From 9851ddd78bbad777774f0d3ffa18e85fd9d373c1 Mon Sep 17 00:00:00 2001 From: Kunchala Hema Sai Venkat Chandra Kumar <72931765+hemachandra666@users.noreply.github.com> Date: Mon, 27 Apr 2026 16:16:14 -0400 Subject: [PATCH 1/8] Add files via upload docs(get-started): add Brev web UI quickstart guide --- docs/get-started/brev-web-ui-quickstart.md | 196 +++++++++++++++++++++ 1 file changed, 196 insertions(+) create mode 100644 docs/get-started/brev-web-ui-quickstart.md diff --git a/docs/get-started/brev-web-ui-quickstart.md b/docs/get-started/brev-web-ui-quickstart.md new file mode 100644 index 0000000000..54a0b8a614 --- /dev/null +++ b/docs/get-started/brev-web-ui-quickstart.md @@ -0,0 +1,196 @@ +# Get Started with NemoClaw on Brev (Web UI) + +Run a sandboxed NemoClaw agent in minutes using the Brev web interface. +No CLI installation, no local setup, no GPU required on your machine. + +> **Note:** This guide covers the Brev web UI flow, which is the fastest +> way to try NemoClaw. If you prefer the CLI-based remote deployment, +> see [Deploy to a Remote GPU Instance](deploy-to-remote-gpu.md). + +## Prerequisites + +- A free Brev account at [brev.nvidia.com](https://brev.nvidia.com) +- A free NVIDIA API key from [build.nvidia.com](https://build.nvidia.com) + +That's it. No local software installation needed. + +## Step 1: Get Your NVIDIA API Key + +1. Go to [build.nvidia.com](https://build.nvidia.com) +2. Sign in or create a free account +3. Click your profile icon in the top right +4. Select **API Keys** +5. Click **Generate API Key** +6. Copy the key -- it starts with `nvapi-` + +Keep this key ready for the next step. + +## Step 2: Deploy NemoClaw on Brev + +1. Go to [brev.nvidia.com](https://brev.nvidia.com) and sign in +2. On the **GPUs** page, look for the banner: + **"Your agents are waiting. Meet NemoClaw"** +3. Click **Try NemoClaw** +4. You will see the NemoClaw setup page showing: + - Instance type: CPU (4 CPUs, 16 GiB RAM) + - Cloud Provider: GCP + - Cost: $0.18/hr +5. Click **Deploy NemoClaw** + +## Step 3: Configure Your Agent (3 Steps) + +### Step 1 of 3 -- Connect to AI + +- **NVIDIA Cloud** is selected by default (recommended) +- This uses Nemotron-3-Super-120B hosted by NVIDIA +- Paste your `nvapi-` API key in the field +- Click **Create Agent** + +> **Other providers available:** OpenAI, Anthropic, Google Gemini, +> Local Ollama. Click "Show Other Providers" to see all options. + +### Step 2 of 3 -- Setup + +NemoClaw automatically: +- Provisions a secure Linux VM on GCP +- Installs Docker and the OpenShell runtime +- Sets up the sandboxed agent environment +- Configures inference routing to NVIDIA Cloud + +This takes approximately 2-3 minutes. + +### Step 3 of 3 -- Launch + +When setup completes you will see: + +``` +AGENT CREATED SUCCESSFULLY +Your agent is running in a secure sandbox and ready to use. + +Agent: agent +Model: nemotron-3-super-120b +Provider: NVIDIA Cloud +``` + +Click **Chat With Agent** to open the OpenClaw Gateway Dashboard. + +## Step 4: Understand the Dashboard + +The OpenClaw Gateway Dashboard has the following sections: + +**Chat** +Direct chat interface for talking to your agent. This is where +you start. The agent reads your workspace files and responds +using Nemotron-3-Super-120B via NVIDIA Cloud. + +**Control** +- **Overview** -- Agent health and status +- **Channels** -- Connect to Slack, Telegram, or Discord +- **Instances** -- Running agent instances +- **Sessions** -- Conversation history +- **Usage** -- Token and API usage +- **Cron Jobs** -- Schedule recurring agent tasks + +**Agent** +- **Agents** -- Manage agent profiles +- **Skills** -- Add new capabilities