AgentOps: AI-Powered Requirements-Driven Test Automation
AgentOps is a next-generation, AI-powered development platform that automatically generates requirements and tests from your codebase. Using advanced multi-agent AI systems, AgentOps bridges the gap between technical implementation and business requirements through bidirectional analysis.
🚀 Quick Start
Installation
# Install from PyPI
pip install agentops-ai
# Or install from source
git clone https://github.com/knaig/agentops_ai.git
cd agentops_ai
pip install -e .
Basic Usage
# 1. Initialize your project
agentops init
# 2. Run complete analysis on your code
agentops runner myfile.py
# 3. Check results and status
agentops status
# 4. View traceability matrix
agentops traceability
That's it! AgentOps will automatically:
- ✅ Analyze your code structure
- ✅ Generate business-focused requirements
- ✅ Create comprehensive test cases
- ✅ Execute tests and provide results
- ✅ Generate traceability matrices
📋 Available Commands
| Command | Description | Example |
|---|---|---|
agentops init |
Initialize project structure | agentops init |
agentops runner <file> |
Complete workflow execution | agentops runner src/main.py |
agentops tests <file> |
Generate test suites | agentops tests src/main.py |
agentops analyze <file> |
Deep requirements analysis | agentops analyze src/main.py |
agentops status |
Check project status | agentops status |
agentops traceability |
Generate traceability matrix | agentops traceability |
agentops onboarding |
Interactive setup guide | agentops onboarding |
agentops version |
Show version information | agentops version |
agentops help |
Show detailed help | agentops help |
🚀 Power User Options
| Option | Description | Example |
|---|---|---|
--all |
Process all Python files | agentops runner --all |
--auto-approve |
Skip manual review | agentops runner myfile.py --auto-approve |
-v, --verbose |
Detailed output | agentops runner myfile.py -v |
Combined Usage:
# Batch process entire project with automation
agentops runner --all --auto-approve -v
# Generate tests for all files
agentops tests --all --auto-approve
# Detailed analysis with verbose output
agentops analyze myfile.py -v
🎯 Enhanced CLI Experience
Interactive Onboarding
New users can get started quickly with the interactive onboarding:
agentops onboarding
This will:
- ✅ Check your installation and API key setup
- ✅ Create sample files for demonstration
- ✅ Run a complete demo workflow
- ✅ Show you all available commands and options
- ✅ Guide you through next steps
Batch Processing
Process your entire project with a single command:
# Analyze all Python files in your project
agentops runner --all
# Generate tests for all files
agentops tests --all
# With automation and verbose output
agentops runner --all --auto-approve -v
CI/CD Integration
Perfect for automated workflows:
# Fully automated analysis
agentops runner --all --auto-approve
# Check project status
agentops status -v
🔧 Configuration
Environment Setup
Create a .env file in your project root:
# Required: OpenAI API Key
OPENAI_API_KEY=your_openai_api_key_here
# Optional: Custom settings
AGENTOPS_OUTPUT_DIR=.agentops
AGENTOPS_LOG_LEVEL=INFO
API Key Validation
Validate your API keys before running:
# Run the validation script
./scripts/validate_api_keys.sh
📁 Generated Artifacts
After running AgentOps, you'll find these artifacts in your project:
.agentops/
├── requirements/
│ ├── requirements.gherkin # Requirements in Gherkin format
│ └── requirements.md # Requirements in Markdown format
├── tests/
│ ├── test_main.py # Generated test files
│ └── test_coverage.xml # Test coverage reports
├── traceability/
│ └── traceability_matrix.md # Requirements-to-tests mapping
└── reports/
└── analysis_report.json # Detailed analysis results
🎯 Key Features
🤖 Multi-Agent AI System
- Code Analyzer: Deep code structure and dependency analysis
- Requirements Engineer: Business-focused requirement extraction
- Test Architect: Comprehensive test strategy design
- Test Generator: High-quality, maintainable test code
- Quality Assurance: Automated test validation and scoring
📊 Requirements-Driven Testing
- Bidirectional Analysis: Code → Requirements → Tests
- Business Context: Requirements focus on real-world value
- Traceability: Complete mapping from requirements to tests
- Multiple Formats: Gherkin (BDD) and Markdown outputs
🔄 Streamlined Workflow
- Single Command:
agentops runnerdoes everything - Automatic Export: Requirements and traceability always up-to-date
- Error Recovery: Robust handling of common issues
- Progress Tracking: Real-time status updates
📖 Examples
Basic Python File Analysis
# myfile.py
def calculate_total(items, tax_rate=0.1):
"""Calculate total with tax for a list of items."""
