Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Rust agentai-agentapplecomputer-usecomputer-use-agentcontainerizationcuadesktop-automationhacktoberfestlumemacosmanusoperatorswiftvirtualizationvirtualization-frameworkwindowswindows-sandbox
docs: enhance documentation with framework naming, branding, and package manager improvements
f-trycuadb77d2ec65b7
diff --git a/docs/content/docs/agent-sdk/custom-tools.mdx b/docs/content/docs/agent-sdk/custom-tools.mdxindex 63d878cba9..cf1652dd29 100644--- a/docs/content/docs/agent-sdk/custom-tools.mdx+++ b/docs/content/docs/agent-sdk/custom-tools.mdx@@ -3,7 +3,7 @@ title: Custom Toolsslug: custom-tools----The Agent SDK supports defining custom Python tools that run securely in sandboxed environments on remote Cua Computers. This enables safe execution of user-defined functions, isolation of dependencies, and robust automation workflows.+The Agent SDK supports defining custom Python tools that run securely in sandboxed environments on remote Cua Computer Frameworks. This enables safe execution of user-defined functions, isolation of dependencies, and robust automation workflows.## Custom Toolsdiff --git a/docs/content/docs/agent-sdk/supported-agents/computer-use-agents.mdx b/docs/content/docs/agent-sdk/supported-agents/computer-use-agents.mdxindex 49a92aa7e3..74371087d8 100644--- a/docs/content/docs/agent-sdk/supported-agents/computer-use-agents.mdx+++ b/docs/content/docs/agent-sdk/supported-agents/computer-use-agents.mdx@@ -77,7 +77,7 @@ async for _ in agent.run("Open Firefox and navigate to github.com"):Qwen3 VL family:-- `cua/qwen/qwen3-vl-235b` (via CUA VLM Router - recommended)+- `cua/qwen/qwen3-vl-235b` (via Cua VLM Router - recommended)```pythonagent = ComputerAgent("cua/qwen/qwen3-vl-235b", tools=[computer])diff --git a/docs/content/docs/agent-sdk/supported-model-providers/cua-vlm-router.mdx b/docs/content/docs/agent-sdk/supported-model-providers/cua-vlm-router.mdxindex 930360a22f..d09cfe9f92 100644--- a/docs/content/docs/agent-sdk/supported-model-providers/cua-vlm-router.mdx+++ b/docs/content/docs/agent-sdk/supported-model-providers/cua-vlm-router.mdx@@ -1,15 +1,15 @@----title: CUA VLM Router+title: Cua VLM Routerdescription: Intelligent vision-language model routing with cost optimization and unified access----# CUA VLM Router+# Cua VLM Router-The **CUA VLM Router** is an intelligent inference API that provides unified access to multiple vision-language model providers through a single API key. It offers cost optimization and detailed observability for production AI applications.+The **Cua VLM Router** is an intelligent inference API that provides unified access to multiple vision-language model providers through a single API key. It offers cost optimization and detailed observability for production AI applications.## Overview-Instead of managing multiple API keys and provider-specific code, CUA VLM Router acts as a smart cloud gateway that:+Instead of managing multiple API keys and provider-specific code, Cua VLM Router acts as a smart cloud gateway that:- **Unifies access** to multiple model providers- **Optimizes costs** through intelligent routing and provider selection@@ -21,7 +21,7 @@ Instead of managing multiple API keys and provider-specific code, CUA VLM Router### 1. Get Your API Key-Sign up at [cua.ai](https://cua.ai/signin) and get your CUA API key from the dashboard.+Sign up at [cua.ai](https://cua.ai/signin) and get your Cua API key from the dashboard.### 2. Set Environment Variable@@ -53,7 +53,7 @@ async for result in agent.run(messages):## Available Models-The CUA VLM Router currently supports these models:+The Cua VLM Router currently supports these models:| Model ID | Provider | Description | Best For || --------------------------------- | --------- | ----------------- | --------------------------------------- |@@ -66,10 +66,10 @@ The CUA VLM Router currently supports these models:### Intelligent Routing-When you make a request to CUA VLM Router:+When you make a request to Cua VLM Router:1. **Model Resolution**: Your model ID (e.g., `cua/anthropic/claude-sonnet-4.5`) is resolved to the appropriate provider-2. **Provider Selection**: CUA routes your request to the appropriate model provider+2. **Provider Selection**: Cua routes your request to the appropriate model provider3. **Response**: You receive an OpenAI-compatible response with metadata## API Reference@@ -224,18 +224,18 @@ Requests are billed in **credits**:}```-**Note:** CUA VLM Router is a fully managed cloud service. If you want to use your own provider API keys directly (BYOK), see the [Supported Model Providers](/agent-sdk/supported-model-providers/) page for direct provider access via the agent SDK.