to your agent +- **Nodes** -- Multi-agent node configuration + +**Settings** +- **Config** -- Agent configuration +- **Debug** -- Debug logs and diagnostics + +## Step 5: Have Your First Conversation + +In the Chat box, type: + +``` +Hello! What can you do for me? What skills do you have available? +``` + +The agent will read its workspace files and introduce itself. +By default it has three skills available: + +- **Weather** -- Get current weather and forecasts +- **Healthcheck** -- Security audit and hardening +- **Skill-Creator** -- Create new custom skills + +## Step 6: Tell the Agent Who You Are + +The agent starts with an empty USER.md file -- it knows nothing +about you. Update it so the agent can personalize its responses. + +In the chat, type: + +``` +Please update my USER.md file with the following: +Name: [your name] +Timezone: [your timezone, e.g. EST] +Notes: [what you are working on] +``` + +The agent will write this to your workspace so it remembers +you across sessions. + +## Step 7: Stop Your Instance When Done + +To avoid unnecessary charges, stop your instance when you are +finished experimenting. + +1. Go back to [brev.nvidia.com](https://brev.nvidia.com) +2. Click **GPUs** in the nav bar +3. Find your NemoClaw instance +4. Click **Stop** + +At $0.18/hr, a 3-hour session costs approximately $0.54. + +## What to Try Next + +Now that your agent is running, explore these capabilities: + +**Connect a messaging channel** +Go to **Channels** in the dashboard to connect your agent +to Telegram, Slack, or Discord so it can message you proactively. + +**Add a new skill** +Go to **Skills** and browse available skills, or use the +built-in Skill-Creator to build your own custom skill. + +**Schedule a recurring task** +Go to **Cron Jobs** to set up tasks the agent runs automatically, +such as a daily email check or calendar reminder. + +**Use a different AI model** +The agent supports switching inference providers at runtime. +See [Switch Inference Providers](../inference/switch-inference-providers.md) +for instructions. + +## Troubleshooting + +**The Deploy NemoClaw button is not visible** +Make sure you are signed in to brev.nvidia.com. The banner +appears on the GPUs page. If you do not see it, try refreshing +the page or navigating directly to the NemoClaw tab in the +top navigation. + +**API key not accepted** +Make sure your key starts with `nvapi-` and was copied in full. +Keys from build.nvidia.com are free and do not require a paid plan. + +**Agent takes more than 5 minutes to deploy** +This can happen during periods of high demand on Brev. +The Cloudflare quota warning at the top of the Brev page +("Secure Links and Tunnels may not be created successfully") +may affect deployment time. Try again after a few minutes. + +**OpenClaw dashboard shows a blank chat** +This is normal on first launch. The agent reads its workspace +files during the first session startup. Type a message and +wait a few seconds for the first response. + +## Related Topics + +- [Quickstart](../get-started/quickstart.md) -- CLI-based local setup +- [Deploy to a Remote GPU Instance](deploy-to-remote-gpu.md) -- CLI-based Brev deployment +- [Set Up the Telegram Bridge](set-up-telegram-bridge.md) +- [Monitor Sandbox Activity](../monitoring/monitor-sandbox-activity.md) From 16b54143b82ea73c78165d7ccfd81f094e04f06b Mon Sep 17 00:00:00 2001 From: Kunchala Hema Sai Venkat Chandra Kumar <72931765+hemachandra666@users.noreply.github.com> Date: Mon, 27 Apr 2026 16:56:12 -0400 Subject: [PATCH 2/8] Revise NemoClaw quickstart guide for Brev web UI Updated the quickstart guide for NemoClaw on Brev web UI, improving formatting and