Gemini API managed agents

Google's Agents API defines and packages reusable AI agents with a base model, instructions, and a preconfigured environment. Agents run in managed cloud sandboxes rather than on the user's laptop; the environments can be shared with users or teams and accessed through an API call.

Managed Agents is a Google Gemini API service for running the Antigravity agent in persistent remote Linux sandboxes. A call to the Interactions API provisions a sandbox, runs the agent loop, and returns an interaction ID and environment ID; subsequent calls can use the previous interaction ID for conversation context and the environment ID to retain files, installed packages, and other sandbox state. The service supports streaming, file downloads, loadable sources such as Google Cloud Storage and GitHub, reusable skills, secure credential injection, and configurable named agents.

Gemini Enterprise Agent Platform, formerly Vertex AI, is a Google Cloud platform for developers to build, run, scale, govern, and optimize autonomous AI agents and agent workflows. It provides session and memory management, persistence, parallel execution, model swapping, and built-in support capabilities.

Gemini API CLI is an experimental command-line interface for the Gemini Interactions API and managed-agent platform. It can run model interactions and managed agents, generate or analyze text and media, transcribe audio or video, manage files, models, agents, environments, triggers, and webhooks, and stream results in formats including JSON, YAML, and TOON. Commands expose machine-readable usage information and request schemas, while --dry-run validates inputs and previews redacted HTTP requests without contacting the API. Authentication can use API keys, OAuth access tokens, an operating-system keychain, or a configuration file. The repository describes the CLI as beta software with possible breaking changes, generated through Speakeasy; its software is licensed under Apache 2.0, and the repository states that it is not an official Google product.

Antigravity agent is a Google DeepMind agent harness for local use and managed remote sandboxes through the Gemini API and Google AI Studio. A single Interactions API call can provision a secure, Google-hosted Linux sandbox identified by an environment ID, where the agent uses Gemini 3.8 Flash to plan, execute Bash, Python, and Node.js code, observe results, and repeat until the task is complete. It can install packages, run tests, build applications, manage files, search Google, fetch web pages, and call custom functions or remote MCP servers. The harness supports reusable skills, configurable tools, multi-turn interactions, streaming, automatic context compaction, persistent sandbox files, synchronous hooks for intercepting and validating code-execution and filesystem operations, and sources loaded from GitHub, Google Cloud Storage, or inline files. Managed environments provide a credential-injecting proxy and named agents, allowing the same workflow to run locally and in the cloud.