mirror of
https://github.com/aljazceru/goose.git
synced 2025-12-18 14:44:21 +01:00
docs: restructure menu (#769)
This commit is contained in:
Angie Jones
@@ -1,172 +0,0 @@
|
||||
---
|
||||
sidebar_position: 2
|
||||
title: Managing Goose Extensions
|
||||
---
|
||||
|
||||
import Tabs from '@theme/Tabs';
|
||||
import TabItem from '@theme/TabItem';
|
||||
|
||||
Extensions are add-ons that provide a way to extend the functionality of Goose. They also provide a way to connect Goose with applications and tools you already use in your workflow. These extensions can be used to add new features, automate tasks, or integrate with other systems.
|
||||
|
||||
Extensions are based on the [Model Context Protocol (MCP)](https://github.com/modelcontextprotocol), so you can connect
|
||||
Goose to a wide ecosystem of capabilities.
|
||||
|
||||
|
||||
## Adding Extensions
|
||||
|
||||
You can add extensions to Goose through the CLI or the UI.
|
||||
|
||||
<Tabs groupId="interface">
|
||||
<TabItem value="cli" label="Goose CLI" default>
|
||||
|
||||
1. After the initial Goose setup, You can add extensions through the configuration system.
|
||||
|
||||
```
|
||||
goose configure
|
||||
```
|
||||
|
||||
2. Choose `Add Extension` to see the options.
|
||||
|
||||
You can also edit the config file directly, which is stored in `~/.config/goose/config.yaml`.
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="ui" label="Goose UI">
|
||||
1. Locate the menu (...) in the top right corner of the Goose UI.
|
||||
2. Select `Settings` from the menu.
|
||||
3. Under `Extensions`, you can add (+) a new extension manually,
|
||||
4. Or [`Browse Extensions`][extensions] to find curated extensions.
|
||||
5. Click 'Install' on extension you'd like to add and it installs right in the Goose app.
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
## Removing Extensions
|
||||
|
||||
You can remove extensions installed on Goose
|
||||
|
||||
<Tabs groupId="interface">
|
||||
<TabItem value="cli" label="Goose CLI" default>
|
||||
At the moment, you can remove extensions by editing the config file directly, which is stored in `~/.config/goose/config.yaml`.
|
||||
</TabItem>
|
||||
<TabItem value="ui" label="Goose UI">
|
||||
|
||||
1. Locate the menu (...) in the top right corner of the Goose UI.
|
||||
2. Select `Settings` from the menu.
|
||||
3. Under `Extensions`, find the extension you'd like to remove and click on the settings icon beside it.
|
||||
4. In the dialog that appears, click `Remove Extension`.
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
## Built-in Extensions
|
||||
Out of the box, Goose is installed with a few extensions out of the box but with only the `Developer` extension enabled by default.
|
||||
|
||||
Here are the default extensions:
|
||||
|
||||
1. **Developer**: The `Developer` extension provides a set of general development tools that are useful for software development.
|
||||
2. **Non-Developer**: The `Non-Developer` extension provides general computer control tools that don't require you to be a developer or engineer.
|
||||
3. **Memory**: The `Memory` extension teaches goose to remember your preferences as you use it
|
||||
4. **JetBrains**: The `JetBrains` extension provides an integration for working with JetBrains IDEs.
|
||||
5. **Google Drive**: The `Google Drive` extension provides an integration for working with Google Drive for file management and access.
|
||||
|
||||
|
||||
#### Toggling Built-in Extensions
|
||||
|
||||
<Tabs groupId="interface">
|
||||
<TabItem value="cli" label="Goose CLI" default>
|
||||
1. Run Goose configuration:
|
||||
|
||||
```bash
|
||||
goose configure
|
||||
```
|
||||
2. Choose `Add Extension`
|
||||
3. Choose `Built-in Extension`
|
||||
|
||||
Alternatively, you can enable a built-in extension by specifying its name in this command:
|
||||
|
||||
```
|
||||
goose mcp {name}
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="ui" label="Goose UI">
|
||||
1. Locate the menu (...) in the top right corner of the Goose UI.
|
||||
2. Select `Settings` from the menu.
|
||||
3. Under `Extensions`, you can toggle the built-in extensions on or off.
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
|
||||
:::tip
|
||||
All of Goose's built-in extensions are MCP servers in their own right. If you'd like
|
||||
to use the MCP servers included with Goose with any other agent, you are free to do so.