+**Note:** Cua VLM Router is a fully managed cloud service. If you want to use your own provider API keys directly (BYOK), see the [Supported Model Providers](/agent-sdk/supported-model-providers/) page for direct provider access via the agent SDK.## Response Metadata-CUA VLM Router includes metadata about routing decisions and costs in the response. This information helps with debugging and monitoring your application's model usage.+Cua VLM Router includes metadata about routing decisions and costs in the response. This information helps with debugging and monitoring your application's model usage.## Configuration### Environment Variables```bash-# Required: Your CUA API key+# Required: Your Cua API keyexport CUA_API_KEY="sk_cua-api01_..."# Optional: Custom endpoint (defaults to https://inference.cua.ai/v1)@@ -259,7 +259,7 @@ agent = ComputerAgent(## Benefits Over Direct Provider Access-| Feature | CUA VLM Router | Direct Provider (BYOK) |+| Feature | Cua VLM Router | Direct Provider (BYOK) || -------------------------- | ---------------------------- | --------------------------------- || **Single API Key** | ✅ One key for all providers | ❌ Multiple keys to manage || **Managed Infrastructure** | ✅ No API key management | ❌ Manage multiple provider keys |@@ -397,7 +397,7 @@ async for result in agent.run(messages):## Migration from Direct Provider Access-Switching from direct provider access (BYOK) to CUA VLM Router is simple:+Switching from direct provider access (BYOK) to Cua VLM Router is simple:**Before (Direct Provider Access with BYOK):**@@ -412,11 +412,11 @@ agent = ComputerAgent()```-**After (CUA VLM Router - Cloud Service):**+**After (Cua VLM Router - Cloud Service):**```pythonimport os-# Required: CUA API key only (no provider keys needed)+# Required: Cua API key only (no provider keys needed)os.environ["CUA_API_KEY"] = "sk_cua-api01_..."agent = ComputerAgent(@@ -425,7 +425,7 @@ agent = ComputerAgent()```-That's it! Same code structure, just different model format. CUA manages all provider infrastructure and credentials for you.+That's it! Same code structure, just different model format. Cua manages all provider infrastructure and credentials for you.## Supportdiff --git a/docs/content/docs/agent-sdk/supported-model-providers/index.mdx b/docs/content/docs/agent-sdk/supported-model-providers/index.mdxindex 44138f631a..d27aab31dd 100644--- a/docs/content/docs/agent-sdk/supported-model-providers/index.mdx+++ b/docs/content/docs/agent-sdk/supported-model-providers/index.mdx@@ -4,9 +4,9 @@ title: Supported Model Providers## Supported Models-### CUA VLM Router (Recommended)+### Cua VLM Router (Recommended)-Use CUA's cloud inference API for intelligent routing and cost optimization with a single API key. CUA manages all provider infrastructure and credentials for you.+Use Cua's cloud inference API for intelligent routing and cost optimization with a single API key. Cua manages all provider infrastructure and credentials for you.```python# Anthropic Claude models@@ -24,7 +24,7 @@ model="cua/google/gemini-3-flash-preview" # Gemini 3 Flash Preview (fastest and- Cost tracking and optimization- Fully managed infrastructure (no provider keys to manage)-[Learn more about CUA VLM Router →](/agent-sdk/supported-model-providers/cua-vlm-router)+[Learn more about Cua VLM Router →](/agent-sdk/supported-model-providers/cua-vlm-router)---diff --git a/docs/content/docs/cli-playbook/commands.mdx b/docs/content/docs/cli-playbook/commands.mdxindex 6f3b4c7ec3..d123221c6b 100644--- a/docs/content/docs/cli-playbook/commands.mdx+++ b/docs/content/docs/cli-playbook/commands.mdx@@ -1,6 +1,6 @@---title: Command Reference-description: Complete reference for all CUA CLI commands+description: Complete reference for all Cua CLI commands---import { Tabs, Tab } from 'fumadocs-ui/components/tabs';@@ -8,7 +8,7 @@ import { Callout } from 'fumadocs-ui/components/callout';## Overview-The CUA CLI provides commands for authentication and sandbox management.