guava deploy up, the CLI packages your project, builds it in the cloud, and launches it for you. No servers to set up, no infrastructure to manage.
Security
Your deployments are secure by default:- Isolated environments — Each deployment runs in its own private sandbox, completely separated from other users’ workloads.
- Network protection — Your sandbox can make outbound requests to the internet (e.g. calling APIs), but no one can connect into your sandbox from the outside.
- Secure credentials — Your API key and phone number are injected securely at runtime and never appear in logs.
- Dedicated resources — CPU and memory are reserved for your deployment, so performance is consistent.
Step-by-step guide
Prerequisites
- A Guava account
- A terminal (macOS, Linux, or Windows PowerShell)
- The Guava CLI installed and authenticated — follow the Quickstart guide
Step 1 — Write your agent code
Edit your entry point (main.py for Python, main.ts for TypeScript) with your voice-agent logic.
Add dependencies the usual way for your language — a Python manifest/lockfile (pyproject.toml, requirements.txt, uv.lock, …) or a Node one (package.json, package-lock.json, pnpm-lock.yaml, yarn.lock). The build auto-detects them at deploy time; see dependency detection in the CLI reference for the exact install command per file.
Step 2 — Deploy
- Check for changes — if your code hasn’t changed since the last deploy, the build step is skipped automatically.
- Upload your code to cloud storage.
- Build a container image with your chosen base image and dependencies. The CLI shows build progress in the terminal.
- Launch your sandbox and wait until it’s running. The CLI shows the deployment status as it starts up.
Step 3 — Stop deployment
Managing your deployment
Once your agent is deployed, these commands let you inspect and manage it:Temporary file storage
To write files at runtime (for example, to cache data), use
/tmp. Note that /tmp is ephemeral: contents are lost when the sandbox restarts.