From f9361a8b24f80cb34bd48a5c1ba0f2c356dfbebe Mon Sep 17 00:00:00 2001 From: "tembo[bot]" <208362400+tembo-io[bot]@users.noreply.github.com> Date: Thu, 16 Oct 2025 14:21:59 +0000 Subject: [PATCH 1/6] docs: Add Gemini Computer Use integration page --- docs.json | 3 ++- integrations/computer-use/gemini.mdx | 31 ++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+), 1 deletion(-) create mode 100644 integrations/computer-use/gemini.mdx diff --git a/docs.json b/docs.json index 2cf7c40..1809c35 100644 --- a/docs.json +++ b/docs.json @@ -105,7 +105,8 @@ "group": "Computer Use", "pages": [ "integrations/computer-use/anthropic", - "integrations/computer-use/openai" + "integrations/computer-use/openai", + "integrations/computer-use/gemini" ] }, "integrations/magnitude", diff --git a/integrations/computer-use/gemini.mdx b/integrations/computer-use/gemini.mdx new file mode 100644 index 0000000..68de633 --- /dev/null +++ b/integrations/computer-use/gemini.mdx @@ -0,0 +1,31 @@ +--- +title: "Gemini" +--- + +[Gemini 2.5 Computer Use](https://ai.google.dev/gemini-api/docs/multimodal-agents) is Google's powerful capability that enables AI models to interact with computers through screen observation, cursor control, and keyboard input. This feature allows AI agents to autonomously navigate websites, interact with web applications, and perform complex multi-step tasks. + +By integrating Gemini 2.5 Computer Use with Kernel (via Stagehand), 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 example template + +Get started quickly with our TypeScript template that demonstrates Gemini 2.5 Computer Use with Kernel: + +Check out the [ts-stagehand-google-cua-agent](https://github.com/onkernel/ts-stagehand-google-cua-agent) repository for a complete working example that shows how to: +- Set up Gemini 2.5 Computer Use with Kernel +- Use Stagehand for browser automation +- Run AI-powered web interactions on cloud infrastructure + +## Benefits of using Kernel with Gemini Computer Use + +- **No local browser management**: Run Computer Use automations without installing or maintaining browsers locally +- **Scalability**: Launch multiple browser sessions in parallel for concurrent automations +- **Stealth mode**: Built-in anti-detection features for web interactions +- **Session persistence**: Maintain browser state across automation runs +- **Live view**: Debug your automations with real-time browser viewing + +## Next steps + +- Check out [live view](/browsers/live-view) for debugging your automations +- Learn about [stealth mode](/browsers/stealth) for avoiding detection +- Learn how to properly [terminate browser sessions](/browsers/termination) +- Learn how to [deploy](/apps/deploy) your Computer Use app to Kernel From 8c9c892ec9f1f16f540278ea264a46381ec0e5b4 Mon Sep 17 00:00:00 2001 From: "tembo[bot]" <208362400+tembo-io[bot]@users.noreply.github.com> Date: Thu, 16 Oct 2025 14:31:04 +0000 Subject: [PATCH 2/6] docs(gemini): update description with official link and wording --- integrations/computer-use/gemini.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/integrations/computer-use/gemini.mdx b/integrations/computer-use/gemini.mdx index 68de633..33dd1a2 100644 --- a/integrations/computer-use/gemini.mdx +++ b/integrations/computer-use/gemini.mdx @@ -2,7 +2,7 @@ title: "Gemini" --- -[Gemini 2.5 Computer Use](https://ai.google.dev/gemini-api/docs/multimodal-agents) is Google's powerful capability that enables AI models to interact with computers through screen observation, cursor control, and keyboard input. This feature allows AI agents to autonomously navigate websites, interact with web applications, and perform complex multi-step tasks. +Google's [Gemini 2.5 Computer Use model](https://blog.google/technology/google-deepmind/gemini-computer-use-model/) is a specialized model built on Gemini 2.5 Pro's capabilities to power agents that can interact with user interfaces. By integrating Gemini 2.5 Computer Use with Kernel (via Stagehand), 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. From d532184f54e037bdbedcbc756e990da7b1e6ad86 Mon Sep 17 00:00:00 2001 From: "tembo[bot]" <208362400+tembo-io[bot]@users.noreply.github.com> Date: Thu, 16 Oct 2025 14:36:00 +0000 Subject: [PATCH 3/6] docs(gemini): improve punctuation in setup section --- integrations/computer-use/gemini.