+The Cua CLI provides commands for authentication and sandbox management.### Command Styles@@ -41,7 +41,7 @@ Both styles work identically - use whichever you prefer!### `cua auth login`-Authenticate with your CUA account using browser-based OAuth flow.+Authenticate with your Cua account using browser-based OAuth flow.```bash# Interactive browser login@@ -69,7 +69,7 @@ API key saved### `cua auth env`-Create or update a `.env` file in the current directory with your CUA API key.+Create or update a `.env` file in the current directory with your Cua API key.```bashcua auth envdiff --git a/docs/content/docs/cli-playbook/index.mdx b/docs/content/docs/cli-playbook/index.mdxindex dec372f961..cd97158bfc 100644--- a/docs/content/docs/cli-playbook/index.mdx+++ b/docs/content/docs/cli-playbook/index.mdx@@ -1,6 +1,6 @@---title: Getting Started-description: Install and set up the CUA CLI+description: Install and set up the Cua CLI---import { Tabs, Tab } from 'fumadocs-ui/components/tabs';@@ -23,7 +23,7 @@ The Cua CLI is a command-line tool for managing your Cua cloud sandboxes. Create</Tab></Tabs>-This installs [Bun](https://bun.sh) and the CUA CLI. Verify with:+This installs [Bun](https://bun.sh) and the Cua CLI. Verify with:```bashcua --help@@ -31,7 +31,7 @@ cua --help## Authentication-Login to your CUA account:+Login to your Cua account:```bash# Browser-based logindiff --git a/docs/content/docs/computer-sdk/cloud-vm-management.mdx b/docs/content/docs/computer-sdk/cloud-vm-management.mdxindex 3db79e6255..21174bd4f3 100644--- a/docs/content/docs/computer-sdk/cloud-vm-management.mdx+++ b/docs/content/docs/computer-sdk/cloud-vm-management.mdx@@ -7,7 +7,7 @@ import { Tab, Tabs } from 'fumadocs-ui/components/tabs';Using the Cua Cloud API, you can manage your Cua Cloud sandboxes with Python or HTTP (curl).-All examples require a CUA API key. You can obtain one from the [Dashboard](https://www.cua.ai/dashboard/keys).+All examples require a Cua API key. You can obtain one from the [Dashboard](https://www.cua.ai/dashboard/keys).---diff --git a/docs/content/docs/computer-sdk/commands.mdx b/docs/content/docs/computer-sdk/commands.mdxindex 7421330dd5..4fc7b0ffdb 100644--- a/docs/content/docs/computer-sdk/commands.mdx+++ b/docs/content/docs/computer-sdk/commands.mdx@@ -3,7 +3,7 @@ title: Commandsdescription: Computer commands and interface methods----This page describes the set of supported **commands** you can use to control a Cua Computer directly via the Python SDK.+This page describes the set of supported **commands** you can use to control a Cua Computer Framework directly via the Python SDK.These commands map to the same actions available in the [Computer Server API Commands Reference](/computer-sdk/computer-server/Commands), and provide low-level, async access to system operations from your agent or automation code.diff --git a/docs/content/docs/computer-sdk/computers.mdx b/docs/content/docs/computer-sdk/computers.mdxindex 2ae18315ae..a504e6e091 100644--- a/docs/content/docs/computer-sdk/computers.mdx+++ b/docs/content/docs/computer-sdk/computers.mdx@@ -8,7 +8,7 @@ description: Understanding Cua computer types and connection methodsBefore we can automate apps using AI, we need to first connect to a Computer Server to give the AI a safe environment to execute workflows in.-Cua Computers are preconfigured sandboxes running the Computer Server. They can be either macOS, Linux, or Windows. They're found in either a cloud-native sandbox, or on your host desktop.+Cua Computer Frameworks are preconfigured sandboxes running the Computer Server. They can be either macOS, Linux, or Windows. They're found in either a cloud-native sandbox, or on your host desktop.## Cloud Sandboxdiff --git a/docs/content/docs/computer-sdk/sandboxed-python.mdx b/docs/content/docs/computer-sdk/sandboxed-python.mdxindex e66ad34c65..fb87bff3ac 100644--- a/docs/content/docs/computer-sdk/sandboxed-python.mdx+++ b/docs/content/docs/computer-sdk/sandboxed-python.mdx@@ -7,7 +7,7 @@ slug: sandboxed-pythonA corresponding <a href="https://github.com/trycua/cua/blob/main/examples/sandboxed_functions_examples.py" target="_blank">Python example</a> is available for this documentation.