Sold by: Software Sushi
Deployed on AWS
This is paid repackaged open-source software. Build stateful workflows with LangGraph OSS, SQLite checkpoints and a human-approval API on Ubuntu 24.04.
Overview
This is a paid repackaging of open-source software. LangGraph 1.2.18 core is MIT-licensed; included dependencies retain their own licenses. Software Sushi supplies the AMI integration, an authenticated local JSON task API, a CSV calculator workflow, systemd services and on-instance documentation. The upstream projects do not endorse this image.
The supplied workflow calculates a synthetic CSV with a real LangGraph tool, obtains a bounded model proposal, pauses for human approval and publishes a local JSON report after approval. SQLite checkpoints preserve the workflow across graceful service restarts. A unique local action record prevents repeated publication of the supplied report. This does not promise exactly-once execution for arbitrary external actions.
Use Ubuntu 24.04 x86_64 with at least 2 GiB RAM and 16 GiB root storage; t3.small is the starting recommendation. Connect through AWS Systems Manager Session Manager, then become ubuntu with sudo -iu ubuntu. The JSON API listens only on loopback port 8123 and requires a per-instance token. There is no browser UI. Leave inbound application ports closed and use the supplied sushi-langgraph client.
After launch, configure your OpenAI-compatible HTTPS provider and exact model in /etc/langgraph/provider.json using a secure editor. No model weights or provider credentials are included. Provider access, inference usage, EC2, EBS and data transfer charges are separate. Review the saved proposal before approving an action. The on-instance guide at /opt/sushi/docs/README.md describes provider setup, the restart and approval walkthrough, persistence, backups and recovery.
This single-user starter uses only the OSS library and local persistence. It does not include LangSmith Server, Studio, managed deployment, multi-tenant authentication or commercial control-plane features. The dependency client packages required by the OSS library do not provide those hosted services.
Software costs USD 0.03 per running instance-hour on each offered type. Public English guide: https://softwaresushi-marketplace-branding-public.s3.us-east-1.amazonaws.com/docs/langgraph/65e335eb7ccf2925bb67/getting-started.html
The provider and chosen model must support OpenAI-compatible JSON-object response mode and return the exact requested action and run ID. Invalid proposals remain recoverable failed nodes; consult the guide before retrying.
Highlights
- LangGraph OSS with local SQLite checkpoints and a bounded CSV calculator workflow.
- Human approval before report publication, with checkpoint resume across graceful service restarts.
- Authenticated loopback JSON API, customer CLI and an independent CSV/result readback demonstration.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04
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.small Recommended | $0.03 |
t3.medium | $0.03 |
t3.large | $0.03 |
t3.xlarge | $0.03 |
t3.2xlarge | $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 not eligible for refund by us.
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
LangGraph 1.2.18 OSS on Ubuntu 24.04 with automatic startup, authenticated loopback API, native CSV tool, SQLite checkpoints, explicit human approval and independent persistence readback. This integration requires a JSON-object-capable OpenAI-compatible model configured after launch. Recommended t3.small with at least 2 GiB RAM and 16 GiB root storage; model use is separate.
Additional details
Usage instructions
Launch t3.small or larger x86_64 with at least 2 GiB RAM and 16 GiB encrypted gp3 root storage and require IMDSv2. Software is USD 0.03 per running instance-hour; EC2, EBS, transfer and model-provider use are separate. For AWS Systems Manager Session Manager, attach an appropriate instance profile and provide outbound endpoint access; the session opens as ssm-user. Run sudo cloud-init status --wait, then sudo -iu ubuntu and sushi-langgraph health. No browser UI is included. Keep inbound application ports closed; the authenticated JSON API listens only on 127.0.0.1:8123. In an unrecorded administration session, use sudoedit /etc/langgraph/provider.json to configure your HTTPS model endpoint, exact available model and key; retain root:ubuntu ownership with file mode 0640 and directory mode 0750. The model must support JSON-object response mode and the exact requested two-field proposal. Never place credentials in arguments, logs or recordings. As ubuntu, run bash /opt/sushi/docs/demo.sh start /home/ubuntu/langgraph-results/my-first-run. Review paused.json, restart the service as an administrator, then use demo.sh resume and, after another restart, demo.sh read with the same directory. Only a successful independent final read prints SUSHI_CUSTOMER_DEMO_PASSED. The tool computes synthetic CSV values in code; the model proposes publication, and an explicit approval publishes a local report. SQLite state persists under ~/langgraph-data; outputs live under ~/langgraph-results. Provider access and billing are your responsibility; no keys or weights are bundled. Configure backups and retention. Full English guide: https://softwaresushi-marketplace-branding-public.s3.us-east-1.amazonaws.com/docs/langgraph/65e335eb7ccf2925bb67/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 project and model-provider support are 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.
Similar products
This is a repackaged open source software product wherein additional charges apply for independent packaging, maintenance and setup guidance. Build and run visual AI workflows with Langflow 1.13.0, private administrator login and persistent SQLite storage.
This is paid repackaged open-source software. Compare tabular datasets with Evidently 0.7.23 on Ubuntu 24.04, inspect drift reports in a local monitoring UI, and export HTML and JSON. No model or Evidently account is required.
This is paid repackaged open-source software. Evaluate assistant answers with DeepEval, optional model judging and saved JSON score reports on Ubuntu 24.04.
This is paid repackaged open-source software. Store text documents and retrieve exact sources with Haystack 3.4.1 and Hayhooks 2.1.0 on Ubuntu 24.04. Add a model you supply for cited answers.
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.