Registry / llm-agents / cuga
library0.2.28pypypiunverified

CUGA is an open-source generalist agent for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features. It is under active development, with minor versions released frequently introducing new features and improvements.

pip install cuga
INSTALL
IMPORT
SIG · CUGA
C
cuga
llm-agentspythonv0.2.28
Install
—
Import
—
Disk
—
Pass rate
0/ 10
Env Coverage0 / 10
glibc
3.9–3.13
musl
3.9–3.13
Install & Compatibility
Where this runs
tested against v? · pip install
Install × environment matrix
Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux
musl
py 3.10–3.920 runs
build_error
glibc
py 3.10–3.920 runs
timeout
Code
Verified usage

Verified import paths — ran on the pinned version, not inferred.

CugaAgent
✓ from cuga.agent import CugaAgent

This quickstart demonstrates how to initialize a `CugaAgent` and invoke it with a simple task. It relies on environment variables (like `OPENAI_API_KEY`) for LLM configuration, which can be loaded from a `.env` file using `python-dotenv`.

import os from dotenv import load_dotenv from cuga.agent import CugaAgent # Load environment variables from a .env file if present load_dotenv() # Ensure your OpenAI API key is set in your environment (e.g., in a .env file or directly) # For testing, you can explicitly set it or retrieve it safely. # os.environ['OPENAI_API_KEY'] = os.environ.get('OPENAI_API_KEY', 'your-openai-api-key-here') # Initialize the agent. It will pick up LLM configurations from environment variables. cuga_agent = CugaAgent() # Define a task for the agent task = "Explain the concept of quantum entanglement in simple terms." # Invoke the agent with the task try: response = cuga_agent.invoke(task=task) # Print the agent's response print(f"Agent's response: {response.result}") except Exception as e: print(f"An error occurred: {e}") print("Please ensure your LLM API keys (e.g., OPENAI_API_KEY) are correctly set in your environment.")
cuga --version
Debug
Known issues
breakingCUGA is in active pre-1.0 development, meaning APIs and internal architecture may change with minor version updates. Features like the Policy System (v0.2.7) and Supervisor SDK (v0.2.10) involved significant overhauls that could impact existing code.
fix
Always review release notes for new versions and pin your `cuga` dependency to a specific minor version in production environments (e.g., `cuga==0.2.*`).
affects: <1.0.0
gotchaCUGA requires specific Python versions. Currently, it supports Python 3.10, 3.11, 3.12, and 3.13. Using unsupported versions will lead to installation or runtime errors.
fix
Ensure your Python environment is within the supported range (>=3.10, <3.14). Use `pyenv` or `conda` to manage Python versions if necessary.
affects: <0.2.21
gotchaTo function, `CugaAgent` needs access to Large Language Models (LLMs). This typically requires setting environment variables like `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, or `COHERE_API_KEY`. Without these, the agent will fail to interact with LLMs.
fix
Set the required LLM API keys in your environment variables. It is recommended to use a `.env` file and `python-dotenv` for local development, or your cloud provider's secrets management for deployment.
affects: All
Upgrade
Version history
0.2.28latest on PyPI · released May 10, 2026
Audit
Dependencies
litellmrequiredUsed for connecting to various LLM providers.
langchainrequiredCore dependency for LLM orchestration and integrations.
pydanticrequiredUsed for data validation and settings management (requires Pydantic V2).
openairequiredRequired for OpenAI model interactions.
Agent activity
30 hits · last 30 days
node
24
OpenAI (training)
1
Resources
cuga — pip install cuga · libregistry