From 80451c45b7d5a83bbfbb381e4f896b137774a186 Mon Sep 17 00:00:00 2001 From: dprevoznik <58714078+dprevoznik@users.noreply.github.com> Date: Wed, 13 May 2026 20:31:00 +0000 Subject: [PATCH 1/2] docs: update Yutori integration to Navigator n1.5 Co-Authored-By: Claude Opus 4.7 --- changelog.mdx | 10 ++++++++++ integrations/computer-use/yutori.mdx | 16 ++++++++++------ integrations/overview.mdx | 2 +- 3 files changed, 21 insertions(+), 7 deletions(-) diff --git a/changelog.mdx b/changelog.mdx index abce5b2..686ffc4 100644 --- a/changelog.mdx +++ b/changelog.mdx @@ -9,6 +9,16 @@ import { YouTubeVideo } from '/snippets/youtube-video.mdx'; For API library updates, see the [Node SDK](https://github.com/onkernel/kernel-node-sdk/blob/main/CHANGELOG.md), [Python SDK](https://github.com/onkernel/kernel-python-sdk/blob/next/CHANGELOG.md), and [Go SDK](https://github.com/onkernel/kernel-go-sdk/blob/main/CHANGELOG.md) changelogs. + +## Product updates + +- Updated the [Yutori](/integrations/computer-use/yutori) `kernel create` template (TypeScript + Python) to Yutori's [Navigator n1.5](https://yutori.com/blog/introducing-n1-5) model. The template runs n1.5 in computer-use-only mode against the `browser_tools_core-20260403` tool set, picks up the new actions (`mouse_move`, `mouse_down`/`mouse_up`, `middle_click`, `hold_key`, `go_forward`, click `modifier`), and trims request payloads on long sessions to stay under the API ceiling. + +## Documentation updates + +- Updated the [Yutori](/integrations/computer-use/yutori) integration page to reference Navigator n1.5 and document the computer-use-only tool set used by the template. + + ## Product updates diff --git a/integrations/computer-use/yutori.mdx b/integrations/computer-use/yutori.mdx index 35077fc..5b898b4 100644 --- a/integrations/computer-use/yutori.mdx +++ b/integrations/computer-use/yutori.mdx @@ -2,13 +2,13 @@ title: "Yutori" --- -[n1](https://yutori.com/blog/introducing-n1) is Yutori's pixels-to-actions LLM that predicts browser actions from screenshots. This computer use model enables AI agents to interact with web interfaces by analyzing visual content and generating appropriate mouse and keyboard actions. +[Navigator n1.5](https://yutori.com/blog/introducing-n1-5) is Yutori's pixels-to-actions LLM that predicts browser actions from screenshots. This computer use model enables AI agents to interact with web interfaces by analyzing visual content and generating appropriate mouse and keyboard actions. -By integrating Yutori n1 with Kernel, you can run these AI-powered browser automations on cloud-hosted infrastructure, eliminating the need for local browser management and enabling scalable, reliable AI agents. +By integrating Yutori n1.5 with Kernel, you can run these AI-powered browser automations on cloud-hosted infrastructure, eliminating the need for local browser management and enabling scalable, reliable AI agents. ## Quick setup with our Yutori example app -Get started quickly with our Kernel app template that includes a pre-configured Yutori n1 integration: +Get started quickly with our Kernel app template that includes a pre-configured Yutori n1.5 integration: ```bash kernel create --name my-yutori-app --template yutori @@ -16,11 +16,15 @@ kernel create --name my-yutori-app --template yutori Choose `TypeScript` or `Python` as the programming language. +The template runs n1.5 in **computer-use-only mode**, using the `browser_tools_core-20260403` tool set for coordinate-based browser actions. The DOM/Playwright "expanded" tools (`extract_elements`, `find`, `set_element_value`, `execute_js`) are disabled because the template doesn't expose a Playwright page to the model. + +Yutori n1.5 recommends a **1280×800 (WXGA, 16:10)** viewport for best grounding accuracy. See [viewports](/browsers/viewport) for supported configurations. + Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Yutori automation on Kernel's infrastructure. -## Benefits of using Kernel with Yutori n1 +## Benefits of using Kernel with Yutori n1.5 -- **No local browser management**: Run n1 automations without installing or maintaining browsers locally +- **No local browser management**: Run n1.5 automations without installing or maintaining browsers locally - **Scalability**: Launch multiple browser sessions