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
Prioritize UI-TARS-2 section in computer-use agents docs
ddupont00231b6d526a
diff --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 8ad89196bf..878ab88567 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@@ -9,6 +9,18 @@ All agent loops are compatible with any LLM provider supported by LiteLLM.See [Running Models Locally](/agent-sdk/supported-model-providers/local-models) for how to use Hugging Face and MLX models on your own machine.+## UI-TARS-2++Next‑generation UI‑TARS via Cua Router:++- `cua/bytedance/ui-tars-2`++```python+agent = ComputerAgent("cua/bytedance/ui-tars-2", tools=[computer])+async for _ in agent.run("Open a browser and search for Python tutorials"):+ pass+```+## Gemini CUAGemini models with computer-use capabilities:@@ -99,18 +111,6 @@ async for _ in agent.run("Open the settings menu and change the theme to dark mopass```-## UI-TARS-2--Next‑generation UI‑TARS via Cua Router:--- `cua/bytedance/ui-tars-2`--```python-agent = ComputerAgent("cua/bytedance/ui-tars-2", tools=[computer])-async for _ in agent.run("Open a browser and search for Python tutorials"):- pass-```----CUAs also support direct click prediction. See [Grounding Models](./grounding-models) for details on `predict_click()`.