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
updated docs
Dillon DuPont8dee77bf6897
diff --git a/docs/content/docs/agent-sdk/integrations/hud.mdx b/docs/content/docs/agent-sdk/integrations/hud.mdxindex b517121e0f..cee5f77f8c 100644--- a/docs/content/docs/agent-sdk/integrations/hud.mdx+++ b/docs/content/docs/agent-sdk/integrations/hud.mdx@@ -10,37 +10,35 @@ The HUD integration allows you to use ComputerAgent with the [HUD benchmarking f```bashpip install "cua-agent[hud]"## or install hud-python directly-# pip install hud-python==0.2.10+# pip install hud-python==0.4.12```## Usage```python-from agent.integrations.hud import run_job-from hud import load_taskset-from hud.taskset import TaskSet-import logging+# Quick single-task smoke test+from agent.integrations.hud import run_single_task-# Load taskset-taskset = await load_taskset("OSWorld-Verified")-taskset = TaskSet(tasks=taskset[:10]) # limit to 10 tasks instead of all 370+await run_single_task(+ dataset="hud-evals/OSWorld-Verified-XLang", # or another HUD dataset+ model="openai/computer-use-preview+openai/gpt-5-nano", # any supported model string+ task_id=155, # e.g., reopen last closed tab+)++# Run a small split of OSWorld-Verified in parallel+from agent.integrations.hud import run_full_dataset-# Run benchmark job-job = await run_job(+results = await run_full_dataset(+ dataset="hud-evals/OSWorld-Verified-XLang", # can also pass a Dataset or list[dict]model="openai/computer-use-preview",- # model="anthropic/claude-3-5-sonnet-20241022",- # model="huggingface-local/HelloKKMe/GTA1-7B+openai/gpt-5",- task_or_taskset=taskset,- job_name="test-computeragent-job",- max_concurrent_tasks=5,- # add any extra ComputerAgent kwargs:- verbosity=logging.INFO, # Enable logging- # trajectory_dir=".." # Save trajectories locally+ split="train[:3]", # try a few tasks to start+ max_concurrent=20, # tune to your infra+ max_steps=50 # safety cap per task)-# Get results OR view them at app.hud.so-print(await job.get_analytics())-print(f"View results at: https://app.hud.so/jobs/{job.id}")+# Environment variables required:+# - HUD_API_KEY (HUD access)+# - OPENAI_API_KEY or ANTHROPIC_API_KEY depending on your chosen model(s)```**Available Benchmarks:**diff --git a/libs/python/agent/pyproject.toml b/libs/python/agent/pyproject.tomlindex 4dd27062d0..4be2f6b6b4 100644--- a/libs/python/agent/pyproject.toml+++ b/libs/python/agent/pyproject.toml@@ -55,7 +55,7 @@ cli = ["yaspin>=3.1.0",]hud = [- "hud-python==0.2.10",+ "hud-python>=0.4.12,<0.5.0",]all = [# omni requirements@@ -72,7 +72,7 @@ all = [# cli requirements"yaspin>=3.1.0",# hud requirements- "hud-python==0.2.10",+ "hud-python>=0.4.12,<0.5.0",][tool.uv]