Skip to main content
guava is the primary interface for working with Guava. It handles authentication, project scaffolding, local runs, deployment, phone number provisioning, conversation history, org management, outbound campaigns, and WebRTC widget codes. Projects can be written in Python or TypeScript/Node — the base image you pick determines the runtime. The Guava SDK is included in the project template.

Quick reference

See CLI commands for the full list, including deployment management, phone numbers, orgs, campaigns, and WebRTC codes.

Targeting a project

Most commands take an optional positional argument that tells the CLI which project to act on. If you omit it, the CLI uses the current directory — so running commands from inside your project folder always works. There are two flavors: The difference: [dir]-style commands need your project files on disk (they build, read config, or run code locally), so they only accept a path. [target]-style commands act on an already-deployed project, so they also accept a project ID — letting you manage a deployment from anywhere without the source checked out.
A [dir] argument that isn’t a real directory silently falls back to the current directory. Double-check the path if a command seems to act on the wrong project.

The guava.toml file

Every Guava project has a guava.toml file in its root directory, created by guava create or guava deploy up. It stores the project’s configuration and deployment state. The CLI reads it to identify the project and track deployments.
Projects created with CLI versions 0.29.0 and lower will have a JSON .guava file. The CLI will automatically migrate to the new guava.toml on the next save.
guava.toml

Instance tiers

Base images & dependencies

When you create a project, you choose a base image. During deployment, your code and dependencies are built on top of this image to produce the final container that runs in the cloud. You can change the base image later with guava update. The base image also determines the project runtime: python-sandbox:* images run Python, node-sandbox:* images run TypeScript/Node. Available base images:
  • python-sandbox:3.14
  • python-sandbox:3.13
  • python-sandbox:3.12
  • python-sandbox:3.11
  • python-sandbox:3.10
  • node-sandbox:26
  • node-sandbox:24
  • node-sandbox:22

Dependency detection

During the build, the system installs your dependencies automatically based on the files present in your project root. It checks each set of files in order and uses the first match. Python: Node / TypeScript: For local Node runs (guava run), also run npm install (or pnpm install / yarn install) first so node_modules exists.

Troubleshooting

  • “Please run guava login” — Your session has expired or you haven’t logged in yet. Run guava login to re-authenticate.
  • “No main.py / main.ts found” — deploy up requires an entry point in your project directory (main.py for Python, main.ts for Node). Make sure you’re running the command from the right folder.
  • Deploy didn’t pick up my changes — If nothing changed since the last deploy, the build step is skipped automatically. Use guava deploy up --rebuild to force a full rebuild.
  • Build failed — Run guava deploy build-logs to see the full build output and diagnose the issue.
  • Missing files in deployment — deploy up excludes guava.toml, hidden files/dirs, __pycache__, and node_modules from the upload. Make sure your files aren’t in an excluded path.
  • Dependencies not installing — The build system auto-detects dependencies from your manifest/lockfiles. For Python that’s pyproject.toml, requirements.txt, uv.lock, poetry.lock, or requirements.in; for Node it’s package.json, package-lock.json, pnpm-lock.yaml, or yarn.lock. Make sure one is present in your project root. For local Node runs, also run npm install so node_modules exists.

Example