Endpoint: AIPLATFORM_EMULATOR_HOST=http://localhost:24080.
Vertex AI agent testing
Vertex AI local testing for AI agents
Use LocalCloud when an agent needs to create, exercise, and reset Vertex AI resources without touching a real Google Cloud project. The same SDK shape points at localhost through AIPLATFORM_EMULATOR_HOST=http://localhost:24080.
Endpoints: HTTP/REST :24080.
Evidence state: partial; Local development coverage is partial. Known limits: [prod_only] Model training and tuning (requires TPU/GPU clusters)., Prediction endpoints and model management are out of current scope..
Registry default: off; assembled default: off (verified); minimum tier: pro.
Persistence: metadata (verified). Audited metadata survives restart while the LocalCloud volume is retained
Route the SDK before writing code
Start LocalCloud, export AIPLATFORM_EMULATOR_HOST=http://localhost:24080, and make the agent perform one Vertex AI operation before changing application logic. That catches accidental production routing early.
Prefer one representative behavior over broad smoke tests
A useful agent check creates local Vertex AI state, reads it back with the project SDK, and records which feature was covered. It should not require a GCP account, service-account key, or billing project.
Use only documented setup paths
Create deterministic state through a contract-documented seed registrar or through an operation listed on this page. Do not assume every service supports seed data, reset, or persistent state.
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.
Environment
eval "$(localcloud env)"
# Verify that the generated environment includes AIPLATFORM_EMULATOR_HOST; do not replace a CLI-remapped value with a hard-coded port. Compatibility
Local check versus release validation
| Area | LocalCloud local check | Real GCP still needed for |
|---|---|---|
| SDK routing | AIPLATFORM_EMULATOR_HOST=http://localhost:24080 points clients at localhost. | Production endpoint, auth, IAM, quota, and regional behavior. |
| Supported features | generateContent, streamGenerateContent, embedContent, countTokens (partial) — Deterministic local GenAI REST facade exists for selected flows. | [prod_only] Model training and tuning (requires TPU/GPU clusters).; Prediction endpoints and model management are out of current scope.; models, tuning, batch prediction: unsupported |
| Agent safety | No default cloud account, credentials, or billing project required. | Final release validation in the target GCP project. |
Use the sandbox deliberately
- Permitted workflows use local endpoint values and should stop rather than fall back to real Google Cloud or real credentials. The Public Preview License permits individuals and organizations, including for-profit companies, to use LocalCloud for non-production internal development, testing, CI, evaluation, and pilots.
- LocalCloud emulates bounded local development workflows. Validate application behavior against real Google Cloud before production deployment.
- Before production deployment, unset LocalCloud emulator environment variables and validate behavior against real Google Cloud.
- Local development coverage is partial. Known limits: [prod_only] Model training and tuning (requires TPU/GPU clusters)., Prediction endpoints and model management are out of current scope..
Keep the agent on the supported path
- Vertex AI service page — Service-specific supported and unsupported capability list.
- 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.
Claims are tied to current sources
- LocalCloud service metadata — Reviewed 2026-08-26; implementation local-facade.
- LocalCloud agentic facts reviewed 2026-08-26.