# Cortex Intelligence Engine 🧠⚡
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
[](tests/)
A **three-layer intelligence engine** designed for integration with [Open Agent Spec](https://github.com/openagents/openagents), providing advanced sensory processing, interpretation, and reasoning capabilities with **intelligent filtering and cost optimization**.
## 🎯 What is Cortex?
Cortex acts as an **intelligent filtering layer** between your OAS agents and expensive external LLMs. Instead of routing every request directly to external LLMs, Cortex:
1. **Processes input through Layer 1** (sensory processing)
2. **Analyzes with Layer 2** (internal intelligence - rule-based or ONNX models)
3. **Decides whether to trigger Layer 3** (external LLM) based on complexity and importance
4. **Provides intelligent responses** with suggested actions
**Result**: 60-80% cost reduction while maintaining intelligence! 💰🧠
## 🏗️ Architecture
Cortex implements a three-layer architecture:
```
OAS Agent → Cortex Intelligence Engine → External LLM (if needed)
↓
Layer 1: Sensory Processing (Text, Image, Audio)
↓
Layer 2: Internal Intelligence (Rule-based/ONNX/Local LLM)
↓
Layer 3: External LLM (OpenAI, Claude, etc.)
```
### Layer Breakdown
1. **Layer 1 - Sensory Processing**: Raw data processing for vision, audio, and text inputs
2. **Layer 2 - Interpretation**: Onboard ONNX/LLM for base-level data interpretation and reaction decisions
3. **Layer 3 - Reasoning**: External LLM vendor integration (OpenAI, Claude, etc.) for complex reasoning
## ✨ Features
- **🧠 Intelligent Filtering**: Automatically decides when to use expensive external LLMs
- **🤖 ONNX Integration**: Local neural network models for intelligent decision-making
- **💰 Cost Optimization**: 60-80% reduction in external API calls
- **⚡ Performance**: Sub-second responses for simple queries
- **🔄 Multi-modal Processing**: Handles text, images, and audio data
- **🎯 Smart Routing**: Determines when complex reasoning is needed
- **🔌 Flexible LLM Integration**: Supports multiple LLM providers with fallback mechanisms
- **🤖 Open Agent Spec Compatible**: Drop-in replacement for standard OAS intelligence engines
- **📊 Performance Monitoring**: Built-in metrics and status tracking
- **📦 Batch Processing**: Efficient processing of multiple inputs
- **⚙️ Configurable Processing Modes**: Reactive, proactive, and selective processing
## 🚀 Installation
```bash
# Clone the repository
git clone https://github.com/yourusername/cortex.git
cd cortex
# Install in development mode
pip install -e .
```
### 📋 Dependencies
- **Python 3.8+**
- **numpy** - Numerical computing
- **Pillow** - Image processing
- **onnxruntime** - Layer 2 ONNX models
- **aiohttp** - Async HTTP requests
- **pydantic** - Data validation
## ⚡ Quick Start
### Basic Usage
```python
import asyncio
from cortex import create_simple_cortex, create_cortex_function
async def main():
# Create a basic Cortex instance
cortex = create_simple_cortex(
openai_api_key="your_openai_key", # Optional
claude_api_key="your_claude_key", # Optional
enable_layer3=True
)
# Process some input
result = await cortex.process_input(
data="Analyze this urgent system alert!",
context="System monitoring detected anomaly"
)
print(f"Response: {result.final_response}")
print(f"Suggested actions: {result.suggested_actions}")
asyncio.run(main())
```
### 🤖 Open Agent Spec Integration
```python
from cortex import create_cortex_oas_intelligence, create_cortex_oas_function
# Configure like standard OAS intelligence
config = {
"type": "cortex",
"config": {
"processing_mode": "reactive",
"layer2_threshold": 0.6,
"enable_layer3": True,
"external_engine": "openai",
"external_model": "gpt-4"
}
}
# Create OAS-compatible intelligence engine
intelligence = create_cortex_oas_intelligence(config)
oas_function = create_cortex_oas_function(intelligence)
# Use in your OAS agent
response = await oas_function(
prompt="URGENT: System failure detected!",
context={"user_id": "123", "session_id": "456"}
)
print(f"Triggered Layer 3: {response['metadata']['triggered_layer3']}")
```
📖 **For detailed OAS integration guide, see [docs/OAS_INTEGRATION.md](docs/OAS_INTEGRATION.md)**
### 🧠 ONNX Integration
```python
from cortex import create_cortex_oas_intelligence, CortexOASConfig
# Configure with ONNX models for intelligent filtering
config = CortexOASConfig(
layer2_engine="onnx", # Enable ONNX models
layer2_threshold=0.6, # Confidence threshold
enable_layer3=True, # Allow external LLM calls
external_engine="openai",
external_model="gpt-4"
)
# Create intelligence engine with ONNX-powered Layer 2
intelligence = create_cortex_oas_intelligence(config)
# Process input - ONNX models will decide if Layer 3 is needed
response = await intelligence.process("URGENT: System failure detected!")
