Data handling
Your repository is cloned into the sandbox for the duration of a session and torn down when the session ends — no repository contents or working state persist afterward. The one exception is projects. When you use a project to speed up environment setup, its repositories and pre-installed dependencies are cached in reusable environments so future sessions start faster. Those cached copies persist until the project is rebuilt or removed. Model providers handle prompt data according to their own retention policies — see the retention table in Max for Tembo-hosted models. With BYOK, model requests run against your own provider account, so provider-side retention follows that account’s terms.Sandbox sizes
Each session runs in a dedicated Linux VM, and no two sessions share the same VM.
Micro and Medium are best for routine code analysis, fixes, features, and reviews. Large and XL are best for heavier builds, integration tests, Docker workloads, large repositories, or multi-container setups.
Your plan sets the largest size you can select — see Plans. XXL and Ultra are not included in a standard plan; contact support@tembo.io to request access.
VM sandboxes include full nested virtualization for Docker-in-Docker and provide a stronger isolation boundary.
If your org requires that untrusted code only runs with a VM boundary, we can enforce a VM-only posture. Contact support@tembo.io.
Pre-installed tools
All sandbox sizes come with:Go and Elixir are available through Nix dev shells. Add a
tembo.nix to install language-specific tooling for your project.Add custom dependencies
Add atembo.nix file to your repository when your project needs tools that are not pre-installed in the sandbox.