---

What is CodeOptiX?

CodeOptiX is the universal code optimization engine that improves coding agent experience with deep evaluations and optimization.

When AI coding agents dazzle with impressive code but leave you wondering about quality, maintainability, security, and reliability, CodeOptiX ensures proper behavior through evaluations, reflection, and self-improvement. Powered by GEPA optimization and Bloom scenario generation.

Built by Superagentic AI - Advancing the future of AI agent optimization and autonomous systems.

🚀 Key Capabilities

• 🔍 Deep Behavioral Evaluation - Comprehensive testing against security, reliability, and quality behaviors
• 🧬 GEPA Optimization Engine - Genetic-Pareto Evolution for automatic agent improvement
• 🌸 Bloom-Style Scenario Generation - Intelligent test case creation for thorough evaluation
• 🎯 Multi-Agent Support - Works with Claude Code, Codex, Gemini CLI, and custom agents
• 🔧 Multi-Provider LLM Support - OpenAI, Anthropic, Google, and Ollama (local models included!)
• ⚡ CI/CD Integration - Automated quality gates and GitHub Actions support

📋 Open Source Limitations

The open source version provides core evaluation capabilities. Advanced features like agent evolution and optimization have limited support. For full optimization capabilities tailored to your needs, please get in touch.

---

Quick Start

Installation

# Using uv (recommended)
uv pip install codeoptix

# Using pip
pip install codeoptix

Your First Evaluation

Option 1: Using Ollama (No API Key Required)

# Make sure Ollama is running
ollama serve

# Run evaluation with local model
codeoptix eval \
  --agent basic \
  --behaviors insecure-code \
  --llm-provider ollama

Option 2: Using Cloud Providers

# Set API key
export OPENAI_API_KEY="your-key-here"

# Run evaluation
codeoptix eval \
  --agent claude-code \
  --behaviors insecure-code \
  --llm-provider openai

---

Built-in Behaviors

Behavior	Description
insecure-code	Detects security vulnerabilities (SQL injection, XSS, hardcoded secrets)
vacuous-tests	Identifies low-quality tests (missing assertions, trivial tests)
plan-drift	Detects requirements misalignment and plan deviations

# Run multiple behaviors
codeoptix eval --behaviors insecure-code,vacuous-tests,plan-drift

---

Usage Modes

CLI Evaluation

codeoptix eval \
  --agent claude-code \
  --behaviors insecure-code \
  --llm-provider openai

CI/CD Integration

codeoptix ci \
  --agent codex \
  --behaviors insecure-code \
  --fail-on-failure

Python API

from codeoptix.adapters.factory import create_adapter
from codeoptix.evaluation import EvaluationEngine
from codeoptix.utils.llm import create_llm_client, LLMProvider

# Create adapter and evaluation engine
adapter = create_adapter("claude-code", config)
llm_client = create_llm_client(LLMProvider.OPENAI)
engine = EvaluationEngine(adapter, llm_client)

# Evaluate behaviors
results = engine.evaluate_behaviors(
    behavior_names=["insecure-code", "vacuous-tests"]
)

---

Development

Setup

# Clone the repository
git clone https://github.com/SuperagenticAI/codeoptix.git
cd codeoptix

# Install with uv (recommended)
uv sync --dev --extra docs

# Or with pip
pip install -e ".[dev,docs]"

Running Tests

# Run all tests
uv run pytest

# Run with coverage
uv run pytest --cov=codeoptix --cov-report=html

Code Quality

# Format code
uv run ruff format .

# Lint code
uv run ruff check .

# Install pre-commit hooks
uv run pre-commit install

---

Contributing

Contributions are welcome! Please see our Contributing Guide.

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Make your changes
4. Run tests and linting (uv run pytest && uv run ruff check .)
5. Commit your changes (git commit -m 'Add amazing feature')
6. Push to the branch (git push origin feature/amazing-feature)
7. Open a Pull Request

---

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

---

Support

• Documentation
• GitHub Issues

---