clarity. --- docs/get-started/brev-web-ui-quickstart.md | 230 +++++++++++---------- 1 file changed, 122 insertions(+), 108 deletions(-) diff --git a/docs/get-started/brev-web-ui-quickstart.md b/docs/get-started/brev-web-ui-quickstart.md index 54a0b8a614..1d224662ec 100644 --- a/docs/get-started/brev-web-ui-quickstart.md +++ b/docs/get-started/brev-web-ui-quickstart.md @@ -1,69 +1,88 @@ +--- +title: Get Started with NemoClaw on Brev (Web UI) +description: Run a sandboxed NemoClaw agent in minutes using the Brev web interface with no CLI installation or local setup required. +keywords: NemoClaw, Brev, OpenClaw, getting started, quickstart, web UI, NVIDIA Cloud, Nemotron +topics: [NemoClaw, Brev, OpenClaw, deployment] +tags: [getting-started, brev, web-ui, nemoclaw] +content_type: tutorial +difficulty: beginner +audience: developers +status: published +--- + + + # Get Started with NemoClaw on Brev (Web UI) Run a sandboxed NemoClaw agent in minutes using the Brev web interface. No CLI installation, no local setup, no GPU required on your machine. -> **Note:** This guide covers the Brev web UI flow, which is the fastest -> way to try NemoClaw. If you prefer the CLI-based remote deployment, -> see [Deploy to a Remote GPU Instance](deploy-to-remote-gpu.md). +:::{note} +This guide covers the Brev web UI flow, which is the fastest way to try NemoClaw. +If you prefer the CLI-based remote deployment, see [Deploy to a Remote GPU Instance](../deployment/deploy-to-remote-gpu.md). +::: ## Prerequisites - A free Brev account at [brev.nvidia.com](https://brev.nvidia.com) - A free NVIDIA API key from [build.nvidia.com](https://build.nvidia.com) -That's it. No local software installation needed. +No local software installation is needed. -## Step 1: Get Your NVIDIA API Key +## Get Your NVIDIA API Key -1. Go to [build.nvidia.com](https://build.nvidia.com) -2. Sign in or create a free account -3. Click your profile icon in the top right -4. Select **API Keys** -5. Click **Generate API Key** -6. Copy the key -- it starts with `nvapi-` +1. Go to [build.nvidia.com](https://build.nvidia.com). +2. Sign in or create a free account. +3. Click your profile icon in the top right. +4. Select **API Keys**. +5. Click **Generate API Key**. +6. Copy the key -- it starts with `nvapi-`. Keep this key ready for the next step. -## Step 2: Deploy NemoClaw on Brev +## Deploy NemoClaw on Brev -1. Go to [brev.nvidia.com](https://brev.nvidia.com) and sign in -2. On the **GPUs** page, look for the banner: - **"Your agents are waiting. Meet NemoClaw"** -3. Click **Try NemoClaw** -4. You will see the NemoClaw setup page showing: +1. Go to [brev.nvidia.com](https://brev.nvidia.com) and sign in. +2. On the **GPUs** page, look for the banner: **"Your agents are waiting. Meet NemoClaw"**. +3. Click **Try NemoClaw**. +4. The NemoClaw setup page shows the following: - Instance type: CPU (4 CPUs, 16 GiB RAM) - Cloud Provider: GCP - Cost: $0.18/hr -5. Click **Deploy NemoClaw** +5. Click **Deploy NemoClaw**. + +## Configure Your Agent + +NemoClaw walks you through three configuration steps. -## Step 3: Configure Your Agent (3 Steps) +### Connect to AI -### Step 1 of 3 -- Connect to AI +- **NVIDIA Cloud** is selected by default (recommended). +- This uses Nemotron-3-Super-120B hosted by NVIDIA. +- Paste your `nvapi-` API key in the field. +- Click **Create Agent**. -- **NVIDIA Cloud** is selected by default (recommended) -- This uses Nemotron-3-Super-120B hosted by NVIDIA -- Paste your `nvapi-` API key in the field -- Click **Create Agent** +:::{note} +Other providers are available: OpenAI, Anthropic, Google Gemini, and Local Ollama. +Click **Show Other Providers** to see