</Callout>-You can run Python functions securely inside a sandboxed virtual environment on a remote Cua Computer. This is useful for executing untrusted user code, isolating dependencies, or providing a safe environment for automation tasks.+You can run Python functions securely inside a sandboxed virtual environment on a remote Cua Computer Framework. This is useful for executing untrusted user code, isolating dependencies, or providing a safe environment for automation tasks.## How It Works@@ -50,7 +50,7 @@ await my_computer.venv_install("myenv", ["requests"])## Example: Interacting with macOS Applications-You can use sandboxed functions to interact with macOS applications on a local Cua Computer (requires `os_type="darwin"`). This is particularly useful for automation tasks that involve GUI applications.+You can use sandboxed functions to interact with macOS applications on a local Cua Computer Framework (requires `os_type="darwin"`). This is particularly useful for automation tasks that involve GUI applications.```python# Example: Use sandboxed functions to execute code in a Cua Sandboxdiff --git a/docs/content/docs/example-usecases/form-filling.mdx b/docs/content/docs/example-usecases/form-filling.mdxindex fd365a0ff4..d133aa026f 100644--- a/docs/content/docs/example-usecases/form-filling.mdx+++ b/docs/content/docs/example-usecases/form-filling.mdx@@ -10,7 +10,7 @@ import { Tab, Tabs } from 'fumadocs-ui/components/tabs';Cua can be used to automate interactions between form filling and local file systems over any operating system. Cua let's you interact with all the elements of a web page and local file systems to integrate between the two.-This preset usecase uses [Cua Computer](/computer-sdk/computers) to interact with a web page and local file systems along with [Agent Loops](/agent-sdk/agent-loops) to run the agent in a loop with message history.+This preset usecase uses [Cua Computer Framework](/computer-sdk/computers) to interact with a web page and local file systems along with [Agent Loops](/agent-sdk/agent-loops) to run the agent in a loop with message history.---@@ -30,7 +30,13 @@ cua-computerpython-dotenv>=1.0.0```-Install the dependencies:+Install the dependencies using uv (recommended):++```bash+uv pip install -r requirements.txt+```++Or using pip:```bashpip install -r requirements.txt@@ -488,7 +494,7 @@ Monitor the output to see the agent's progress through each task.## Next Steps-- Learn more about [Cua computers](/computer-sdk/computers) and [computer commands](/computer-sdk/commands)-- Read about [Agent loops](/agent-sdk/agent-loops), [tools](/agent-sdk/custom-tools), and [supported model providers](/agent-sdk/supported-model-providers/)+- Learn more about [Cua Computer Framework](/computer-sdk/computers) and [Computer Commands](/computer-sdk/commands)+- Read about [Agent Loops](/agent-sdk/agent-loops), [Tools](/agent-sdk/custom-tools), and [Supported Model Providers](/agent-sdk/supported-model-providers/)- Experiment with different [Models and Providers](/agent-sdk/supported-model-providers/)- Join our [Discord community](https://discord.com/invite/mVnXXpdE85) for helpdiff --git a/docs/content/docs/example-usecases/post-event-contact-export.mdx b/docs/content/docs/example-usecases/post-event-contact-export.mdxindex f0a2b6dd2f..3bbac2526f 100644--- a/docs/content/docs/example-usecases/post-event-contact-export.mdx+++ b/docs/content/docs/example-usecases/post-event-contact-export.mdx@@ -12,7 +12,7 @@ After networking events, you need to export new connections from LinkedIn, X, or**The workflow**: Kick off the script after an event and let it run overnight. Wake up to a clean CSV ready for your CRM or email tool.-This example focuses on LinkedIn but works across platforms. It uses [Cua Computer](/computer-sdk/computers) to interact with web interfaces and [Agent Loops](/agent-sdk/agent-loops) to iterate through connections with conversation history.+This example focuses on LinkedIn but works across platforms. It uses [Cua Computer Framework](/computer-sdk/computers) to interact with web interfaces and [Agent Loops](/agent-sdk/agent-loops) to iterate through connections with conversation history.