print(f"Triggered Layer 3: {response['metadata']['triggered_layer3']}")
```
📖 **For detailed ONNX integration guide, see [docs/ONNX_INTEGRATION.md](docs/ONNX_INTEGRATION.md)**
## 📚 Usage Examples
### 📝 Text Processing
```python
result = await cortex.process_input(
data="Emergency: Database server is down!",
sense_type="text",
task_type="incident_response"
)
```
### 🖼️ Image Processing
```python
from PIL import Image
image = Image.open("photo.jpg")
result = await cortex.process_input(
data=image,
sense_type="vision",
context="Security camera feed analysis"
)
```
### 🎵 Audio Processing
```python
import numpy as np
# Audio data as numpy array
audio_data = np.load("audio_sample.npy")
result = await cortex.process_input(
data=audio_data,
sense_type="audio",
task_type="sound_classification"
)
```
### 📦 Batch Processing
```python
inputs = [
{"data": "Message 1", "task_type": "general"},
{"data": "URGENT: Alert message", "task_type": "alert"},
{"data": image_data, "sense_type": "vision"}
]
results = await cortex.batch_process(inputs)
```
## ⚙️ Configuration
### 🔄 Processing Modes
| Mode | Behavior | Use Case |
|------|----------|----------|
| **REACTIVE** | Only Layer 3 when Layer 2 decides | Cost-effective, intelligent filtering |
| **PROACTIVE** | Always use all layers | Maximum intelligence, higher cost |
| **SELECTIVE** | Custom logic for Layer 3 | Custom filtering rules |
```python
from cortex.core import CortexConfig, ProcessingMode
config = CortexConfig(
processing_mode=ProcessingMode.REACTIVE,
layer2_threshold=0.6,
enable_layer3=True,
max_processing_time=30.0
)
cortex = Cortex(config)
```
### 🤖 LLM Provider Configuration
```python
from cortex.layers.layer3 import LLMConfig, LLMProvider
# OpenAI Configuration
openai_config = LLMConfig(
provider=LLMProvider.OPENAI,
api_key="your_key",
model="gpt-3.5-turbo",
max_tokens=1000,
temperature=0.7
)
# Claude Configuration
claude_config = LLMConfig(
provider=LLMProvider.CLAUDE,
api_key="your_key",
model="claude-3-sonnet-20240229",
max_tokens=1000,
temperature=0.7
)
cortex.add_llm_provider(openai_config, is_primary=True)
cortex.add_llm_provider(claude_config, is_primary=False) # Fallback
```
## 🤖 Open Agent Spec Integration
Cortex is designed as a **drop-in replacement** for standard OAS intelligence engines:
### Basic OAS Configuration
```yaml
name: "my_cortex_agent"
intelligence:
type: "cortex"
engine: "cortex-hybrid"
config:
processing_mode: "reactive"
layer2_threshold: 0.6
enable_layer3: true
external_engine: "openai"
external_model: "gpt-4"
external_endpoint: "https://api.openai.com/v1"
temperature: 0.7
max_tokens: 150
trigger_keywords: ["help", "urgent", "error", "assist"]
```
### Response Format
Cortex returns OAS-compatible responses:
```json
{
"success": true,
"response": "Analysis and response from Cortex",
"actions": ["suggested_action_1", "suggested_action_2"],
"metadata": {
"layers_used": ["layer1", "layer2", "layer3"],
"processing_time": 1.23,
"confidence": 0.85,
"cortex_stats": {
"total_requests": 100,
"layer2_only": 70,
"layer3_triggered": 30,
"average_response_time": 0.5
},
"triggered_layer3": true
},
"error": null
}
```
📖 **For comprehensive OAS integration guide, see [docs/OAS_INTEGRATION.md](docs/OAS_INTEGRATION.md)**
## 📊 Monitoring and Metrics
### Performance Statistics
```python