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/integrations/computer-use/gemini.mdx b/integrations/computer-use/gemini.mdx index 33dd1a2..1163deb 100644 --- a/integrations/computer-use/gemini.mdx +++ b/integrations/computer-use/gemini.mdx @@ -8,9 +8,9 @@ By integrating Gemini 2.5 Computer Use with Kernel (via Stagehand), you can run ## Quick setup with our example template -Get started quickly with our TypeScript template that demonstrates Gemini 2.5 Computer Use with Kernel: +Get started quickly with our TypeScript template that demonstrates Gemini 2.5 Computer Use with Kernel. -Check out the [ts-stagehand-google-cua-agent](https://github.com/onkernel/ts-stagehand-google-cua-agent) repository for a complete working example that shows how to: +Check out the [ts-stagehand-google-cua-agent](https://github.com/onkernel/ts-stagehand-google-cua-agent) repository for a complete working example that shows how to - Set up Gemini 2.5 Computer Use with Kernel - Use Stagehand for browser automation - Run AI-powered web interactions on cloud infrastructure From 926e30b660c66a4d2c15a5771569059c38f6b476 Mon Sep 17 00:00:00 2001 From: "tembo[bot]" <208362400+tembo-io[bot]@users.noreply.github.com> Date: Thu, 16 Oct 2025 14:39:05 +0000 Subject: [PATCH 4/6] docs: reorder computer use pages alphabetically in sidebar --- docs.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs.json b/docs.json index 1809c35..a7ee85c 100644 --- a/docs.json +++ b/docs.json @@ -105,8 +105,8 @@ "group": "Computer Use", "pages": [ "integrations/computer-use/anthropic", - "integrations/computer-use/openai", - "integrations/computer-use/gemini" + "integrations/computer-use/gemini", + "integrations/computer-use/openai" ] }, "integrations/magnitude", From 0ca1ee1dc905493cdc5207f2262d68d504d1fc22 Mon Sep 17 00:00:00 2001 From: "tembo[bot]" <208362400+tembo-io[bot]@users.noreply.github.com> Date: Thu, 16 Oct 2025 14:41:02 +0000 Subject: [PATCH 5/6] Tembo Commit --- integrations/computer-use/gemini.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/integrations/computer-use/gemini.mdx b/integrations/computer-use/gemini.mdx index 1163deb..612e081 100644 --- a/integrations/computer-use/gemini.mdx +++ b/integrations/computer-use/gemini.mdx @@ -4,7 +4,7 @@ title: "Gemini" Google's [Gemini 2.5 Computer Use model](https://blog.google/technology/google-deepmind/gemini-computer-use-model/) is a specialized model built on Gemini 2.5 Pro's capabilities to power agents that can interact with user interfaces. -By integrating Gemini 2.5 Computer Use with Kernel (via Stagehand), 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 Gemini 2.5 Computer Use 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 example template From b9e8a95bfd7f11f8e6e48349bdd80cf4d0f7412d Mon Sep 17 00:00:00 2001 From: "tembo[bot]" <208362400+tembo-io[bot]@users.noreply.github.com> Date: Thu, 16 Oct 2025 14:46:16 +0000 Subject: [PATCH 6/6] docs(gemini): update link text to Open-source Gemini Template --- integrations/computer-use/gemini.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/integrations/computer-use/gemini.mdx b/integrations/computer-use/gemini.mdx index 612e081..8917023 100644 --- a/integrations/computer-use/gemini.mdx +++ b/integrations/computer-use/gemini.mdx @@ -10,7 +10,7 @@ By integrating Gemini 2.5 Computer Use with Kernel, you can run these AI-powered Get started quickly with our TypeScript template that demonstrates Gemini 2.5 Computer Use with Kernel. -Check out the [ts-stagehand-google-cua-agent](https://github.com/onkernel/ts-stagehand-google-cua-agent) repository for a complete working example that shows how to +Check out the [Open-source Gemini Template](https://github.com/onkernel/ts-stagehand-google-cua-agent) repository for a complete working example that shows how to: - Set up Gemini 2.5 Computer Use with Kernel - Use Stagehand for browser automation - Run AI-powered web interactions on cloud infrastructure