### Why Cua is Perfect for This@@ -66,7 +66,13 @@ cua-computerpython-dotenv>=1.0.0```-Install the dependencies:+Install the dependencies using uv (recommended):++```bash+uv pip install -r requirements.txt+```++Or using pip:```bashpip install -r requirements.txt@@ -75,7 +81,7 @@ pip install -r requirements.txtCreate a `.env` file with your API keys:```text-ANTHROPIC_API_KEY=your-anthropic-api-key # optional, BYOK. By default, this cookbook uses the CUA VLM Router+ANTHROPIC_API_KEY=your-anthropic-api-key # optional, BYOK. By default, this cookbook uses the Cua VLM RouterCUA_API_KEY=sk_cua-api01...CUA_CONTAINER_NAME=m-linux-...```@@ -468,8 +474,8 @@ This script demonstrates a practical workflow for extracting LinkedIn connection## Next Steps-- Learn more about [Cua computers](/computer-sdk/computers) and [computer commands](/computer-sdk/commands)-- Read about [Agent loops](/agent-sdk/agent-loops), [tools](/agent-sdk/custom-tools), and [supported model providers](/agent-sdk/supported-model-providers/)+- Learn more about [Cua Computer Framework](/computer-sdk/computers) and [Computer Commands](/computer-sdk/commands)+- Read about [Agent Loops](/agent-sdk/agent-loops), [Tools](/agent-sdk/custom-tools), and [Supported Model Providers](/agent-sdk/supported-model-providers/)- Experiment with different [Models and Providers](/agent-sdk/supported-model-providers/)- Adapt this script for other platforms (Twitter/X, email extraction, etc.)- Join our [Discord community](https://discord.com/invite/mVnXXpdE85) for helpdiff --git a/docs/content/docs/example-usecases/windows-app-behind-vpn.mdx b/docs/content/docs/example-usecases/windows-app-behind-vpn.mdxindex 3e910987ed..7779a40fed 100644--- a/docs/content/docs/example-usecases/windows-app-behind-vpn.mdx+++ b/docs/content/docs/example-usecases/windows-app-behind-vpn.mdx@@ -616,8 +616,8 @@ If costs are higher than expected:## Next Steps-- **Explore custom tools**: Learn how to create [custom tools](/agent-sdk/custom-tools) for application-specific actions-- **Implement callbacks**: Add [monitoring and logging](/agent-sdk/callbacks) for production workflows+- **Explore Custom Tools**: Learn how to create [Custom Tools](/agent-sdk/custom-tools) for application-specific actions+- **Implement Callbacks**: Add [Monitoring and Logging](/agent-sdk/callbacks) for production workflows- **Join community**: Get help in our [Discord](https://discord.com/invite/mVnXXpdE85)---diff --git a/docs/content/docs/get-started/quickstart.mdx b/docs/content/docs/get-started/quickstart.mdxindex a0cd5bcb2a..0c2e304c60 100644--- a/docs/content/docs/get-started/quickstart.mdx+++ b/docs/content/docs/get-started/quickstart.mdx@@ -49,7 +49,7 @@ You can run your Cua sandbox in the cloud (recommended for easiest setup), local**Option 2: Via CLI**- 1. Install the CUA CLI:+ 1. Install the Cua CLI:```bash# macOS/Linuxcurl -LsSf https://cua.ai/cli/install.sh | sh@@ -201,23 +201,37 @@ You can run your Cua sandbox in the cloud (recommended for easiest setup), local----## Developer Quickstart+## Automate Your Sandbox<Callout type="warn" title="Python Version Compatibility">Cua packages require **Python 3.12 or 3.13**. Python 3.14 is not currently supported due to dependency compatibility issues (pydantic-core/PyO3 compatibility). If you encounter build errors on Python 3.14, please use Python 3.13 or earlier.</Callout>+This section guides you through building automation in layers:++1. **Cua Computer Framework** - Direct sandbox control for manual automation and testing+2. **Cua Agent Framework** - Adds AI automation on top, using vision-language models to understand and interact with the UI++Start by setting up Cua Computer Framework to verify your sandbox works, then add Cua Agent Framework on top to enable intelligent, autonomous automation.+<Steps><Step>-### Using Computer+### Step 1: Connect with Cua Computer Framework-Connect to your Cua computer and perform basic interactions, such as taking screenshots or simulating user input.+Install Cua Computer Framework and verify your sandbox is working by performing basic interactions such as taking screenshots or simulating user input. This is an important verification step before adding AI agents.