all options. +::: -> **Other providers available:** OpenAI, Anthropic, Google Gemini, -> Local Ollama. Click "Show Other Providers" to see all options. +### Setup -### Step 2 of 3 -- Setup +NemoClaw automatically performs the following: -NemoClaw automatically: -- Provisions a secure Linux VM on GCP -- Installs Docker and the OpenShell runtime -- Sets up the sandboxed agent environment -- Configures inference routing to NVIDIA Cloud +- Provisions a secure Linux VM on GCP. +- Installs Docker and the OpenShell runtime. +- Sets up the sandboxed agent environment. +- Configures inference routing to NVIDIA Cloud. This takes approximately 2-3 minutes. -### Step 3 of 3 -- Launch +### Launch -When setup completes you will see: +When setup completes, the following confirmation appears: -``` +```text AGENT CREATED SUCCESSFULLY Your agent is running in a secure sandbox and ready to use. @@ -74,123 +93,118 @@ Provider: NVIDIA Cloud Click **Chat With Agent** to open the OpenClaw Gateway Dashboard. -## Step 4: Understand the Dashboard +## Understand the Dashboard -The OpenClaw Gateway Dashboard has the following sections: +The OpenClaw Gateway Dashboard has the following sections. -**Chat** -Direct chat interface for talking to your agent. This is where -you start. The agent reads your workspace files and responds -using Nemotron-3-Super-120B via NVIDIA Cloud. +**Chat.** +Direct chat interface for talking to your agent. +This is where you start. +The agent reads your workspace files and responds using Nemotron-3-Super-120B via NVIDIA Cloud. -**Control** -- **Overview** -- Agent health and status -- **Channels** -- Connect to Slack, Telegram, or Discord -- **Instances** -- Running agent instances -- **Sessions** -- Conversation history -- **Usage** -- Token and API usage -- **Cron Jobs** -- Schedule recurring agent tasks +**Control.** -**Agent** -- **Agents** -- Manage agent profiles -- **Skills** -- Add new capabilities to your agent -- **Nodes** -- Multi-agent node configuration +- **Overview** -- Agent health and status. +- **Channels** -- Connect to Slack, Telegram, or Discord. +- **Instances** -- Running agent instances. +- **Sessions** -- Conversation history. +- **Usage** -- Token and API usage. +- **Cron Jobs** -- Schedule recurring agent tasks. -**Settings** -- **Config** -- Agent configuration -- **Debug** -- Debug logs and diagnostics +**Agent.** -## Step 5: Have Your First Conversation +- **Agents** -- Manage agent profiles. +- **Skills** -- Add new capabilities to your agent. +- **Nodes** -- Multi-agent node configuration. -In the Chat box, type: +**Settings.** -``` +- **Config** -- Agent configuration. +- **Debug** -- Debug logs and diagnostics. + +## Have Your First Conversation + +In the Chat box, type the following: + +```text Hello! What can you do for me? What skills do you have available? ``` -The agent will read its workspace files and introduce itself. +The agent reads its workspace files and introduces itself. By default it has three skills available: -- **Weather** -- Get current weather and forecasts -- **Healthcheck** -- Security audit and hardening -- **Skill-Creator** -- Create new custom skills +- **Weather** -- Get current weather and forecasts. +- **Healthcheck** -- Security audit and hardening. +- **Skill-Creator** -- Create new custom skills. -## Step 6: Tell the Agent Who You Are +## Tell the Agent Who You Are -The agent starts with an empty USER.md file -- it knows nothing -about you. Update it so the agent can personalize its responses. +The agent starts with an empty `USER.md` file -- it knows nothing about you. +Update it so the agent personalizes its responses. -In the chat, type: +In the