Overview
This is a paid repackaged software product. NextChat is available under the MIT license; Software Sushi charges for the AMI packaging and configuration. Launch one Ubuntu 24.04 instance and connect the web UI through a Session Manager port-forwarding tunnel. Configure your own OpenAI-compatible provider using a credential file, then chat in the browser or run the included inventory demo through the application API. The optional API walkthrough requires your configured provider, checks a structured response and saves input, request, response and hashes. It consumes provider usage and does not create a browser conversation. Conversations stay in the browser's IndexedDB with a localStorage fallback: use the same origin and browser profile and export conversations for backup. Server configuration and the randomly generated instance access code persist across restarts. No enterprise RBAC, shared server-side chat database, provider subscription, model credit, a local inference model, GPU or commercial NextChat service is included. EC2, EBS, data transfer and provider usage are separate charges. Recommended instance: t3.medium with 4 GiB RAM and at least 24 GiB root storage. The on-instance guide explains setup, backup, recovery and provider requirements. Session Manager may open as ssm-user; wait for cloud-init and switch with sudo -iu ubuntu for application commands. Provider configuration is supplied after launch through a protected file; browser credential overrides are disabled. The static UI is reachable through the local tunnel; the per-instance code protects model API requests. No public HTTPS endpoint or reverse proxy is configured. Software Sushi does not claim upstream or AWS endorsement. Software is USD 0.03 per running instance-hour; any five-day, one-concurrent-instance software trial is subject to the actual offer. Infrastructure and provider charges apply separately during that trial.
Highlights
- Self-hosted web assistant with loopback UI and API on port 3000, accessed through Session Manager.
- Random per-instance access code and file-based configuration for a buyer-supplied OpenAI-compatible provider.
- Browser-local conversations and an optional API inventory walkthrough with independent JSON and saved-file readback.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Free trial
Dimension | Cost/hour |
|---|---|
t3.medium Recommended | $0.03 |
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 billed by AWS and 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
NextChat 2.16.1 on Ubuntu 24.04 x86_64 with a random first-boot access code, loopback web UI and API, file-based buyer provider configuration, browser-local conversations and an optional API inventory walkthrough with independent saved-result readback. Recommended t3.medium with 4 GiB memory and 24 GiB storage. Provider service and charges are supplied separately after launch.
Additional details
Usage instructions
- Launch Ubuntu 24.04 x86_64 on t3.medium with at least 4 GiB RAM and 24 GiB encrypted gp3 root storage, require IMDSv2 and attach your own appropriate Session Manager instance role. Allow outbound HTTPS to Systems Manager and the selected provider; no inbound application port is required.
- In the Session Manager administrative shell run sudo cloud-init status --wait, inspect sushi-nextchat-firstboot.service and nextchat.service, and switch with sudo -iu ubuntu for the user-owned provider-file workflow in /opt/sushi/docs/README.md. Configure a provider root URL without a trailing /v1, exact supported model and credential in a mode-0600 file; invoke sudo /opt/sushi/bin/sushi-nextchat configure --provider-file /home/ubuntu/.config/nextchat/provider.json. Do not put credentials in command arguments, URLs, recordings or support logs.
- From your workstation use AWS-StartPortForwardingSession to forward instance port 3000 to workstation port 3000. Keep that tunnel open and open its local HTTP address in your browser. The app listens only on instance loopback; this package does not configure a public HTTPS endpoint, certificate or reverse proxy. Read the per-instance access code privately from /home/ubuntu/.config/nextchat/access-code and enter it in the app. The code protects model API requests; the static UI is available through the tunnel. Browser provider credential overrides are disabled.
- The browser app requires your configured OpenAI-compatible provider supporting chat completions and streaming responses. Remote providers require HTTPS and valid TLS. No provider account, credit or inference model is included. The included API walkthrough sudo -iu ubuntu bash /opt/sushi/docs/demo.sh sends a new synthetic inventory task, consumes provider usage and independently rereads the saved result under /home/ubuntu/nextchat-demo/. It does not add a browser chat. Saved API results can be reread without a provider call using /opt/sushi/bin/nextchat-demo --readback SAVED_RUN_DIRECTORY.
- Conversations persist in the same browser origin/profile through IndexedDB with a localStorage fallback. Export them through the app for backup; clearing browser data, using another profile or changing the tunnel origin can make them unavailable. Server EBS snapshots do not back up browser conversations. Root-only instance/provider configuration and the matching operator access-code copy persist independently on the instance. Protect backups and do not delete identity/configuration to force recovery.
- Software is USD 0.03 per running instance-hour. If your actual offer includes the five-day software trial for one concurrent instance, other simultaneous instances incur software charges and EC2, EBS, data transfer and provider charges still apply during the trial. Read /opt/sushi/docs/README.md for setup, provider restrictions, persistence and recovery.
- Getting started: https://softwaresushi-marketplace-branding-public.s3.us-east-1.amazonaws.com/docs/nextchat/getting-started.html
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; upstream hosted or commercial support is not included.
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.