[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [Muse Ember](https://spiral.ai/integrations/antigravity/muse-ember)

# How to Use Muse Ember in Google Antigravity

Muse Ember handles focused coding tasks, routing, and document extraction. Choose it for repeated execution; Muse Spark and Muse Wonder are better choices for hard one-shot coding and knowledge-heavy questions.

|  |  |
| --- | --- |
| Model | Muse Ember |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.002668 per run at the default inputs. $0.13 per 1M input tokens, $0.65 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Muse Ember in Google Antigravity

- Use Muse Ember to investigate the failing parser test in this project. Make the smallest relevant fix, run the parser tests, and report the change and actual results.
- Use Muse Ember to port the date-normalization function from Python to TypeScript using the existing fixtures as the reference. Preserve its behavior and report any case that cannot be matched.
- Use Muse Ember to inspect the request router and its tests. Classify the uncovered request examples using the existing routing rules and add tests for those examples.
- Use Muse Ember to summarize the authentication module from its source and tests. List entry points, dependencies, and behavior that the tests establish, with file references.
- Use Muse Ember to update the deprecated helper calls in the validation module only. Follow the replacement examples already in the project and run the relevant checks.

## How to set up Muse Ember in Google Antigravity

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Open the MCP config**: * Antigravity App: click Customizations, then Installed. In the MCP Servers section, click Copy Config File Path and open that file. * Antigravity IDE: click … at the top of the agent side panel, select MCP Servers, then Manage MCP Servers › View raw config. * Antigravity CLI: edit `~/.gemini/config/mcp_config.json`.

2. **Add the server**: Add Spiral under `mcpServers`:

```json
{
  "mcpServers": {
    "spiral": {
      "serverUrl": "https://api.spiral.ai/mcp"
    }
  }
}
```

3. **Sign in**: In the Antigravity App, open Customizations › Installed. Under MCP Servers, click Authenticate next to Spiral. Sign in to Spiral, pick the organization and click Authorize. Copy the authorization code the browser shows, paste it into Enter authorization code and click Submit. No API key.

### Use the Spiral skill

1. **Send Google Antigravity this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Muse Ember**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openrouter",
    "model": "meta/muse-ember",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds Muse Ember on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/antigravity

## Muse Ember tools and prices

- [Meta: Muse Ember](https://spiral.ai/tools/openrouter/meta/muse-ember) (OpenRouter): Up to $0.002668 per run at the default inputs. $0.13 per 1M input tokens, $0.65 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 943718 | — | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). |

## What can you do with Muse Ember in Google Antigravity?

Turn a coding plan into focused repairs, test work, and bounded migrations with Muse Ember. Give each task the relevant files, permitted changes, and acceptance checks.

### Focused code repairs

Give Muse Ember a failing check, the relevant code, and a narrow acceptance criterion. Ask for a targeted fix and the verification result.

### Bounded code migrations

Use Muse Ember to port one function or module against a supplied reference and test suite. Define the interfaces and required behavior before requesting the change.

### Support ticket classification

Have Muse Ember assign each ticket to a defined category and include a short supporting excerpt for review.

### Request routing

Give Muse Ember the available handlers and their responsibilities. Ask it to select a destination for each incoming request and explain the selection briefly.

### Document extraction

Ask Muse Ember to extract dates, names, obligations, or totals from supplied document text into a consistent JSON structure, with source references and missing values marked explicitly.

### Document summaries

Use Muse Ember to summarize each supplied report with the same headings: findings, decisions, open questions, and supporting passages.