# Get current status
status = cortex.get_status()
print(f"Performance metrics: {status['cortex']['performance_metrics']}")
# Get processing history
history = cortex.get_recent_history(limit=10)
# Reset metrics
cortex.reset_metrics()
```
### 📈 Example Output
```
Performance Statistics:
Total Requests: 100
Layer 2 Only: 70 (70.0%)
Layer 3 Triggered: 30 (30.0%)
Average Response Time: 0.5s
```
## 🔔 Callback System
```python
async def on_high_priority(data):
print(f"High priority reaction detected: {data}")
cortex.add_callback("on_reaction_decision", on_high_priority)
```
## 🛠️ Development
### 🧪 Running Tests
```bash
pip install pytest pytest-asyncio
python -m pytest tests/ -v
```
### 🚀 Running Examples
```bash
# Basic usage examples
python examples/basic_usage.py
# OAS integration examples
python examples/oas_integration_example.py
```
### 📁 Project Structure
```
cortex/
├── cortex/
│ ├── __init__.py
│ ├── core.py # Main Cortex class
│ ├── oas_integration.py # OAS integration module
│ └── layers/
│ ├── __init__.py
│ ├── layer1.py # Sensory processing
│ ├── layer2.py # Interpretation and reaction decisions
│ └── layer3.py # External LLM reasoning
├── examples/
│ ├── basic_usage.py # Basic usage examples
│ └── oas_integration_example.py # OAS integration examples
├── docs/
│ └── OAS_INTEGRATION.md # Detailed OAS integration guide
├── tests/
│ └── test_basic.py # Test suite
├── pyproject.toml # Project configuration
└── README.md
```
## 🤝 Contributing
1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests for new functionality
5. Run the test suite
6. Submit a pull request
## 📄 License
MIT License - see LICENSE file for details.
## 📚 API Reference
### 🧠 Core Classes
- `Cortex`: Main intelligence engine
- `SenseLayer`: Layer 1 sensory processing
- `InterpretationLayer`: Layer 2 interpretation and reaction decisions
- `ReasoningLayer`: Layer 3 external LLM reasoning
### 🛠️ Utility Functions
- `create_simple_cortex()`: Quick Cortex setup
- `create_cortex_function()`: Create Open Agent Spec compatible function
- `create_cortex_oas_intelligence()`: Create OAS intelligence engine
- `create_cortex_oas_function()`: Create OAS-compatible function
### ⚙️ Configuration Classes
- `CortexConfig`: Main configuration
- `CortexOASConfig`: OAS-specific configuration
- `LLMConfig`: LLM provider configuration
- `ProcessingMode`: Processing mode enumeration
## 🎯 Use Cases
### 💰 Cost Optimization
- **Problem**: High LLM API costs for simple queries
- **Solution**: Cortex filters out simple requests
- **Result**: 60-80% cost reduction
### ⚡ Response Speed
- **Problem**: Slow responses for simple questions
- **Solution**: Layer 2 handles simple queries instantly
- **Result**: Sub-second responses for basic requests
### 🧠 Intelligent Routing
- **Problem**: All requests treated equally
- **Solution**: Cortex analyzes complexity and urgency
- **Result**: Appropriate resource allocation
### 🔄 Multi-modal Support
- **Problem**: Text-only intelligence engines
- **Solution**: Cortex handles text, images, and audio
- **Result**: Rich multi-modal interactions
---
**Cortex** - Intelligent filtering for Open Agent Spec agents. 🧠⚡
Raw data
{
"_id": null,
"home_page": null,
"name": "cortex-intelligence",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "ai, intelligence, onnx, open-agent-spec, machine-learning, neural-networks",