|
||||
:::
|
||||
|
||||
## MCP Servers
|
||||
|
||||
You can run any MCP server as a Goose extension.
|
||||
|
||||
<Tabs groupId="interface">
|
||||
<TabItem value="cli" label="Goose CLI" default>
|
||||
|
||||
1. Run `goose configure`
|
||||
2. Choose `Add Extension`
|
||||
3. Choose `Command-line Extension`
|
||||
|
||||
You'll then be prompted to enter a command and any environment variables needed. For example, to connect to the [Fetch Server](https://github.com/modelcontextprotocol/servers/tree/main/src/fetch), enter `uvx mcp-server-fetch` as the command.
|
||||
|
||||
You can also edit the resulting config entry directly, which would look like this:
|
||||
|
||||
```yaml
|
||||
extensions:
|
||||
fetch:
|
||||
name: fetch
|
||||
cmd: uvx
|
||||
args: [mcp-server-fetch]
|
||||
enabled: true
|
||||
envs: {}
|
||||
type: stdio
|
||||
```
|
||||
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="ui" label="Goose UI">
|
||||
|
||||
1. Locate the menu (...) in the top right corner of the Goose UI.
|
||||
2. Select `Settings` from the menu.
|
||||
3. Under `Extensions`, you can add a MCP server as an extension manually by clicking on the (+) button to the right.
|
||||
4. In the dialog that appears, enter the details of the MCP server including any environment variables needed.
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
|
||||
## Discovering Extensions
|
||||
|
||||
Goose comes with a [central directory][extensions] of extensions that you can install and use. You can install extensions from the Goose CLI or from the Goose GUI. The page will give you a test command to try out extensions, and if you want to keep them, you can add through `goose configure`.
|
||||
|
||||
You can test out an extension for a single session with
|
||||
|
||||
```sh
|
||||
goose session --with-extension "command to run"
|
||||
```
|
||||
|
||||
|
||||
## Starting a Session with Extensions
|
||||
|
||||
You can start a tailored goose session with specific extensions directly from the CLI. To do this, run the following command:
|
||||
|
||||
```bash
|
||||
goose session --with-extension "{extension command}"
|
||||
```
|
||||
|
||||
:::note
|
||||
You may need to set necessary environment variables for the extension to work correctly.
|
||||
```bash
|
||||
goose session --with-extension "VAR=value command arg1 arg2"
|
||||
```
|
||||
:::
|
||||
|
||||
## Developing Extensions
|
||||
Goose extensions are implemented with MCP - a system that allows AI models and agents to securely connect with local or remote resources using standard protocols. Learn how to build your own [extension as an MCP server](https://modelcontextprotocol.io/quickstart/server).
|
||||
|
||||
|
||||
[extensions]: https://block.github.io/goose/v1/extensions
|
||||
@@ -1,116 +0,0 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
---
|
||||
|
||||
import Tabs from '@theme/Tabs';
|
||||
import TabItem from '@theme/TabItem';
|
||||
|
||||
# Supported LLM Providers
|
||||
|
||||
You can use Goose with your preferred LLM. Goose supports a variety of LLM providers. To configure your chosen provider or see available options, run `goose configure` in the CLI or visit the `Provider Settings` page in the Goose UI.