subtotal = sum(items)
tax = subtotal * tax_rate
return subtotal + tax
def apply_discount(total, discount_percent):
"""Apply percentage discount to total."""
discount = total * (discount_percent / 100)
return total - discount
# Run analysis
agentops runner myfile.py
Generated Requirements (Gherkin):
Feature: Shopping Cart Calculations
Scenario: Calculate total with tax
Given a list of items with prices [10, 20, 30]
And a tax rate of 10%
When I calculate the total
Then the result should be 66.0
Scenario: Apply discount to total
Given a total amount of 100
And a discount of 15%
When I apply the discount
Then the final amount should be 85.0
Generated Tests:
def test_calculate_total_with_tax():
items = [10, 20, 30]
result = calculate_total(items, tax_rate=0.1)
assert result == 66.0
def test_apply_discount():
result = apply_discount(100, 15)
assert result == 85.0
🛠️ Advanced Usage
Custom Configuration
# agentops_ai/agentops_core/config.py
LLM_MODEL = "gpt-4"
LLM_TEMPERATURE = 0.1
OUTPUT_DIR = ".agentops"
LOG_LEVEL = "INFO"
Python API
from agentops_ai.agentops_core.orchestrator import AgentOrchestrator
# Create orchestrator
orchestrator = AgentOrchestrator()
# Run analysis
result = orchestrator.run_workflow("myfile.py")
# Access results
print(f"Requirements: {len(result.requirements)}")
print(f"Tests generated: {len(result.test_code)} lines")
print(f"Quality score: {result.quality_score}")
🔍 Troubleshooting
Common Issues
API Key Errors:
# Set your OpenAI API key
export OPENAI_API_KEY="your-key-here"
Permission Errors:
# Ensure write permissions
chmod 755 .agentops/
Import Errors:
# Reinstall dependencies
pip install -r requirements.txt
Getting Help
# Show detailed help
agentops help
# Check version
agentops version
# Validate setup
agentops status
📚 Documentation
🤝 Contributing
We welcome contributions! Please see our Contributing Guide for details.
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🆘 Support
- Issues: GitHub Issues
- Documentation: Project Docs
- Email: agentops_info@protonmail.com
AgentOps: Bridging technical implementation and business requirements through AI-powered analysis. 🚀
Metadata
Release files for agentops-ai 1.4.1
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 |
|---|---|---|---|---|
| agentops_ai-1.4.1.tar.gz | 198.4 kB | Without provenance | Details for agentops_ai-1.4.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentops_ai-1.4.1-py3-none-any.whl | Python 3 | none | any | Details for agentops_ai-1.4.1-py3-none-any.whl |
Total release size: 424.3 kB
Release files / agentops_ai-1.4.1.tar.gz
| Download URL | agentops_ai-1.4.1.tar.gz |
|---|---|
| Size | 198.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b4f79b9940f34157cdcc814660d81e523789af304fc21563b32ee248806b7164
|
|
BLAKE2b-256 checksum How to use checksums |
46906c760d9648ef7afdb22aa93419598c4b1b14c53d715a3598d4b81dc53f59
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.2
|
Release files / agentops_ai-1.4.1-py3-none-any.whl
| Download URL | agentops_ai-1.4.1-py3-none-any.whl |
|---|---|
| Size | 225.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
9b08ddd7beb89cdf347c5f5d9fda4f649565e299116dab8a855b8d518106c791
|
|
BLAKE2b-256 checksum How to use checksums |
93de6f7d89eeda117abf50cda48977f09744f166c297398c38a5880e820579fc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.2
|
Security for agentops-ai 1.4.1
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.