### Record normalization

Have Muse Ember convert inconsistent text records into a defined structure. Supply normalization rules and require ambiguous entries to be flagged.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Google Antigravity guides](https://spiral.ai/integrations/antigravity)

## Muse Ember in other agents

- [Amp](https://spiral.ai/integrations/amp/muse-ember)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/muse-ember)
- [Claude](https://spiral.ai/integrations/claude-desktop/muse-ember)
- [Claude Code](https://spiral.ai/integrations/claude-code/muse-ember)
- [Cline](https://spiral.ai/integrations/cline/muse-ember)
- [Codex](https://spiral.ai/integrations/codex/muse-ember)
- [Cursor](https://spiral.ai/integrations/cursor/muse-ember)
- [Devin](https://spiral.ai/integrations/devin/muse-ember)
- [dots](https://spiral.ai/integrations/dots/muse-ember)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/muse-ember)
- [Gemini](https://spiral.ai/integrations/gemini/muse-ember)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/muse-ember)
- [goose](https://spiral.ai/integrations/goose/muse-ember)
- [Grok](https://spiral.ai/integrations/grok/muse-ember)
- [Grok Build](https://spiral.ai/integrations/grok-build/muse-ember)
- [Hermes](https://spiral.ai/integrations/hermes/muse-ember)
- [Instinct](https://spiral.ai/integrations/instinct/muse-ember)
- [Manus](https://spiral.ai/integrations/manus/muse-ember)
- [Muse](https://spiral.ai/integrations/muse/muse-ember)
- [Muse Code](https://spiral.ai/integrations/muse-code/muse-ember)
- [n8n](https://spiral.ai/integrations/n8n/muse-ember)
- [Notion](https://spiral.ai/integrations/notion/muse-ember)
- [OpenClaw](https://spiral.ai/integrations/openclaw/muse-ember)
- [opencode](https://spiral.ai/integrations/opencode/muse-ember)
- [Perplexity](https://spiral.ai/integrations/perplexity/muse-ember)
- [Raycast](https://spiral.ai/integrations/raycast/muse-ember)
- [VS Code](https://spiral.ai/integrations/vscode/muse-ember)
- [Windsurf](https://spiral.ai/integrations/windsurf/muse-ember)
- [Zapier](https://spiral.ai/integrations/zapier/muse-ember)

## More Google Antigravity guides

- [Motif 3](https://spiral.ai/integrations/antigravity/motif-3)
- [Muse Glimmer 30B](https://spiral.ai/integrations/antigravity/muse-glimmer-30b)
- [Morph V3 Large (batch)](https://spiral.ai/integrations/antigravity/morph-v3-large-batch)
- [Muse Glimmer 30B (batch)](https://spiral.ai/integrations/antigravity/muse-glimmer-30b-batch)
- [Morph V3 Large](https://spiral.ai/integrations/antigravity/morph-v3-large)
- [Muse Spark 1.1](https://spiral.ai/integrations/antigravity/muse-spark-1-1)

## Questions about Muse Ember in Google Antigravity

**Can Google Antigravity use Muse Ember?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run Muse Ember like any built-in tool.

**How much does Muse Ember cost in Google Antigravity?**

Up to $0.002668 per run at the default inputs. $0.13 per 1M input tokens, $0.65 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Google Antigravity plan is separate.

**Do I need an OpenRouter account to use Muse Ember in Google Antigravity?**

No. Spiral runs Muse Ember on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Muse Ember in Google Antigravity?**

About two minutes: open the MCP config, then add the server, then sign in.

**Does Google Antigravity wait while Muse Ember runs?**

Muse Ember runs in the background. Google Antigravity starts the run, checks on it and gives you the text, json when it's ready.

**What is Muse Ember best suited for?**

Use it for focused work you repeat: coding subtasks, request routing, document summaries, and extracting information into a consistent structure.

**When should I choose Muse Spark or Muse Wonder instead?**

Meta recommends them for hard one-shot coding problems, knowledge-heavy questions, and visual coding. Give Muse Ember a narrower task when the broader problem needs those capabilities.

**How much text can Muse Ember handle?**

Meta documents a 1,048,576-token context window and up to 524,288 output tokens. Internal reasoning also consumes the output budget, so that maximum is not a promise of an equally long visible answer.

**Can Muse Ember return structured JSON?**

Yes. Use schema-constrained output for extraction and classification tasks that need a consistent JSON structure.

**How much reasoning should I use?**

Start with the lowest effort that passes your task checks. Leave enough output budget for both internal reasoning and the answer you need.