chat, type the following: -``` +```text Please update my USER.md file with the following: Name: [your name] Timezone: [your timezone, e.g. EST] Notes: [what you are working on] ``` -The agent will write this to your workspace so it remembers -you across sessions. +The agent writes this to your workspace so it remembers you across sessions. -## Step 7: Stop Your Instance When Done +## Stop Your Instance When Done -To avoid unnecessary charges, stop your instance when you are -finished experimenting. +To avoid unnecessary charges, stop your instance when you are finished experimenting. -1. Go back to [brev.nvidia.com](https://brev.nvidia.com) -2. Click **GPUs** in the nav bar -3. Find your NemoClaw instance -4. Click **Stop** +1. Go back to [brev.nvidia.com](https://brev.nvidia.com). +2. Click **GPUs** in the nav bar. +3. Find your NemoClaw instance. +4. Click **Stop**. At $0.18/hr, a 3-hour session costs approximately $0.54. ## What to Try Next -Now that your agent is running, explore these capabilities: +Now that your agent is running, explore these capabilities. -**Connect a messaging channel** -Go to **Channels** in the dashboard to connect your agent -to Telegram, Slack, or Discord so it can message you proactively. +**Connect a messaging channel.** +Go to **Channels** in the dashboard to connect your agent to Telegram, Slack, or Discord so it can message you proactively. -**Add a new skill** -Go to **Skills** and browse available skills, or use the -built-in Skill-Creator to build your own custom skill. +**Add a new skill.** +Go to **Skills** and browse available skills, or use the built-in Skill-Creator to build a custom skill. -**Schedule a recurring task** -Go to **Cron Jobs** to set up tasks the agent runs automatically, -such as a daily email check or calendar reminder. +**Schedule a recurring task.** +Go to **Cron Jobs** to set up tasks the agent runs automatically, such as a daily email check or calendar reminder. -**Use a different AI model** +**Use a different AI model.** The agent supports switching inference providers at runtime. -See [Switch Inference Providers](../inference/switch-inference-providers.md) -for instructions. +See [Switch Inference Providers](../inference/switch-inference-providers.md) for instructions. ## Troubleshooting -**The Deploy NemoClaw button is not visible** -Make sure you are signed in to brev.nvidia.com. The banner -appears on the GPUs page. If you do not see it, try refreshing -the page or navigating directly to the NemoClaw tab in the -top navigation. +**The Deploy NemoClaw button is not visible.** +Make sure you are signed in to `brev.nvidia.com`. +The banner appears on the GPUs page. +If you do not see it, try refreshing the page or navigating directly to the NemoClaw tab in the top navigation. -**API key not accepted** +**API key not accepted.** Make sure your key starts with `nvapi-` and was copied in full. -Keys from build.nvidia.com are free and do not require a paid plan. +Keys from `build.nvidia.com` are free and do not require a paid plan. -**Agent takes more than 5 minutes to deploy** +**Agent takes more than 5 minutes to deploy.** This can happen during periods of high demand on Brev. -The Cloudflare quota warning at the top of the Brev page -("Secure Links and Tunnels may not be created successfully") -may affect deployment time. Try again after a few minutes. +The Cloudflare quota warning at the top of the Brev page may affect deployment time. +Try again after a few minutes. -**OpenClaw dashboard shows a blank chat** -This is normal on first launch. The agent reads its workspace -files during the first session startup. Type a message and -wait a few seconds for the first response. +**OpenClaw dashboard shows a blank chat.