in parallel for concurrent AI agents - **Stealth mode**: Built-in anti-detection features for reliable web interactions - **Session state**: Maintain browser state across runs via [Profiles](/auth/profiles) @@ -33,4 +37,4 @@ Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to depl - Learn about [stealth mode](/browsers/bot-detection/stealth) for avoiding detection - Learn how to properly [terminate browser sessions](/browsers/termination) - Learn how to [deploy](/apps/deploy) your Yutori app to Kernel -- Read the [Yutori n1 API documentation](https://docs.yutori.com/reference/n1) for model details +- Read the [Yutori n1.5 API documentation](https://docs.yutori.com/reference/n1-5) for model details diff --git a/integrations/overview.mdx b/integrations/overview.mdx index ca7e727..6ad6c7b 100644 --- a/integrations/overview.mdx +++ b/integrations/overview.mdx @@ -35,7 +35,7 @@ Kernel provides detailed guides for popular agent frameworks: - **[Computer Use (OpenAI)](/integrations/computer-use/openai)** - OpenAI's computer use capability - **[Computer Use (Gemini)](/integrations/computer-use/gemini)** - Gemini's computer use capability - **[Computer Use (OpenAGI)](/integrations/computer-use/openagi)** - OpenAGI's computer use capability -- **[Computer Use (Yutori)](/integrations/computer-use/yutori)** - Yutori n1 pixels-to-actions model +- **[Computer Use (Yutori)](/integrations/computer-use/yutori)** - Yutori Navigator n1.5 pixels-to-actions model - **[Laminar](/integrations/laminar)** - Observability and tracing for AI browser automations - **[Magnitude](/integrations/magnitude)** - Vision-focused browser automation framework - **[Notte](/integrations/notte)** - AI agent framework for browser automation From 0ff627e011a6d032f4d4f3ccdabc28ea28bb4055 Mon Sep 17 00:00:00 2001 From: dprevoznik <58714078+dprevoznik@users.noreply.github.com> Date: Wed, 13 May 2026 20:51:22 +0000 Subject: [PATCH 2/2] remove changelog entry and template detail paragraphs Co-Authored-By: Claude Opus 4.7 --- changelog.mdx | 10 ---------- integrations/computer-use/yutori.mdx | 4 ---- 2 files changed, 14 deletions(-) diff --git a/changelog.mdx b/changelog.mdx index 686ffc4..abce5b2 100644 --- a/changelog.mdx +++ b/changelog.mdx @@ -9,16 +9,6 @@ import { YouTubeVideo } from '/snippets/youtube-video.mdx'; For API library updates, see the [Node SDK](https://github.com/onkernel/kernel-node-sdk/blob/main/CHANGELOG.md), [Python SDK](https://github.com/onkernel/kernel-python-sdk/blob/next/CHANGELOG.md), and [Go SDK](https://github.com/onkernel/kernel-go-sdk/blob/main/CHANGELOG.md) changelogs. - -## Product updates - -- Updated the [Yutori](/integrations/computer-use/yutori) `kernel create` template (TypeScript + Python) to Yutori's [Navigator n1.5](https://yutori.com/blog/introducing-n1-5) model. The template runs n1.5 in computer-use-only mode against the `browser_tools_core-20260403` tool set, picks up the new actions (`mouse_move`, `mouse_down`/`mouse_up`, `middle_click`, `hold_key`, `go_forward`, click `modifier`), and trims request payloads on long sessions to stay under the API ceiling. - -## Documentation updates - -- Updated the [Yutori](/integrations/computer-use/yutori) integration page to reference Navigator n1.5 and document the computer-use-only tool set used by the template. - - ## Product updates diff --git a/integrations/computer-use/yutori.mdx b/integrations/computer-use/yutori.mdx index 5b898b4..6f6e20a 100644 --- a/integrations/computer-use/yutori.mdx +++ b/integrations/computer-use/yutori.mdx @@ -16,10 +16,6 @@ kernel create --name my-yutori-app --template yutori Choose `TypeScript` or `Python` as the programming language. -The template runs n1.5 in **computer-use-only mode**, using the `browser_tools_core-20260403` tool set for coordinate-based browser actions. The DOM/Playwright "expanded" tools (`extract_elements`, `find`, `set_element_value`, `execute_js`) are disabled because the template doesn't expose a Playwright page to the model. - -Yutori n1.5 recommends a **1280×800 (WXGA, 16:10)** viewport for best grounding accuracy. See [viewports](/browsers/viewport) for supported configurations. - Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Yutori automation on Kernel's infrastructure. ## Benefits of using Kernel with Yutori n1.5