crewai-omega
CrewAI Integration for OmegaEngine
Documentation • Playground • Issues
✨ Features
- 🚀 Governed Crews — Add policies to any CrewAI crew
- 🤖 Agent Monitoring — Track all agent actions and tool usage
- 🔧 Tool Guards — Validate tool executions before running
- 📊 Task Auditing — Full audit trail for crew operations
- 🛡️ Output Validation — Ensure crew outputs meet policies
📦 Installation
pip install crewai-omega
🚀 Quick Start
Governed Crew
from crewai import Agent, Task, Crew
from crewai_omega import GovernedCrew
# Define your agents
researcher = Agent(
role='Senior Research Analyst',
goal='Research market trends',
backstory='Expert analyst...',
)
writer = Agent(
role='Content Writer',
goal='Create compelling content',
backstory='Professional writer...',
)
# Define tasks
research_task = Task(
description='Research the AI market...',
agent=researcher,
)
write_task = Task(
description='Write a report...',
agent=writer,
)
# Create governed crew
crew = GovernedCrew(
agents=[researcher, writer],
tasks=[research_task, write_task],
omega_api_key="your-omega-api-key",
policy_id="crew_policy",
)
# Run with governance
result = crew.kickoff()
Agent-Level Governance
from crewai_omega import GovernedAgent
# Governed agent with individual policy
analyst = GovernedAgent(
role='Financial Analyst',
goal='Analyze investments',
omega_api_key="your-omega-api-key",
policy_id="finance_policy",
block_on_deny=True,
)
🎯 Use Cases
| Use Case | How It Helps |
|---|---|
| Research Crews | Ensure factual, unbiased research |
| Content Teams | Block off-brand or harmful content |
| Code Crews | Prevent malicious code generation |
| Data Processing | Protect PII and sensitive data |
📄 License
Licensed under the Apache License 2.0.
Built with ❤️ by the OmegaEngine team
Metadata
Release files for crewai-omega 0.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| crewai_omega-0.3.0.tar.gz | 562.9 kB | Without provenance | Details for crewai_omega-0.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| crewai_omega-0.3.0-py3-none-any.whl | Python 3 | none | any | Details for crewai_omega-0.3.0-py3-none-any.whl |
Total release size: 574.2 kB
Release files / crewai_omega-0.3.0.tar.gz
| Download URL | crewai_omega-0.3.0.tar.gz |
|---|---|
| Size | 562.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5a1fdcd1d04e918db9ad88b4dd443e5db7d2849a8d3eefe6f8afaa7defb8c235
|
|
BLAKE2b-256 checksum How to use checksums |
006ded677d1eefd0d3fd8d5e05e0ecde14b2a1732ebd4cf9258691f43982496b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.13
|
Release files / crewai_omega-0.3.0-py3-none-any.whl
| Download URL | crewai_omega-0.3.0-py3-none-any.whl |
|---|---|
| Size | 11.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
701bc1c43ca07f30af0b0eaffa1d994d56396bcc59dc69e593519bf515b87466
|
|
BLAKE2b-256 checksum How to use checksums |
58e9e9de5d84d3dd719ca69039bf6bee13cf135cff20eb557d1f24119f3f648a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.13
|
Security for crewai-omega 0.3.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.