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
[build-system]
requires = ["pdm-backend"]
build-backend = "pdm.backend"
[project]
name = "cua-agent"
version = "0.9.1"
description = "Cua (Computer Use) Agent for AI-driven computer interaction"
readme = "README.md"
classifiers = ["Development Status :: 7 - Inactive"]
license = { text = "MIT" }
authors = [
{ name = "TryCua", email = "[email protected]" }
]
dependencies = [
"httpx>=0.27.0",
"aiohttp>=3.9.3",
"anyio>=4.4.1",
"typing-extensions>=4.12.2",
"pydantic>=2.6.4",
"rich>=13.7.1",
"python-dotenv>=1.0.1",
"cua-core>=0.3.0,<0.4.0",
"certifi>=2024.2.2",
"litellm==1.86.2",
"Pillow>=10.0.0"
]
requires-python = ">=3.11,<3.14"
[project.optional-dependencies]
computer = [
"cua-sandbox>=0.8.0,<0.10.0",
]
openai = []
anthropic = []
qwen = [
"qwen-vl-utils",
"qwen-agent",
"Pillow>=10.0.0",
]
# No `omni` extra: cua-som is deprecated, unmaintained and AGPL-3.0, and this
# package is MIT. The omniparser loop still runs with it installed separately
# (`pip install cua-som`).
uitars = []
uitars-mlx = [
"mlx-vlm>=0.1.27; sys_platform == 'darwin'"
]
uitars-hf = [
"accelerate",
"torch",
"transformers>=4.54.0"
]
glm45v-hf = [
"accelerate",
"torch",
"transformers>=5.0.0rc3"
]
opencua-hf = [
"accelerate",
"torch",
"transformers>=4.53.0",
"tiktoken>=0.11.0",
"blobfile>=3.0.0"
]
internvl-hf = [
"accelerate",
"torch",
"transformers>=4.55.0",
"einops",
"timm"
]
moondream3 = [
"accelerate",
"torch",
"transformers>=4.55.0"
]
ui = [
"gradio>=6.0.0",
"python-dotenv>=1.0.1",
]
cli = [
"yaspin>=3.1.0",
]
hud = [
"hud-python==0.4.52",
"fastmcp>=3.2.0,<3.3.0",
]
gemini = [
"google-genai>=1.41.0",
]
# API-only extras for cloud/container deployments — excludes torch/transformers/local models.
# Supports: openai, anthropic, gemini, uitars (API mode).
cloud = [
# gemini API SDK
"google-genai>=1.41.0",
# cli spinner
"yaspin>=3.1.0",
# qwen tool-call formatting (used by generic_vlm.py for API-based Qwen calls)
"qwen-agent",
"qwen-vl-utils",
"Pillow>=10.0.0",
]
all = [
# uitars requirements
"mlx-vlm>=0.1.27; sys_platform == 'darwin'",
"accelerate",
"torch",
"transformers>=4.55.0",
# internvl requirements,
"einops",
"timm",
# opencua requirements
"tiktoken>=0.11.0",
"blobfile>=3.0.0",
# ui requirements
"gradio>=6.0.0",
"python-dotenv>=1.0.1",
# cli requirements
"yaspin>=3.1.0",
# gemini requirements
"google-genai>=1.41.0",
# qwen requirements
"qwen-vl-utils",
"qwen-agent",
"Pillow>=10.0.0",
]
[tool.uv]
constraint-dependencies = ["fastrtc>0.43.0", "mlx-audio>0.2.3"]
[tool.pdm]
distribution = true
[tool.pdm.build]
includes = ["cua_agent/"]