Gemini CLI sandbox

Gemini CLI local GCP sandbox

Gemini CLI-style workflows can use LocalCloud as a concrete localhost target for GCP code. The key is to separate model authentication from cloud-resource authentication: a CLI may need its own model access, but LocalCloud tests should not need Google Cloud credentials.

Read docs Check compatibility SDK examples

Agent prompt CTAs

Start LocalCloud

Give an agent one URL and have it start the local GCP sandbox.

Fetch https://local.cloud/ai/agents.md and follow the instructions to start LocalCloud on my machine. Verify Docker, start or reuse the localcloud container, export emulator environment variables, and run one local GCP SDK/API smoke check. Do not ask for or use real GCP credentials.

Configure this repo

Have an agent wire an existing project to LocalCloud safely.

Set up this repository to use LocalCloud for local GCP development. First read https://local.cloud/ai/agents.md, then inspect this repo, identify the GCP services and SDK language, configure emulator environment variables, and run the narrowest integration test against localhost. Do not use real GCP credentials or production endpoints.

Troubleshoot routing

Diagnose why SDKs or Terraform are still reaching real GCP.

Troubleshoot my LocalCloud setup. Read https://local.cloud/ai/agents.md, check whether Docker and the localcloud container are healthy, verify emulator environment variables are set in this shell/test runner, and identify any SDK or Terraform configuration that could still call real Google Cloud.

Fact

Use shell-visible emulator variables for SDK tests.

Fact

Model or CLI login is separate from GCP runtime credentials.

Fact

Ask for a local proof before broader refactors.

Setup caveat

Keep model access separate from GCP access

If a Gemini CLI variant requires login or API keys for the assistant itself, that does not mean the repository should receive Google Cloud credentials. LocalCloud only needs Docker and localhost endpoint variables for default tests.

Verification

Make the CLI show the route it used

Ask for the command, active env vars, and a short result from a local service operation. If any command reaches production endpoints, stop and troubleshoot routing before editing more files.

Copy-ready setup

Commands and prompts

Use these snippets as starting points, then keep the checks scoped to localhost until you intentionally validate against real Google Cloud.

Gemini CLI prompt

Use LocalCloud for local GCP validation. Fetch https://local.cloud/ai/agents.md, start or reuse the Docker container, export emulator env vars in this shell, and run one SDK/API check against localhost. Keep assistant authentication separate from Google Cloud credentials.

Limitations

Use the sandbox deliberately

Gemini CLI distributions and approval models change; verify current client docs before publishing client-specific install claims.
Local emulation does not replace final production validation against real Google Cloud.

Next routes

Keep the agent on the supported path

Compatibility matrix — Check current support boundaries before relying on a local-only test.
Service catalog — Review every LocalCloud service, endpoint, and limitation.
SDK examples — Use standard Google Cloud SDKs pointed at localhost.
Seed data — Load deterministic fixtures for repeatable agent and CI runs.