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
Reuse agent configuration for HUD evaluation
James Murdzaea1caea73c9c
diff --git a/notebooks/hud_hackathon.ipynb b/notebooks/hud_hackathon.ipynbindex 9c209ea718..eea8c2f67c 100644--- a/notebooks/hud_hackathon.ipynb+++ b/notebooks/hud_hackathon.ipynb@@ -124,14 +124,16 @@" verbosity=logging.INFO\n",")\n","\n",+ "agent_config = {\n",+ " \"model\": \"openai/computer-use-preview\",\n",+ " \"tools\": [computer],\n",+ " \"trajectory_dir\": str(Path(\"trajectories\")),\n",+ " \"only_n_most_recent_images\": 3,\n",+ " \"verbosity\": logging.INFO\n",+ "}\n",+ "\n","# Create agent\n",- "agent = ComputerAgent(\n",- " model=\"openai/computer-use-preview\",\n",- " tools=[computer],\n",- " trajectory_dir=str(Path(\"trajectories\")),\n",- " only_n_most_recent_images=3,\n",- " verbosity=logging.INFO\n",- ")"+ "agent = ComputerAgent(**agent_config)"]},{@@ -195,7 +197,7 @@"results = await run_full_dataset(\n"," dataset=\"ddupont/OSWorld-Tiny-Public\", # You can also pass a Dataset or a list[dict]\n"," job_name=job_name, # Optional; defaults to a timestamp for custom datasets\n",- " model=\"openai/computer-use-preview\", # Or any supported model string\n",+ " **agent_config,\n"," max_concurrent=20, # Tune to your infra\n"," max_steps=50, # Safety cap per task\n"," #split=\"train[:5]\" # Limit to just 5 tasks\n",