Skip to content

armgit / cua

Public Imported from GitHub
0

Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.

add uitars in examples and .toml

Dillon DuPontc319003ca291
diff --git a/examples/agent_examples.py b/examples/agent_examples.py
index 4d52b7fefa..01d7483ec7 100644
--- a/examples/agent_examples.py
+++ b/examples/agent_examples.py
@@ -30,6 +30,7 @@ async def run_agent_example():
computer=macos_computer,
# loop=AgentLoop.OPENAI,
# loop=AgentLoop.ANTHROPIC,
+ # loop=AgentLoop.UITARS,
loop=AgentLoop.OMNI,
# model=LLM(provider=LLMProvider.OPENAI), # No model name for Operator CUA
# model=LLM(provider=LLMProvider.OPENAI, name="gpt-4o"),
diff --git a/libs/agent/pyproject.toml b/libs/agent/pyproject.toml
index a460afbc8d..1572465b23 100644
--- a/libs/agent/pyproject.toml
+++ b/libs/agent/pyproject.toml
@@ -34,6 +34,9 @@ openai = [
"openai>=1.14.0,<2.0.0",
"httpx>=0.27.0,<0.29.0",
]
+uitars = [
+ "httpx>=0.27.0,<0.29.0",
+]
ui = [
"gradio>=5.23.3,<6.0.0",
"python-dotenv>=1.0.1,<2.0.0",
diff --git a/libs/mcp-server/README.md b/libs/mcp-server/README.md
index 8d55d59a15..a43076166e 100644
--- a/libs/mcp-server/README.md
+++ b/libs/mcp-server/README.md
@@ -104,7 +104,7 @@ The server is configured using environment variables (can be set in the Claude D
| Variable | Description | Default |
|----------|-------------|---------|
-| `CUA_AGENT_LOOP` | Agent loop to use (OPENAI, ANTHROPIC, OMNI) | OMNI |
+| `CUA_AGENT_LOOP` | Agent loop to use (OPENAI, ANTHROPIC, UITARS, OMNI) | OMNI |
| `CUA_MODEL_PROVIDER` | Model provider (ANTHROPIC, OPENAI, OLLAMA, OAICOMPAT) | ANTHROPIC |
| `CUA_MODEL_NAME` | Model name to use | None (provider default) |
| `CUA_PROVIDER_BASE_URL` | Base URL for provider API | None |