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
Update docs to use os.environ instead of export in Python examples
f-trycuad2b24d33594c
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 c2f6cd84cd..a0ce1340ab 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@@ -344,8 +344,9 @@ Switching from direct provider access (BYOK) to CUA VLM Router is simple:**Before (Direct Provider Access with BYOK):**```python+import os# Required: Provider-specific API key-export ANTHROPIC_API_KEY="sk-ant-..."+os.environ["ANTHROPIC_API_KEY"] = "sk-ant-..."agent = ComputerAgent(model="anthropic/claude-sonnet-4-5-20250929",@@ -355,8 +356,9 @@ agent = ComputerAgent(**After (CUA VLM Router - Cloud Service):**```python+import os# Required: CUA API key only (no provider keys needed)-export CUA_API_KEY="sk_cua-api01_..."+os.environ["CUA_API_KEY"] = "sk_cua-api01_..."agent = ComputerAgent(model="cua/anthropic/claude-sonnet-4.5", # Add "cua/" prefixdiff --git a/docs/content/docs/get-started/quickstart.mdx b/docs/content/docs/get-started/quickstart.mdxindex 0b1ac0d80f..6819d9236f 100644--- a/docs/content/docs/get-started/quickstart.mdx+++ b/docs/content/docs/get-started/quickstart.mdx@@ -141,15 +141,13 @@ 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):- ```bash- export CUA_API_KEY="sk_cua-api01_..."- ```-- Then connect to your sandbox:+ Set your CUA API key (same key used for model inference) and connect to your sandbox:```python+ import osfrom computer import Computer+ os.environ["CUA_API_KEY"] = "sk_cua-api01_..."+computer = Computer(os_type="linux", # or "windows" or "macos"provider_type="cloud",@@ -346,15 +344,13 @@ Choose how you want to access vision-language models for your agent: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.- **Set your CUA API key:**- ```bash- export CUA_API_KEY="sk_cua-api01_..."- ```-**Use the agent with CUA models:**```python+ import osfrom agent import ComputerAgent+ os.environ["CUA_API_KEY"] = "sk_cua-api01_..."+agent = ComputerAgent(model="cua/anthropic/claude-sonnet-4.5", # CUA-routed modeltools=[computer],@@ -383,19 +379,16 @@ Choose how you want to access vision-language models for your agent:Use your own API keys from model providers like Anthropic, OpenAI, or others.- **Set your provider API key:**- ```bash- # For Anthropic- export ANTHROPIC_API_KEY="sk-ant-..."-- # For OpenAI- export OPENAI_API_KEY="sk-..."- ```-**Use the agent with your provider:**```python+ import osfrom agent import ComputerAgent+ # Set your provider API key+ os.environ["ANTHROPIC_API_KEY"] = "sk-ant-..." # For Anthropic+ # OR+ os.environ["OPENAI_API_KEY"] = "sk-..." # For OpenAI+agent = ComputerAgent(model="anthropic/claude-sonnet-4-5-20250929", # Direct provider modeltools=[computer],