** +This is normal on first launch. +The agent reads its workspace files during the first session startup. +Type a message and wait a few seconds for the first response. -## Related Topics +## Next Steps -- [Quickstart](../get-started/quickstart.md) -- CLI-based local setup -- [Deploy to a Remote GPU Instance](deploy-to-remote-gpu.md) -- CLI-based Brev deployment -- [Set Up the Telegram Bridge](set-up-telegram-bridge.md) +- [Quickstart](quickstart.md) -- CLI-based local setup. +- [Deploy to a Remote GPU Instance](../deployment/deploy-to-remote-gpu.md) -- CLI-based Brev deployment. +- [Set Up the Telegram Bridge](../deployment/set-up-telegram-bridge.md) - [Monitor Sandbox Activity](../monitoring/monitor-sandbox-activity.md) From 0971a6b678e04e60264eb71b72f8a2f36e9aae5e Mon Sep 17 00:00:00 2001 From: Kunchala Hema Sai Venkat Chandra Kumar <72931765+hemachandra666@users.noreply.github.com> Date: Tue, 28 Apr 2026 19:50:42 -0400 Subject: [PATCH 3/8] docs(get-started): update Brev web UI quickstart to follow style guide - Updated frontmatter to match NVIDIA template format - Fixed SPDX license header to correct NVIDIA format - Removed step numbering from headings - Fixed future tense to present tense throughout - Added code block language labels - Changed Related Topics to Next Steps - Fixed gateway and sandbox capitalization Signed-off-by: Kunchala Hema Sai Venkat Chandra Kumar --- docs/get-started/brev-web-ui-quickstart.md | 34 +++++++++++++--------- 1 file changed, 21 insertions(+), 13 deletions(-) diff --git a/docs/get-started/brev-web-ui-quickstart.md b/docs/get-started/brev-web-ui-quickstart.md index 1d224662ec..36b1a850a1 100644 --- a/docs/get-started/brev-web-ui-quickstart.md +++ b/docs/get-started/brev-web-ui-quickstart.md @@ -1,21 +1,29 @@ --- -title: Get Started with NemoClaw on Brev (Web UI) -description: Run a sandboxed NemoClaw agent in minutes using the Brev web interface with no CLI installation or local setup required. -keywords: NemoClaw, Brev, OpenClaw, getting started, quickstart, web UI, NVIDIA Cloud, Nemotron -topics: [NemoClaw, Brev, OpenClaw, deployment] -tags: [getting-started, brev, web-ui, nemoclaw] -content_type: tutorial -difficulty: beginner -audience: developers +title: + page: "Get Started with NemoClaw on Brev (Web UI)" + nav: "Brev Web UI" +description: + main: "Run a sandboxed NemoClaw agent in minutes using the Brev web interface with no CLI installation or local setup required." + agent: "Guides users through deploying NemoClaw using the Brev web UI. Use when a user wants to try NemoClaw without installing the CLI, or asks how to get started on Brev." +keywords: ["nemoclaw brev web ui", "nemoclaw getting started", "brev quickstart", "nvidia nemotron agent"] +topics: ["generative_ai", "ai_agents"] +tags: ["brev", "openclaw", "getting-started", "web-ui", "nemoclaw"] +content: + type: get_started + difficulty: technical_beginner + audience: ["developer", "engineer"] status: published --- - + # Get Started with NemoClaw on Brev (Web UI) Run a sandboxed NemoClaw agent in minutes using the Brev web interface. -No CLI installation, no local setup, no GPU required on your machine. +No CLI installation, no local setup, and no GPU required on your machine. :::{note} This guide covers the Brev web UI flow, which is the fastest way to try NemoClaw. @@ -91,11 +99,11 @@ Model: nemotron-3-super-120b Provider: NVIDIA Cloud ``` -Click **Chat With Agent** to open the OpenClaw Gateway Dashboard. +Click **Chat With Agent** to open the OpenClaw gateway dashboard. ## Understand the Dashboard -The OpenClaw Gateway Dashboard has the following sections. +The OpenClaw gateway dashboard has the following sections. **Chat.