<Tabs items={['Python', 'TypeScript']}><Tab value="Python">Install the Cua computer Python SDK:++ **Using uv (recommended):**+ ```bash+ uv pip install cua-computer+ ```++ **Or with pip:**```bashpip install cua-computer```@@ -226,7 +240,7 @@ Connect to your Cua computer and perform basic interactions, such as taking scre<Tabs items={['Cloud Sandbox', 'Linux on Docker', 'QEMU Docker', 'macOS Sandbox', 'Windows Sandbox', 'Your host desktop']}><Tab value="Cloud Sandbox">- Set your CUA API key (same key used for model inference) and connect to your sandbox:+ Set your Cua API key (same key used for model inference) and connect to your sandbox:```pythonimport osfrom computer import Computer@@ -464,10 +478,6 @@ Connect to your Cua computer and perform basic interactions, such as taking scre</Tab><Tab value="TypeScript">- <Callout type="warn" title="TypeScript SDK Deprecated">- The TypeScript interface is currently deprecated. We're working on version 0.2.0 with improved TypeScript support. In the meantime, please use the Python SDK.- </Callout>-Install the Cua computer TypeScript SDK:```bashnpm install @trycua/computer@@ -477,7 +487,7 @@ Connect to your Cua computer and perform basic interactions, such as taking scre<Tabs items={['Cloud Sandbox', 'Linux on Docker', 'macOS Sandbox', 'Windows Sandbox', 'Your host desktop']}><Tab value="Cloud Sandbox">- Set your CUA API key (same key used for model inference):+ Set your Cua API key (same key used for model inference):```bashexport CUA_API_KEY="sk_cua-api01_..."```@@ -562,30 +572,43 @@ Connect to your Cua computer and perform basic interactions, such as taking scre</Tab></Tabs>-Learn more about computers in the [Cua computers documentation](/computer-sdk/computers). You will see how to automate computers with agents in the next step.+Learn more about computers in the [Cua computers documentation](/computer-sdk/computers).</Step><Step>-### Using Agent+### Step 2: Add AI Automation with Cua Agent Framework-Utilize an Agent to automate complex tasks by providing it with a goal and allowing it to interact with the computer environment.+Now that you've verified your sandbox works, use an Agent to automate complex tasks by providing it with a goal. The agent will interact with the computer environment using a vision-language model to understand the UI and execute actions.-Install the Cua agent Python SDK:+While you can build your own agent loop with any LLM, Cua Agent Framework is the recommended approach as it provides:+- **100+ VLM options** through Cua VLM Router and direct provider access+- **Built-in optimizations** for computer-use tasks+- **Structured agent loops** for consistent behavior-```bash-pip install "cua-agent[all]"-```+<Tabs items={['Python', 'TypeScript']}>+ <Tab value="Python">+ Install the Cua agent Python SDK:++ **Using uv (recommended):**+ ```bash+ uv pip install "cua-agent[all]"+ ```-Choose how you want to access vision-language models for your agent:+ **Or with pip:**+ ```bash+ pip install "cua-agent[all]"+ ```++ Choose how you want to access vision-language models for your agent:-<Tabs items={['CUA VLM Router', 'BYOK (Bring Your Own Key)']}>- <Tab value="CUA VLM Router">+<Tabs items={['Cua VLM Router', 'BYOK (Bring Your Own Key)']}>+ <Tab value="Cua VLM Router">- Use CUA's inference API to access multiple model providers with a single API key (same key used for sandbox access). CUA VLM Router provides intelligent routing and cost optimization.+ Use Cua's inference API to access multiple model providers with a single API key (same key used for sandbox access). Cua VLM Router provides intelligent routing and cost optimization.- **Use the agent with CUA models:**+ **Use the agent with Cua models:**```pythonimport osimport asyncio@@ -626,7 +649,7 @@ Choose how you want to access vision-language models for your agent:asyncio.run(main())```- **Available CUA models:**+ **Available Cua models:**- `cua/anthropic/claude-sonnet-4.5` - Claude Sonnet 4.5 (recommended)- `cua/anthropic/claude-opus-4.5` - Claude Opus 4.5 (enhanced agentic capabilities)- `cua/anthropic/claude-haiku-4.5` - Claude Haiku 4.5 (faster, cost-effective)@@ -704,6 +727,156 @@ Choose how you want to access vision-language models for your agent:See [Supported Models](/agent-sdk/supported-model-providers/) for the complete list.