"author": null,
"author_email": "Andrew Whitehouse <andrew@primevector.com.au>",
"download_url": "https://files.pythonhosted.org/packages/84/e8/82fef2814c54e78f01ecf1e2b6fd32aeaf196b4d9b5eb08661e06b76eb9d/cortex_intelligence-0.1.0.tar.gz",
"platform": null,
"description": "# Cortex Intelligence Engine \ud83e\udde0\u26a1\n\n[](https://www.python.org/downloads/)\n[](https://opensource.org/licenses/MIT)\n[](tests/)\n\nA **three-layer intelligence engine** designed for integration with [Open Agent Spec](https://github.com/openagents/openagents), providing advanced sensory processing, interpretation, and reasoning capabilities with **intelligent filtering and cost optimization**.\n\n## \ud83c\udfaf What is Cortex?\n\nCortex acts as an **intelligent filtering layer** between your OAS agents and expensive external LLMs. Instead of routing every request directly to external LLMs, Cortex:\n\n1. **Processes input through Layer 1** (sensory processing)\n2. **Analyzes with Layer 2** (internal intelligence - rule-based or ONNX models)\n3. **Decides whether to trigger Layer 3** (external LLM) based on complexity and importance\n4. **Provides intelligent responses** with suggested actions\n\n**Result**: 60-80% cost reduction while maintaining intelligence! \ud83d\udcb0\ud83e\udde0\n\n## \ud83c\udfd7\ufe0f Architecture\n\nCortex implements a three-layer architecture:\n\n```\nOAS Agent \u2192 Cortex Intelligence Engine \u2192 External LLM (if needed)\n \u2193\n Layer 1: Sensory Processing (Text, Image, Audio)\n \u2193\n Layer 2: Internal Intelligence (Rule-based/ONNX/Local LLM)\n \u2193\n Layer 3: External LLM (OpenAI, Claude, etc.)\n```\n\n### Layer Breakdown\n\n1. **Layer 1 - Sensory Processing**: Raw data processing for vision, audio, and text inputs\n2. **Layer 2 - Interpretation**: Onboard ONNX/LLM for base-level data interpretation and reaction decisions\n3. **Layer 3 - Reasoning**: External LLM vendor integration (OpenAI, Claude, etc.) for complex reasoning\n\n## \u2728 Features\n\n- **\ud83e\udde0 Intelligent Filtering**: Automatically decides when to use expensive external LLMs\n- **\ud83e\udd16 ONNX Integration**: Local neural network models for intelligent decision-making\n- **\ud83d\udcb0 Cost Optimization**: 60-80% reduction in external API calls\n- **\u26a1 Performance**: Sub-second responses for simple queries\n- **\ud83d\udd04 Multi-modal Processing**: Handles text, images, and audio data\n- **\ud83c\udfaf Smart Routing**: Determines when complex reasoning is needed\n- **\ud83d\udd0c Flexible LLM Integration**: Supports multiple LLM providers with fallback mechanisms\n- **\ud83e\udd16 Open Agent Spec Compatible**: Drop-in replacement for standard OAS intelligence engines\n- **\ud83d\udcca Performance Monitoring**: Built-in metrics and status tracking\n- **\ud83d\udce6 Batch Processing**: Efficient processing of multiple inputs\n- **\u2699\ufe0f Configurable Processing Modes**: Reactive, proactive, and selective processing\n\n## \ud83d\ude80 Installation\n\n```bash\n# Clone the repository\ngit clone https://github.com/yourusername/cortex.git\ncd cortex\n\n# Install in development mode\npip install -e .