# Antigravity CLI (slim)

> Google's terminal agent for coding tasks, distributed as a closed-source binary and installed as agy. It replaces Gemini CLI for consumer accounts.

- Full: https://www.anchorterminal.com/tools/antigravity-cli.md (~7,050 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/antigravity-cli.json · canonical https://www.anchorterminal.com/tools/antigravity-cli
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-10

**C · 57.7/100 · rank #599 of 954 · #15 in Agent harnesses · not agent-ready · confidence medium**


Assessment: Google's terminal agent, shipped as a closed-source binary with a terminal sandbox on by default on macOS and Linux and documented headless JSON output. Interactions are used to improve Google products unless users opt out, and a headless run exits 0 when a tool is denied.

## Facts

- Kind: Agent harness · vendor: Google · category: Agent harnesses · legal entity: Google LLC · provenance 56/100
- Auth: OAuth or key · pricing: Freemium · x402: no · licence: Proprietary. The repository holds the README, changelog and examples, with no source and no licence file. Use is under the Google Antigravity Additional Terms of Service, the Google Terms of Service and the Privacy Policy
- Probe metrics: not measured yet (probes haven't run)
- Interfaces: Terminal user interface, with headless runs through `agy -p`, a remote control daemon and an SSH login flow. macOS, Linux, Windows and Android through Termux
- Install: `install.sh` on macOS and Linux, PowerShell and CMD scripts on Windows. The binary is named `antigravity` in the tarball and installed as `agy` in ~/.local/bin
- Models: Gemini 3.8, 3.7 and 3.6 Flash and Gemini 3.1 Pro on every plan. Claude Sonnet 5.5 and Opus 5.5 (thinking) on paid plans. Claude Sonnet 4.6, Opus 4.6 and GPT-OSS 120B are marked for removal on 2 November 2026
- Permission presets: Default runs commands in the sandbox and asks outside it. Request Review turns the sandbox off and always asks. Turbo turns it off and allows everything
- Sandbox: sandbox-exec profiles on macOS and Linux namespaces. Project folders are writable, ~/.ssh and .env are hidden, and network access is limited to approved domains
- MCP: stdio, Streamable HTTP, SSE and WebSocket servers in mcp_config.json, managed with `/mcp`. Allow rules use mcp(server/tool), mcp(server/*) or mcp(*)
- Extensions: Skills as folders with a SKILL.md file, custom subagents, hooks in hooks.json (PreToolUse, PostToolUse and Stop), and plugins installed with `/plugin` or `agy plugin install`
- Headless: `agy -p` or `--print`, with `--output-format` set to text, json or stream-json. Exit 0 for success and soft-denied tools, 1 for an error envelope such as an unknown model, 2 for an ERROR result on malformed stream-json input, and 3 for a model or agent error during a streamed run
- Telemetry: Enable Telemetry in the Account settings controls sharing of Interactions. The settings page also describes the same key as anonymous usage statistics and crash reports
- Implementation: Built in Go, according to Google's announcement of 19 May 2026. Source isn't published
- Releases in 90 days: 47 numbered releases from 1.1.2 (13 July) to 1.3.2 (8 October 2026)

- Scores: Reliability 43, Performance pending, Schema & documentation 78, Agent ergonomics 78, Security & auth 53, Payments & pricing 30, Task success pending, Maintenance & community 68, Transparency & trust 54 · total over the 7 assessed categories
- Why: Reliability, Local-package reading. · Schema & documentation, Framework reading. · Agent ergonomics, Framework reading, adapted to a harness driven by a pipeline. · Security & auth, Framework reading (credentials and telemetry defaults, approvals and sandboxing, guardrails, audit, security programme), five lines. · Payments & pricing, Harness reading of the published rubric. · Maintenance & community, 1.3.2 on 8 October 2026 (30). · Transparency & trust, Closed source, with clear terms.
- Sources: 21, open questions: 9, both in the full twin
- Capabilities: agent.harness, agent.mcp-client, agent.multi-agent
- JSON: https://www.anchorterminal.com/api/v1/tools/antigravity-cli.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/antigravity-cli.svg` or a link to https://www.anchorterminal.com/tools/antigravity-cli from a page on antigravity.google or one of its subdomains, or the README of github.com/google-antigravity/antigravity-cli, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Read the `status` field from `--output-format json` and read stderr too. A tool refused for lack of approval still exits 0
2. Pre-approve each shell command and tool a headless run needs with `action(target)` rules under `permissions.allow` in ~/.gemini/antigravity-cli/settings.json, because headless runs cannot ask
3. Export `GEMINI_API_KEY` after setting modelProvider to gemini. The CLI won't start when the key is missing, and setting the variable alone has no effect
4. Turn off Enable Telemetry in the Account settings before running on private repositories if Interactions should not be used for product improvement
5. Set `--print-timeout` explicitly. The docs give a five-minute default, while `agy --help` shows 0s

## Connect

```bash
curl -fsSL https://antigravity.google/cli/install.sh | bash
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Kilo Code CLI | BB | 75.4 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/kilo-code-cli.min.md |
| goose | BB | 73.9 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/goose.min.md |
| Qwen Code | BB | 72.4 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/qwen-code.min.md |
| OpenHands | BB | 70.8 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/openhands.min.md |
| OpenCode | B | 67.7 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/opencode.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)