|
||||
|
||||
<Tabs groupId="interface">
|
||||
<TabItem value="cli" label="Goose CLI" default>
|
||||
1. Run the following command:
|
||||
```sh
|
||||
goose configure
|
||||
```
|
||||
2. Select `Configure Providers` from the menu.
|
||||
|
||||
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="ui" label="Goose UI">
|
||||
**To update your LLM provider and API key:**
|
||||
|
||||
1. Click on the three dots in the top-right corner.
|
||||
2. Select `Provider Settings` from the menu.
|
||||
3. Click Edit, enter your API key, and click `Set as Active`.
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
## Available Providers
|
||||
|
||||
- OpenAI
|
||||
- Databricks
|
||||
- Ollama
|
||||
- Anthropic
|
||||
- Google Gemini
|
||||
- Groq
|
||||
- OpenRouter
|
||||
|
||||
|
||||
### OpenAI
|
||||
|
||||
OpenAI offers powerful language models that include GPT-4, GPT-3.5-turbo, and more.
|
||||
|
||||
1. Run the following command and choose "Configure Providers":
|
||||
```sh
|
||||
goose configure
|
||||
```
|
||||
2. Select `OpenAI` from the list of available providers.
|
||||
3. Enter your `OPENAI_API_KEY` when prompted, which you can obtain by registering at [OpenAI's platform](https://platform.openai.com/api-keys).
|
||||
|
||||
### Databricks
|
||||
|
||||
Databricks is a data analytics and AI platform that provides access to various AI models and tools. They offer integration with popular models and custom model deployment.
|
||||
|
||||
1. Run the following command and choose "Configure Providers":
|
||||
```sh
|
||||
goose configure
|
||||
```
|
||||
2. Select `Databricks` as your provider.
|
||||
3. Enter your `DATABRICKS_HOST` and `DATABRICKS_TOKEN`, which can be generated in your [Databricks Account Settings](https://www.databricks.com/).
|
||||
|
||||
### Ollama
|
||||
|
||||
Ollama is an open-source project that allows running large language models locally. It supports various open-source models and provides an API for integration.
|
||||
|
||||
1. Run the following command and choose "Configure Providers":
|
||||
```sh
|
||||
goose configure
|
||||
```
|
||||
2. Select `Ollama` and follow the steps to download and set up your models as detailed on [Ollama's site](https://ollama.com/). Requires `OLLAMA_HOST`.
|
||||
|
||||
### Anthropic
|
||||
|
||||
Anthropic is an AI research company that offers advanced language models through its API. Their primary model is Claude, which comes in various versions.
|
||||
|
||||
1. Run the following command and choose "Configure Providers":
|
||||
```sh
|
||||
goose configure
|
||||
```
|
||||
2. Choose `Anthropic` and provide the `ANTHROPIC_API_KEY`, obtainable via [Anthropic's platform](https://www.anthropic.com/).
|
||||
|
||||
### Google Gemini
|
||||
|
||||
Google Gemini is a suite of large language models developed by Google. It offers multimodal capabilities and can be accessed through the [Google AI Studio](https://ai.google.dev/gemini-api/docs).
|
||||
|
||||
1. Run the following command and choose "Configure Providers":
|
||||
```sh
|
||||
goose configure
|
||||
```
|
||||
2. Pick `Google Gemini` from the list of providers and input your `GOOGLE_API_KEY`. .
|
||||
|
||||
### Groq
|
||||
|
||||
Groq is an AI company that offers high-performance inference for large language models. They provide access to various models through their API.
|
||||
|
||||
1. Run the following command and choose "Configure Providers":
|
||||
```sh
|
||||
goose configure
|
||||
```
|
||||
2. Select `Groq` from the list of providers and input your `GROQ_API_KEY`, set up via the [Groq Console](https://groq.com/).
|
||||
|
||||
### OpenRouter
|
||||
|
||||
OpenRouter is a platform that provides access to multiple AI models from various providers through a single API. It simplifies the process of using different AI models in applications.
|
||||
|
||||
1. Run the following command and choose "Configure Providers":
|
||||
```sh
|
||||
goose configure
|
||||
```
|
||||
|
||||
2. Select `OpenRouter` from the list of providers and input your `OPENROUTER_API_KEY`, set up via the [OpenRouter Console](https://openrouter.ai/).
|
||||
|
||||
Reference in New Issue
Block a user