and outbound HTTPS. No inbound application ports are needed.
- Connect with AWS Systems Manager Session Manager and wait for cloud-init to finish.
- sudo -iu ubuntu bash /opt/sushi/docs/demo.sh
- On your computer, forward port 3000 with aws ssm start-session --document-name AWS-StartPortForwardingSession and leave that session open.
- Set your OpenAI-compatible chat and embedding endpoint in a mode 0600 file, then import it with the guide. Never put the key in user data or logs. Guide: /opt/sushi/docs/README.md on the instance (less /opt/sushi/docs/README.md).
Resources
Vendor resources
Support
Vendor support
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 support from the Vane or SearxNG authors.
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.