+ </Tab>+ </Tabs>++ </Tab>+ <Tab value="TypeScript">+ For TypeScript, you can build agent loops using the [Vercel AI SDK](https://ai-sdk.dev/) with the Cua Computer Framework TypeScript library. The Vercel AI SDK provides a unified interface for building multi-step agent workflows with language models.++ Install the required packages:++ ```bash+ npm install @trycua/computer ai+ ```++ Here's an example of building an agent loop with the Vercel AI SDK:++ ```typescript+ import Anthropic from "@anthropic-ai/sdk";+ import { Computer, OSType } from "@trycua/computer";+ import { generateText } from "ai";+ import { anthropic } from "@ai-sdk/anthropic";++ const client = new Anthropic();+ let computer: Computer;++ const computerTool = {+ type: "tool" as const,+ name: "computer",+ description: "Control the computer with actions like screenshot, click, type, etc.",+ inputSchema: {+ type: "object" as const,+ properties: {+ action: {+ type: "string" as const,+ description: "Action to perform (screenshot, click, type, key_press, etc.)",+ },+ coordinate: {+ type: "array" as const,+ items: { type: "number" as const },+ description: "x, y coordinates for click actions",+ },+ text: {+ type: "string" as const,+ description: "Text to type",+ },+ },+ required: ["action"],+ },+ };++ async function runAgentLoop(goal: string) {+ // Initialize computer+ computer = new Computer({+ osType: OSType.LINUX,+ provider_type: "cloud",+ name: "your-sandbox-name",+ apiKey: process.env.CUA_API_KEY!,+ });++ await computer.run();++ const messages: any[] = [];++ // First message with goal+ messages.push({+ role: "user",+ content: goal,+ });++ // Agent loop+ for (let i = 0; i < 10; i++) {+ // Get model response with tool use+ const response = await client.messages.create({+ model: "claude-opus-4-1-20250805",+ max_tokens: 4096,+ tools: [computerTool],+ messages: messages,+ });++ // Check if we're done+ if (response.stop_reason === "end_turn") {+ console.log("Task completed!");+ break;+ }++ // Add assistant response to history+ messages.push({+ role: "assistant",+ content: response.content,+ });++ // Process tool calls+ const toolResults = [];+ for (const block of response.content) {+ if (block.type === "tool_use") {+ try {+ let result: any;+ switch (block.input.action) {+ case "screenshot":+ result = await computer.interface.screenshot();+ break;+ case "click":+ result = await computer.interface.click(+ block.input.coordinate[0],+ block.input.coordinate[1]+ );+ break;+ case "type":+ result = await computer.interface.type(block.input.text);+ break;+ case "key_press":+ result = await computer.interface.key_press(block.input.text);+ break;+ default:+ result = { error: "Unknown action" };+ }++ toolResults.push({+ type: "tool_result",+ tool_use_id: block.id,+ content: JSON.stringify(result),+ });+ } catch (error) {+ toolResults.push({+ type: "tool_result",+ tool_use_id: block.id,+ content: `Error: ${error}`,+ is_error: true,+ });+ }+ }+ }++ // Add tool results to messages+ if (toolResults.length > 0) {+ messages.push({+ role: "user",+ content: toolResults,+ });+ }+ }++ await computer.disconnect();+ }++ // Run the agent+ runAgentLoop("Take a screenshot and tell me what you see");+ ```++ For more details and examples, see the [Vercel AI SDK Computer Use Cookbook](https://ai-sdk.dev/cookbook/guides/computer-use).+</Tab></Tabs>@@ -714,21 +887,23 @@ Learn more about agents in [Agent Loops](/agent-sdk/agent-loops) and available m### Next Steps-- Learn more about [Cua computers](/computer-sdk/computers) and [computer commands](/computer-sdk/commands)-- Read about [Agent loops](/agent-sdk/agent-loops), [tools](/agent-sdk/custom-tools), and [supported model providers](/agent-sdk/supported-model-providers/)-- Join our [Discord community](https://discord.com/invite/mVnXXpdE85) for help-- Try out [Form Filling](/example-usecases/form-filling) preset usecase+- Explore [Cua Computer Framework Commands](/computer-sdk/commands) for more sandbox interactions+- Learn about [Agent Loops](/agent-sdk/agent-loops) and advanced agent configuration+- Check out [Custom Tools](/agent-sdk/custom-tools) to extend your agents+- Review [Supported Model Providers](/agent-sdk/supported-model-providers/) for more LLM options+- Try the [Form Filling](/example-usecases/form-filling) example use case+- Join our [Discord community](https://discord.com/invite/cua-ai) for help and discussion{/* ---## CLI Quickstart-Get started quickly with the CUA CLI - the easiest way to manage cloud sandboxes and run AI agents.