** Direct chat interface for talking to your agent. @@ -204,7 +212,7 @@ Type a message and wait a few seconds for the first response. ## Next Steps +- [Prerequisites](prerequisites.md) -- System requirements before getting started. - [Quickstart](quickstart.md) -- CLI-based local setup. - [Deploy to a Remote GPU Instance](../deployment/deploy-to-remote-gpu.md) -- CLI-based Brev deployment. -- [Set Up the Telegram Bridge](../deployment/set-up-telegram-bridge.md) - [Monitor Sandbox Activity](../monitoring/monitor-sandbox-activity.md) From d1c96ed193a55723faa63d6aa8bfd248c6a3605d Mon Sep 17 00:00:00 2001 From: Kunchala Hema Sai Venkat Chandra Kumar <72931765+hemachandra666@users.noreply.github.com> Date: Tue, 28 Apr 2026 19:56:12 -0400 Subject: [PATCH 4/8] docs(get-started): register Brev web UI page in toctree Signed-off-by: Kunchala Hema Sai Venkat Chandra Kumar --- docs/index.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/index.md b/docs/index.md index b8fabc7871..dd0277d55a 100644 --- a/docs/index.md +++ b/docs/index.md @@ -298,6 +298,7 @@ Release Notes Prerequisites Quickstart +Brev Web UI ``` ```{toctree} From fb7e661bb0fd94397bcf75a9a9ae2a16f4f53cfe Mon Sep 17 00:00:00 2001 From: Kunchala Hema Sai Venkat Chandra Kumar <72931765+hemachandra666@users.noreply.github.com> Date: Mon, 4 May 2026 19:50:08 -0400 Subject: [PATCH 5/8] Update docs/get-started/brev-web-ui-quickstart.md Co-authored-by: Miyoung Choi --- docs/get-started/brev-web-ui-quickstart.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/get-started/brev-web-ui-quickstart.md b/docs/get-started/brev-web-ui-quickstart.md index 36b1a850a1..9f9c29c2fa 100644 --- a/docs/get-started/brev-web-ui-quickstart.md +++ b/docs/get-started/brev-web-ui-quickstart.md @@ -32,8 +32,8 @@ If you prefer the CLI-based remote deployment, see [Deploy to a Remote GPU Insta ## Prerequisites -- A free Brev account at [brev.nvidia.com](https://brev.nvidia.com) -- A free NVIDIA API key from [build.nvidia.com](https://build.nvidia.com) +- An NVIDIA Brev account at [brev.nvidia.com](https://brev.nvidia.com) +- An NVIDIA API key from [build.nvidia.com](https://build.nvidia.com) No local software installation is needed. From 31237e9dcf3d1c8aac547204149b77aa2b9aee0e Mon Sep 17 00:00:00 2001 From: Kunchala Hema Sai Venkat Chandra Kumar <72931765+hemachandra666@users.noreply.github.com> Date: Mon, 4 May 2026 20:11:16 -0400 Subject: [PATCH 6/8] docs(index): move Brev web UI page to Deployment section Signed-off-by: Kunchala Hema Sai Venkat Chandra Kumar --- docs/index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/index.md b/docs/index.md index cf3acba979..bf6dd4df8a 100644 --- a/docs/index.md +++ b/docs/index.md @@ -308,7 +308,6 @@ Release Notes Prerequisites Quickstart -Brev Web UI Quickstart with OpenClaw Quickstart with Hermes ``` @@ -346,6 +345,7 @@ Customize the Network Policy :hidden: Deploy to a Remote GPU Instance +Brev Web UI Install OpenClaw Plugins Sandbox Hardening ``` From 3616258b9abace1271250681b0d3a9ca32918d3e Mon Sep 17 00:00:00 2001 From: Kunchala Hema Sai Venkat Chandra Kumar <72931765+hemachandra666@users.noreply.github.com> Date: Mon, 4 May 2026 20:22:23 -0400 Subject: [PATCH 7/8] docs(get-started): remove Dashboard, Troubleshooting, and upstream OpenClaw sections Signed-off-by: Kunchala Hema Sai Venkat Chandra Kumar --- docs/get-started/brev-web-ui-quickstart.md | 57 +--------------------- 1 file changed, 1 insertion(+), 56 deletions(-) diff --git a/docs/get-started/brev-web-ui-quickstart.md b/docs/get-started/brev-web-ui-quickstart.md index 9f9c29c2fa..e3c68f1fcc 100644 --- a/docs/get-started/brev-web-ui-quickstart.md +++ b/docs/get-started/brev-web-ui-quickstart.md @@ -101,35 +101,6 @@ Provider: NVIDIA Cloud Click **Chat With Agent** to open the OpenClaw gateway dashboard. -## Understand the Dashboard - -The OpenClaw gateway dashboard has the following sections. - -**Chat.