Today we are releasing a new Gemini managed agents version with better caching, lower costs, a Files API, and a Credentials API. 📉 Up to 30% lower costs with up to 22% higher cache hits 📁 Files API: Upload, list and download files from sandbox easily 🔐 Credentials API... for MCP servers, OAuth2, and 3rd-party APIs as secure egress proxy 🆓 Free tier to experiment in Google AI Studio & Gemini API Start Here:show more

`antigravity-preview-09-2026` upgrades our managed agent runtime: - Runs on Gemini 3.8 Flash by default, or configure default model. - Persistent Linux sandbox with bash execution, file tools (`view_file`, `write_to_file`, `replace_file_content`), Google Search, and URL context. - 30% cost reduction on multi-turn coding and 17% on reasoning thanks to higher cache hit rates. - 40% fewer tokens on file edits and up to 8% higher task completion on SWE and research evals. - Automatic context compaction at ~135k tokens. - Save reusable agent configs once with `agents.create()` and call them by id. Docs:

New Credentials API to securely authenticate with external services and MCP servers without the model ever seeing your secrets: - Register secrets once with `credentials.create()` supporting `bearer_token`, `environment_variable`, or `oauth2` (with auto-refresh and token rotation). - Zero plaintext exposure: Secrets never enter model context, stdout, memory. - The agent only sees a placeholder (e.g., `__GEMINI_CRED_slack-bot-token__`). - Egress proxy swaps real token on the request only for allowlisted `trusted_domains` (any exfiltration attempt to another host gets a `403`). - Bind credentials directly to remote `mcp_server` tools or sandbox env vars. Docs:

New Files API to move data in and out of your agent environment: - Seed files inline or upload data mid-conversation with `files.upload()`. - Inspect generated files and directory sizes with `files.list()`. - Download artifacts, dashboards, reports, CSVs, or git repos with `files download()`. - Sandboxes persist across turns via `environment_id` Docs:

that’s great feature to use with incoming models

cached credentials combined with managed agent routing lowers operational friction for sandbox deployment significantly 🔥

22% higher cache hits and a 30% cost reduction right out of the gate is wild. Pairing sandbox file management with that level of efficiency makes production agents so much more viable. Incredible work! 📉👏

The Credentials API is the interesting part. A secure egress proxy means the agent never holds the secret, which is the right shape. The catch is scope: if the proxy returns a token that still reaches every MCP server you connected, you moved the key, not the boundary.

Can this run in an eu region only? (And greetings from Heidenheim Philipp)