+Get started quickly with the Cua CLI - the easiest way to manage cloud sandboxes and run AI agents.<Steps><Step>-### Install the CUA CLI+### Install the Cua CLI<Tabs items={['macOS / Linux', 'Windows', 'Bun (Alternative)', 'From Source']}><Tab value="macOS / Linux">@@ -746,7 +921,7 @@ Get started quickly with the CUA CLI - the easiest way to manage cloud sandboxes# Install Bun if you don't have itcurl -fsSL https://bun.sh/install | bash- # Install CUA CLI+ # Install Cua CLIbun add -g @trycua/cli```</Tab>diff --git a/docs/content/docs/index.mdx b/docs/content/docs/index.mdxindex d3a08d98ac..7392099612 100644--- a/docs/content/docs/index.mdx+++ b/docs/content/docs/index.mdx@@ -25,11 +25,11 @@ Computer-Use Sandboxes are isolated, controlled environments where AI agents can## Key Features-With the **Computer SDK**, you can:+With **Cua Computer Framework**, you can:- Automate **Windows, Linux, and macOS** sandboxes with a consistent, pyautogui-like API- Create & manage sandboxes locally or using **Cua Cloud**-With the **Agent SDK**, you can:+With **Cua Agent Framework**, you can:- Run computer-use models with a consistent schema- Benchmark on **OSWorld-Verified**, **SheetBench-V2**, and **ScreenSpot**- Combine UI grounding models with any LLM using **composed agents**@@ -44,6 +44,6 @@ Check out our [tutorials](https://cua.ai/blog), [examples](https://github.com/tr<div className="grid grid-cols-2 md:grid-cols-4 gap-2 mt-4 text-sm"><Card icon={<Rocket className="w-4 h-4" />} href="/get-started/quickstart" title="Quickstart" /><Card icon={<Zap className="w-4 h-4" />} href="/agent-sdk/agent-loops" title="Agent Loops" />- <Card icon={<BookOpen className="w-4 h-4" />} href="/computer-sdk/computers" title="Computer SDK" />+ <Card icon={<BookOpen className="w-4 h-4" />} href="/computer-sdk/computers" title="Cua Computer" /><Card icon={<Monitor className="w-4 h-4" />} href="/example-usecases/form-filling" title="Examples" /></div>diff --git a/docs/content/docs/meta.json b/docs/content/docs/meta.jsonindex 2d0268c28b..14f80e9ed3 100644--- a/docs/content/docs/meta.json+++ b/docs/content/docs/meta.json@@ -8,12 +8,12 @@"[discord][Discord](https://discord.com/invite/cua-ai)","---[Rocket]Get Started---","...get-started",- "---[ChefHat]Cookbook---",+ "---[ChefHat]Examples Cookbook---","...example-usecases",- "---[BookCopy]Computer Playbook---",- "...computer-sdk","---[Bot]Agent Playbook---","...agent-sdk",+ "---[BookCopy]Computer Playbook---",+ "...computer-sdk","---[Terminal]Cloud CLI Playbook---","...cli-playbook","---[Terminal]macOS VM CLI Playbook---",diff --git a/docs/src/app/layout.config.tsx b/docs/src/app/layout.config.tsxindex 510707d5f6..cb10e5dfcc 100644--- a/docs/src/app/layout.config.tsx+++ b/docs/src/app/layout.config.tsx@@ -34,7 +34,7 @@ export const baseOptions: BaseLayoutProps = {className="hidden dark:block"alt="Logo"/>- <span className="text-lg font-bold">Cua</span>+ <span className="text-lg font-bold" style={{ fontFamily: 'var(--font-urbanist)' }}>Cua</span></div>),url: 'https://cua.ai',diff --git a/docs/src/app/layout.tsx b/docs/src/app/layout.tsxindex 712010a829..727b2aedea 100644--- a/docs/src/app/layout.tsx+++ b/docs/src/app/layout.tsx@@ -1,6 +1,6 @@import './global.css';import { RootProvider } from 'fumadocs-ui/provider';-import { Geist, Geist_Mono } from 'next/font/google';+import { Geist, Geist_Mono, Urbanist } from 'next/font/google';import type { ReactNode } from 'react';import { PHProvider, PostHogPageView } from '@/providers/posthog-provider';import { AnalyticsTracker } from '@/components/analytics-tracker';@@ -18,11 +18,16 @@ const geistMono = Geist_Mono({variable: '--font-geist-mono',});+const urbanist = Urbanist({+ subsets: ['latin'],+ variable: '--font-urbanist',+});+export default function Layout({ children }: { children: ReactNode }) {return (<htmllang="en"- className={`${geist.variable} ${geistMono.variable} font-sans`}+ className={`${geist.variable} ${geistMono.variable} ${urbanist.variable} font-sans`}suppressHydrationWarning><head>