** -Direct chat interface for talking to your agent. -This is where you start. -The agent reads your workspace files and responds using Nemotron-3-Super-120B via NVIDIA Cloud. - -**Control.** - -- **Overview** -- Agent health and status. -- **Channels** -- Connect to Slack, Telegram, or Discord. -- **Instances** -- Running agent instances. -- **Sessions** -- Conversation history. -- **Usage** -- Token and API usage. -- **Cron Jobs** -- Schedule recurring agent tasks. - -**Agent.** - -- **Agents** -- Manage agent profiles. -- **Skills** -- Add new capabilities to your agent. -- **Nodes** -- Multi-agent node configuration. - -**Settings.** - -- **Config** -- Agent configuration. -- **Debug** -- Debug logs and diagnostics. - ## Have Your First Conversation In the Chat box, type the following: @@ -179,40 +150,14 @@ Now that your agent is running, explore these capabilities. **Connect a messaging channel.** Go to **Channels** in the dashboard to connect your agent to Telegram, Slack, or Discord so it can message you proactively. -**Add a new skill.** -Go to **Skills** and browse available skills, or use the built-in Skill-Creator to build a custom skill. - -**Schedule a recurring task.** -Go to **Cron Jobs** to set up tasks the agent runs automatically, such as a daily email check or calendar reminder. - **Use a different AI model.** The agent supports switching inference providers at runtime. See [Switch Inference Providers](../inference/switch-inference-providers.md) for instructions. -## Troubleshooting - -**The Deploy NemoClaw button is not visible.** -Make sure you are signed in to `brev.nvidia.com`. -The banner appears on the GPUs page. -If you do not see it, try refreshing the page or navigating directly to the NemoClaw tab in the top navigation. - -**API key not accepted.** -Make sure your key starts with `nvapi-` and was copied in full. -Keys from `build.nvidia.com` are free and do not require a paid plan. - -**Agent takes more than 5 minutes to deploy.** -This can happen during periods of high demand on Brev. -The Cloudflare quota warning at the top of the Brev page may affect deployment time. -Try again after a few minutes. - -**OpenClaw dashboard shows a blank chat.** -This is normal on first launch. -The agent reads its workspace files during the first session startup. -Type a message and wait a few seconds for the first response. - ## Next Steps - [Prerequisites](prerequisites.md) -- System requirements before getting started. - [Quickstart](quickstart.md) -- CLI-based local setup. - [Deploy to a Remote GPU Instance](../deployment/deploy-to-remote-gpu.md) -- CLI-based Brev deployment. +- [Troubleshooting](../reference/troubleshooting.md) -- Common issues and fixes. - [Monitor Sandbox Activity](../monitoring/monitor-sandbox-activity.md) From fd7493fe5df6b354d08b3e53c2ce93697005eb5f Mon Sep 17 00:00:00 2001 From: Kunchala Hema Sai Venkat Chandra Kumar <72931765+hemachandra666@users.noreply.github.com> Date: Tue, 5 May 2026 11:34:12 -0400 Subject: [PATCH 8/8] Update docs/index.md Co-authored-by: Miyoung Choi --- docs/index.md | 1 - 1 file changed, 1 deletion(-) diff --git a/docs/index.md b/docs/index.md index bf6dd4df8a..45c932621b 100644 --- a/docs/index.md +++ b/docs/index.md @@ -307,7 +307,6 @@ Release Notes :hidden: Prerequisites -Quickstart Quickstart with OpenClaw Quickstart with Hermes ```