> ## Documentation Index
> Fetch the complete documentation index at: https://docs.memanto.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Goose Integration

> Give the Goose AI agent persistent, cross-session memory with Memanto — via the CLI connector or as an MCP extension.

# Goose + Memanto

<img src="https://mintcdn.com/memanto/7cqii5_wGejS32un/logo/integrations/goose.svg?fit=max&auto=format&n=7cqii5_wGejS32un&q=85&s=495d6933959b13b92c181d7e722458cd" alt="Goose" width="64" style={{marginBottom: "1.5rem"}} data-path="logo/integrations/goose.svg" />

Connect the [Goose](https://block.github.io/goose/) AI agent to Memanto so it can store and recall persistent memory across sessions.

## Connect via CLI (recommended)

```bash theme={null}
memanto connect goose
```

This installs a Goose-specific instruction file and the `memanto-memory` skill into your project. Add `--global` to install system-wide:

```bash theme={null}
memanto connect goose --global
```

## Connect via MCP

Goose speaks MCP, so you can alternatively register Memanto as an extension. Edit `~/.config/goose/config.yaml`:

```yaml theme={null}
extensions:
  memanto:
    type: stdio
    command: memanto-mcp
    envs:
      MOORCHEH_API_KEY: mch_xxxxxxxxxxxxxxxxxx
      MEMANTO_DEFAULT_AGENT_ID: goose-workspace
```

See the [MCP integration guide](/integrations/mcp) for the full server reference.

## Next Steps

* [CLI: connect command](/cli/connect/connect)
* [MCP Integration](/integrations/mcp)
* [Memory Types Reference](/reference/memory-types)