Sold by: Software Sushi
Deployed on AWS
Free Trial
Tabby is an open source, self-hosted AI coding assistant server for code completion and chat, an alternative to hosted copilots. This Ubuntu 24.04 AMI runs the Tabby v0.32.0 CPU server on localhost, with no model weights baked in. Attach the completion model you choose and keep code and prompts in your own AWS account.
Overview
Tabby v0.32.0 is a self-hosted coding assistant server: IDE extensions send code context to it and it returns completions and chat answers from a model you control. This AMI is for engineering teams that want a self-hosted copilot alternative inside their own AWS account.
What you get: the Tabby CPU server (official v0.32.0 release binaries, with SHA-256 recorded) listening on 127.0.0.1:8080, first-boot state under /var/lib/tabby, a loopback embedding stub on 127.0.0.1:18080 so the server starts without downloading any model, and an example config for attaching a model at /opt/sushi/etc/tabby/customer-model.example.toml. No completion, chat or embedding weights are included,; completions and chat start working once you attach a model. The Enterprise web UI is disabled (--no-webserver); GPU/CUDA builds are out of scope.
Getting started takes a few minutes: launch t3.medium (16 GiB encrypted gp3 or larger, IMDSv2), attach an instance profile with AmazonSSMManagedInstanceCore, allow outbound HTTPS and keep the security group free of inbound rules. Connect, run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh to check health and the no-model boundary, then copy the example model config into /var/lib/tabby/config.toml and restart tabby.service. Local models need more RAM and disk, so size up before downloading weights.
Software fee: USD 0.02 per running t3.medium instance-hour with the first five days free for one concurrent instance; the same full software runs throughout and there is no product-imposed time, user or usage limit. Additional concurrent instances incur software fees. EC2, EBS, data transfer and any model-provider charges are billed separately. No annual offer is configured.
This is a repackaged open source software product wherein additional charges apply for independent AWS packaging, validation, maintenance and setup documentation (https://tabby.tabbyml.com/docs/welcome/ ). TabbyML publishes non-ee/ content under Apache-2.0. The ee/ tree uses the Tabby Enterprise license and is not part of this offer. Software Sushi supplies the AMI recipe and setup guide without claiming TabbyML endorsement. Back up /var/lib/tabby and /etc/tabby after adding models or changing config.
Highlights
- Self-hosted AI code completion and chat server, so code context stays in your AWS account.
- Starts with no model downloads. Attach the completion model you choose using the included example config.
- The server binds to localhost and you connect through Session Manager. No inbound ports are needed.
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
Free trial
Try this product free for 5 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
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 | $0.02 |
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.
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
Tabby v0.32.0 CPU server on Ubuntu 24.04 LTS, packaged by Software Sushi from official release binaries with recorded SHA-256. The server listens on 127.0.0.1:8080 and is reached through Session Manager port forwarding. State persists under /var/lib/tabby. Includes a guided walkthrough (sudo -iu ubuntu bash /opt/sushi/docs/demo.sh). Attach your own model after launch; no model weights are included.
Additional details
Usage instructions
- Launch t3.medium (16 GiB or larger encrypted gp3, IMDSv2) with AmazonSSMManagedInstanceCore and outbound HTTPS. No inbound rules are needed.
- Connect with aws ssm start-session --target <instance-id>. After cloud-init finishes, run: sudo -iu ubuntu bash /opt/sushi/docs/demo.sh (expect SUSHI_CUSTOMER_DEMO_PASSED).
- Attach a model: copy guidance from /opt/sushi/etc/tabby/customer-model.example.toml into /var/lib/tabby/config.toml (with sudo), then sudo systemctl restart tabby.service. Local models need more RAM and disk.
- From your workstation: aws ssm start-session --target <instance-id> --document-name AWS-StartPortForwardingSession --parameters '{"portNumber":["8080"],"localPortNumber":["8080"]}' and check http://127.0.0.1:8080/v1/health . Add your own reverse proxy and authentication before exposing it to IDEs over a network.
- Back up /var/lib/tabby and /etc/tabby. Documentation: https://tabby.tabbyml.com/docs/welcome/ Support: info@softwaresushi.com
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 TabbyML support or Tabby Enterprise features.
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
Sushi ML Studio is no-code machine learning that runs in your browser, on your own EC2 instance. Upload a CSV or Excel file, pick the column you want to predict, and it trains and compares against many scikit-learn models, tells you in plain language how good the best one is, and adds predictions to new spreadsheets. Your data never leaves the instance, and you keep the model file and the Python code that reproduces it.
Open Interpreter lets a language model write and run code to get real work done from plain-English requests: analyze and chart data, clean up files, convert formats and automate scripts. This Ubuntu 24.04 image runs it on an isolated cloud instance instead of your laptop, asks before running any code and works with the model provider you choose.
Production-ready Hermes AI messaging agent on hardened Ubuntu 24.04. Add your model-provider and Telegram credentials and run it in your AWS account.
Goose is an open source AI agent for the command line. Give it a task in plain English and it plans the steps, then reads and writes files and runs shell commands until the job is done, using the LLM provider you configure. This Ubuntu 24.04 image gives you a private agent workstation reachable through Session Manager, with no inbound ports.
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.