AI 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.
3 uses taken from transcripts — each links to the moment in the video.
A coding-oriented agent harness that can investigate repositories, read and modify files, reason about tasks, and generate reports autonomously. In Managed Agents, it runs in a persistent remote sandbox and can use the same skills and prompts as a local Antigravity setup.
Provides the agent harness used locally and in managed remote sandboxes, including coding workflows and reusable skills.
A remote agent in the Gemini API powered by the same harness as the Antigravity product. It runs in a Google-managed cloud sandbox where it can run code, create files, install dependencies and tools, share environments with other agents, and picks up skills and AGENTS.md files automatically.
2 in the library.