diff --git a/documentation/docs/getting-started/providers.md b/documentation/docs/getting-started/providers.md index 685959a732..8f12d25570 100644 --- a/documentation/docs/getting-started/providers.md +++ b/documentation/docs/getting-started/providers.md @@ -31,6 +31,7 @@ Goose is compatible with a wide range of LLM providers, allowing you to choose a | [GCP Vertex AI](https://cloud.google.com/vertex-ai) | Google Cloud's Vertex AI platform, supporting Gemini and Claude models. **Credentials must be [configured in advance](https://cloud.google.com/vertex-ai/docs/authentication).** | `GCP_PROJECT_ID`, `GCP_LOCATION` and optionally `GCP_MAX_RATE_LIMIT_RETRIES` (5), `GCP_MAX_OVERLOADED_RETRIES` (5), `GCP_INITIAL_RETRY_INTERVAL_MS` (5000), `GCP_BACKOFF_MULTIPLIER` (2.0), `GCP_MAX_RETRY_INTERVAL_MS` (320_000). | | [GitHub Copilot](https://docs.github.com/en/copilot/using-github-copilot/ai-models) | Access to GitHub Copilot's chat models including gpt-4o, o1, o3-mini, and Claude models. Uses device code authentication flow for secure access. | Uses GitHub device code authentication flow (no API key needed) | | [Groq](https://groq.com/) | High-performance inference hardware and tools for LLMs. | `GROQ_API_KEY` | +| [LiteLLM](https://docs.litellm.ai/docs/) | LiteLLM proxy supporting multiple models with automatic prompt caching and unified API access. | `LITELLM_HOST`, `LITELLM_BASE_PATH` (optional), `LITELLM_API_KEY` (optional), `LITELLM_CUSTOM_HEADERS` (optional), `LITELLM_TIMEOUT` (optional) | | [Ollama](https://ollama.com/) | Local model runner supporting Qwen, Llama, DeepSeek, and other open-source models. **Because this provider runs locally, you must first [download and run a model](#local-llms).** | `OLLAMA_HOST` | | [Ramalama](https://ramalama.ai/) | Local model using native [OCI](https://opencontainers.org/) container runtimes, [CNCF](https://www.cncf.io/) tools, and supporting models as OCI artifacts. Ramalama API an compatible alternative to Ollama and can be used with the Goose Ollama provider. Supports Qwen, Llama, DeepSeek, and other open-source models. **Because this provider runs locally, you must first [download and run a model](#local-llms).** | `OLLAMA_HOST` | | [OpenAI](https://platform.openai.com/api-keys) | Provides gpt-4o, o1, and other advanced language models. Also supports OpenAI-compatible endpoints (e.g., self-hosted LLaMA, vLLM, KServe). **o1-mini and o1-preview are not supported because Goose uses tool calling.** | `OPENAI_API_KEY`, `OPENAI_HOST` (optional), `OPENAI_ORGANIZATION` (optional), `OPENAI_PROJECT` (optional), `OPENAI_CUSTOM_HEADERS` (optional) | diff --git a/documentation/docs/guides/interactive-chat/index.md b/documentation/docs/guides/interactive-chat/index.md index fa7bb55174..370c77ec29 100644 --- a/documentation/docs/guides/interactive-chat/index.md +++ b/documentation/docs/guides/interactive-chat/index.md @@ -42,5 +42,10 @@ import styles from '@site/src/components/Card/styles.module.css'; description="MCP-UI servers return content that Goose Desktop renders as rich, embeddable UI." link="/blog/2025/08/11/mcp-ui-post-browser-world" /> + \ No newline at end of file diff --git a/documentation/docs/guides/recipes/session-recipes.md b/documentation/docs/guides/recipes/session-recipes.md index b1ae9fac8a..c678543115 100644 --- a/documentation/docs/guides/recipes/session-recipes.md +++ b/documentation/docs/guides/recipes/session-recipes.md @@ -456,15 +456,15 @@ You can turn your current Goose session into a reusable recipe that includes the - Share your recipe with Desktop users by copying the recipe URL from the recipe creation dialog. + Share your recipe with Desktop users by copying the recipe link: - To copy the recipe URL: - 1. [Open the recipe](#use-recipe) - 2. Click the button at the bottom of the app - 3. Click `View/Edit Recipe` - 4. Scroll down and copy the link + 1. Click the button in the top-left to open the sidebar + 2. Click `Recipes` in the sidebar + 3. Find your recipe in the Recipe Library + 4. Click `Preview` next to the recipe you want to share + 5. Under `Deeplink`, click `Copy` and then share the link with others - When someone clicks the URL, it will open Goose Desktop with your recipe configuration. They can also use your recipe URL to [import a recipe](/docs/guides/recipes/storing-recipes#storing-recipes) into their Recipe Library. + When someone clicks the link, it will open Goose Desktop with your recipe configuration. They can also use your recipe link to [import a recipe](/docs/guides/recipes/storing-recipes#storing-recipes) into their Recipe Library for future use. @@ -477,6 +477,10 @@ You can turn your current Goose session into a reusable recipe that includes the +:::info Privacy & Isolation +Each recipient gets their own private session when using your shared recipe. No data is shared between users, and your original session and recipe remain unaffected. +::: + ## Schedule Recipe diff --git a/documentation/src/components/DesktopProviderSetup.js b/documentation/src/components/DesktopProviderSetup.js index ba6cb5aada..0c77aea389 100644 --- a/documentation/src/components/DesktopProviderSetup.js +++ b/documentation/src/components/DesktopProviderSetup.js @@ -5,8 +5,8 @@ export const DesktopProviderSetup = () => { <>

On the welcome screen, choose how to configure a provider:

    -
  • OpenRouter (recommended) - One-click OAuth authentication provides instant access to multiple AI models with built-in rate limiting.
    • -
  • Ollama - Free local AI that runs privately on your computer. If needed, the setup flow will guide you through installing Ollama and downloading the recommended model.
    • +
  • Tetrate Agent Router - One-click OAuth authentication provides instant access to multiple AI models, starting credits, and built-in rate limiting.
    • +
  • OpenRouter - One-click OAuth authentication provides instant access to multiple AI models with built-in rate limiting.
  • Other Providers - Choose from ~20 supported providers including OpenAI, Anthropic, Google Gemini, and others through manual configuration. Be ready to provide your API key.