Sold by: Software Sushi
Deployed on AWS
This is paid repackaged open-source software. Run an Agno AgentOS API with a CSV calculation tool and persistent SQLite sessions on your EC2 instance.
Overview
Run an Agno agent through an authenticated API on your own EC2 instance. This paid repackaging of Agno 3.1.11 includes Software Sushi installation, service configuration, buyer documentation and a CSV Analyst starter. The agent reads a local CSV, invokes a real calculation tool and saves JSON results with persistent SQLite sessions. Configure your own OpenAI-compatible model provider after launch; API usage charges and provider terms apply separately. No model weights, provider credits, commercial Agno control-plane UI, hosted service, no-code editor or SSO are included. The API binds to 127.0.0.1:7777 and requires a per-instance Bearer token. Connect with Session Manager or an SSH tunnel; no public application port is needed. Start with a t3.medium and 24 GiB root volume for use with a remote model. On the instance, read /opt/sushi/docs/README.md, run sudo -iu ubuntu sushi-agno configure, restart sushi-agno, and run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh. Settings and provider keys remain in a mode-0600 file. Sessions and task files persist locally across idle service restarts; back them up before replacing the instance or volume. Software Sushi is independent of Agno and does not imply endorsement.
This is paid repackaged open-source software. Agno 3.1.11 uses Apache License 2.0; dependencies retain their own licenses and original notices. The pinned application and dependency inputs, original notices and corresponding source archives are retained on the instance.
AWS Systems Manager Session Manager requires your own appropriate instance profile and outbound regional endpoint access; sessions initially open as ssm-user. Provider configuration uses a hidden-key prompt as ubuntu. Only send data that your chosen model provider is authorized to process; review its privacy and retention terms. The API token grants single-user administrator access and must not be shared with untrusted callers. There is no bundled commercial control-plane UI or OS sandbox for arbitrary agents.
Software is USD 0.03 per running instance-hour on each offered type. EC2, EBS, data transfer and model-provider use are billed separately. English getting-started guide: https://softwaresushi-marketplace-branding-public.s3.us-east-1.amazonaws.com/docs/agno/81fef5488b14eff437f3/getting-started.html
Highlights
- Local authenticated AgentOS API with a native Agno CSV calculation tool and independently checkable JSON results.
- SQLite conversation sessions and task files retained across idle service restarts, with documented backup and recovery.
- Bring an OpenAI-compatible provider with tool calling; no bundled model weights or commercial control-plane UI.
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.medium Recommended | $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
Agno 3.1.11 on Ubuntu 24.04 x86_64 with automatic authenticated loopback AgentOS API, a CSV Analyst native calculation tool, local SQLite sessions and independent saved-result readback. Configure your own entitled OpenAI-compatible tool-calling model after launch. No commercial Agno control-plane UI, hosted service, SSO or model weights. Recommended t3.medium, 4 GiB RAM and 24 GiB root storage. Verified version: 0.1.2 (Agno 3.1.11). Source AMI: ami-0b6d1064ce612a4c3.
Additional details
Usage instructions
Launch t3.medium or larger x86_64 with at least 4 GiB RAM and 24 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. Use AWS Systems Manager Session Manager with your own appropriate instance profile and outbound regional endpoint access; sessions initially open as ssm-user. Alternatively use your own SSH key with tightly restricted access. Do not expose the application port publicly. Run sudo cloud-init status --wait, then sudo -iu ubuntu sushi-agno health. The AgentOS API starts automatically and listens only at 127.0.0.1:7777; every route requires its per-instance Bearer token. No commercial Agno UI is bundled. To configure a model, run sudo -iu ubuntu sushi-agno configure in an unrecorded terminal and enter an entitled OpenAI-compatible model ID, base URL and hidden provider key. Remote endpoints require HTTPS, non-streaming chat and tool calling. No weights, model account, subscription or credit is supplied. Do not print settings, keys or populated provider errors. Restart with sudo systemctl restart sushi-agno, then run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh. The demo reads a synthetic CSV containing 5, 17 and 20 through a real calculation tool, checks sum 42 and three rows, and rereads the native stored session. Successful readback prints SUSHI_CUSTOMER_DEMO_PASSED. New tasks and original JSON outputs remain under /var/lib/agno/workspace; SQLite sessions persist at /var/lib/agno/sessions.db. The mode-0600 settings file is /home/ubuntu/.config/sushi-agno/settings.json. Back up settings securely and the application data while stopped before replacing the instance or root volume. Use the login banner SSM port-forward command for API access without public inbound rules. After provider or connectivity failures, verify endpoint, entitlement, tool support and outbound access; preserve the failed task and use a new task directory. Read the on-instance /opt/sushi/docs/README.md for independent readback, idle-restart checks and recovery. English guide: https://softwaresushi-marketplace-branding-public.s3.us-east-1.amazonaws.com/docs/agno/81fef5488b14eff437f3/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 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.
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.
Nanobot with localhost WebUI, native Python tools and a private Telegram channel. Customer cloud-model credentials are required after launch.
This is paid repackaged open-source software. Evaluate assistant answers with DeepEval, optional model judging and saved JSON score reports on Ubuntu 24.04.
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.