{"id":51535974,"url":"https://github.com/lamia-lang/lamia-cloud","last_synced_at":"2026-07-09T08:30:48.993Z","repository":{"id":365800069,"uuid":"1262232287","full_name":"lamia-lang/lamia-cloud","owner":"lamia-lang","description":"Run Lamia scripts on GCP with one-shot --remote execution, Cloud Run Jobs scheduling, Cloud Triggers and Vertex AI integration for secure serverless automation. You don't need to start from scratch for you uses cases!","archived":false,"fork":false,"pushed_at":"2026-06-28T20:18:10.000Z","size":73,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-28T21:12:45.900Z","etag":null,"topics":["ai-agent","automation","cloud-scheduler","llm","serverless","vertex-ai","workflow-automation"],"latest_commit_sha":null,"homepage":"https://lamia-lang.github.io/lamia/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/lamia-lang.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-06-07T18:31:27.000Z","updated_at":"2026-06-28T20:18:14.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/lamia-lang/lamia-cloud","commit_stats":null,"previous_names":["lamia-lang/lamia-cloud"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/lamia-lang/lamia-cloud","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lamia-lang%2Flamia-cloud","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lamia-lang%2Flamia-cloud/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lamia-lang%2Flamia-cloud/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lamia-lang%2Flamia-cloud/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lamia-lang","download_url":"https://codeload.github.com/lamia-lang/lamia-cloud/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lamia-lang%2Flamia-cloud/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35293216,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-09T02:00:07.329Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agent","automation","cloud-scheduler","llm","serverless","vertex-ai","workflow-automation"],"created_at":"2026-07-09T08:30:48.112Z","updated_at":"2026-07-09T08:30:48.981Z","avatar_url":"https://github.com/lamia-lang.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# lamia-cloud\n\nCloud execution backend for [Lamia](https://github.com/lamia-lang/lamia). Run `.lm` scripts once with `--remote`, deploy scheduled cloud jobs, and prepare for upcoming cloud trigger support. Currently supports GCP.\n\nFor common agent use cases, you usually do not need to build custom cloud-agent infrastructure from scratch before shipping with Lamia.\n\n## Installation\n\n```bash\npip install \"lamia-lang[cloud]\"\n```\n\n## Prerequisites\n\n- GCP project with billing enabled\n- Application Default Credentials: `gcloud auth application-default login`\n\nAll required GCP APIs (including Service Usage) are enabled automatically on first deploy.\n\n## Quick Start\n\n1. Add a `cloud` section to your project's `config.yaml`:\n\n```yaml\ncloud:\n  provider: gcp\n  project_id: my-gcp-project\n  location: us-central1  # optional, default: us-central1\n```\n\n2. Run a script once in the cloud with `--remote`:\n\n```bash\nlamia my_script.lm --remote\n```\n\nUse this one-shot run to validate cloud execution, permissions, and logs before adding a schedule.\n\n3. Schedule your script with the `--remote` flag:\n\n```bash\nlamia schedule add my_script.lm --every day --remote\n```\n\nThe `--remote` flag tells lamia to deploy and run the script in the cloud instead of locally.\n\n## Managing Schedules\n\n```bash\nlamia schedule list              # shows all jobs (local + cloud) with live status\nlamia schedule add X --remote    # deploy and schedule a new cloud job\nlamia schedule remove \u003cid\u003e       # tears down cloud resources and removes the job\n```\n\n## How It Works\n\n1. `lamia \u003cscript\u003e.lm --remote` packages your project and runs it as a Cloud Run Job (one-shot)\n2. `lamia schedule add \u003cscript\u003e.lm --remote` deploys the same cloud job with Cloud Scheduler\n3. Cloud Scheduler triggers the job on your cron schedule\n4. Logs are available in Cloud Logging\n5. `lamia schedule list` fetches live execution status from the cloud\n\n## LLM on Cloud — Vertex AI\n\nScripts that use LLM calls run through **Vertex AI** on cloud. This gives you:\n\n- **No API keys** — authentication via IAM, no keys to store, rotate, or leak\n- **Budget control** — Vertex AI quotas and billing alerts\n- **Secure by default** — no API key transport or storage, traffic stays within GCP\n\n### Supported Models\n\n| Provider | Cloud routing |\n|----------|--------------|\n| **Anthropic** (Claude) | Runs natively on Vertex AI — same models, same quality |\n| **Google** (Gemini) | Runs natively on Vertex AI |\n| **OpenAI** (GPT, o-series) | Automatically mapped to Gemini by tier (strong/medium/light) with runtime selection of the best available current Gemini model |\n\nAnthropic and Google models run as-is. OpenAI models are mapped because they're not available on Vertex AI — tier classification is stable while the selected Gemini model is discovered dynamically at runtime.\n\n## Configuration Reference\n\n| Field | Required | Default | Description |\n|-------|----------|---------|-------------|\n| `cloud.provider` | Yes | — | Cloud provider (currently `gcp`) |\n| `cloud.project_id` | Yes | — | Your GCP project ID |\n| `cloud.location` | No | `us-central1` | Region for Cloud Run deployment |\n\nNo environment variables are required.\n\n## Troubleshooting\n\n- If Vertex AI access is not enabled yet, lamia-cloud logs a project-specific URL and attempts to open it automatically in your browser:\n  `https://console.cloud.google.com/vertex-ai?project=\u003cyour-project-id\u003e`\n- After accepting terms, re-run the schedule/install command once.\n\n## Development\n\n```bash\ngit clone https://github.com/lamia-lang/lamia-cloud.git\ncd lamia-cloud\npip install -e \".[dev]\"\npytest\n```\n\n## Releasing\n\n```bash\ngit tag v0.1.0\ngit push origin v0.1.0\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flamia-lang%2Flamia-cloud","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flamia-lang%2Flamia-cloud","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flamia-lang%2Flamia-cloud/lists"}