\n```\n\n### \ud83d\udccb Dependencies\n\n- **Python 3.8+**\n- **numpy** - Numerical computing\n- **Pillow** - Image processing\n- **onnxruntime** - Layer 2 ONNX models\n- **aiohttp** - Async HTTP requests\n- **pydantic** - Data validation\n\n## \u26a1 Quick Start\n\n### Basic Usage\n\n```python\nimport asyncio\nfrom cortex import create_simple_cortex, create_cortex_function\n\nasync def main():\n # Create a basic Cortex instance\n cortex = create_simple_cortex(\n openai_api_key=\"your_openai_key\", # Optional\n claude_api_key=\"your_claude_key\", # Optional\n enable_layer3=True\n )\n \n # Process some input\n result = await cortex.process_input(\n data=\"Analyze this urgent system alert!\",\n context=\"System monitoring detected anomaly\"\n )\n \n print(f\"Response: {result.final_response}\")\n print(f\"Suggested actions: {result.suggested_actions}\")\n\nasyncio.run(main())\n```\n\n### \ud83e\udd16 Open Agent Spec Integration\n\n```python\nfrom cortex import create_cortex_oas_intelligence, create_cortex_oas_function\n\n# Configure like standard OAS intelligence\nconfig = {\n \"type\": \"cortex\",\n \"config\": {\n \"processing_mode\": \"reactive\",\n \"layer2_threshold\": 0.6,\n \"enable_layer3\": True,\n \"external_engine\": \"openai\",\n \"external_model\": \"gpt-4\"\n }\n}\n\n# Create OAS-compatible intelligence engine\nintelligence = create_cortex_oas_intelligence(config)\noas_function = create_cortex_oas_function(intelligence)\n\n# Use in your OAS agent\nresponse = await oas_function(\n prompt=\"URGENT: System failure detected!\",\n context={\"user_id\": \"123\", \"session_id\": \"456\"}\n)\n\nprint(f\"Triggered Layer 3: {response['metadata']['triggered_layer3']}\")\n```\n\n\ud83d\udcd6 **For detailed OAS integration guide, see [docs/OAS_INTEGRATION.md](docs/OAS_INTEGRATION.md)**\n\n### \ud83e\udde0 ONNX Integration\n\n```python\nfrom cortex import create_cortex_oas_intelligence, CortexOASConfig\n\n# Configure with ONNX models for intelligent filtering\nconfig = CortexOASConfig(\n layer2_engine=\"onnx\", # Enable ONNX models\n layer2_threshold=0.6, # Confidence threshold\n enable_layer3=True, # Allow external LLM calls\n external_engine=\"openai\",\n external_model=\"gpt-4\"\n)\n\n# Create intelligence engine with ONNX-powered Layer 2\nintelligence = create_cortex_oas_intelligence(config)\n\n# Process input - ONNX models will decide if Layer 3 is needed\nresponse = await intelligence.process(\"URGENT: System failure detected!\")\nprint(f\"Triggered Layer 3: {response['metadata']['triggered_layer3']}\")\n```\n\n\ud83d\udcd6 **For detailed ONNX integration guide, see [docs/ONNX_INTEGRATION.md](docs/ONNX_INTEGRATION.md)**\n\n## \ud83d\udcda Usage Examples\n\n### \ud83d\udcdd Text Processing\n\n```python\nresult = await cortex.process_input(\n data=\"Emergency: Database server is down!\",\n sense_type=\"text\",\n task_type=\"incident_response\"\n)\n```\n\n### \ud83d\uddbc\ufe0f Image Processing\n\n```python\nfrom PIL import Image\n\nimage = Image.open(\"photo.jpg\")\nresult = await cortex.process_input(\n data=image,\n sense_type=\"vision\",\n context=\"Security camera feed analysis\"\n)\n```\n\n### \ud83c\udfb5 Audio Processing\n\n```python\nimport numpy as np\n\n# Audio data as numpy array\naudio_data = np.load(\"audio_sample.npy\")\nresult = await cortex.process_input(\n data=audio_data,\n sense_type=\"audio\",\n task_type=\"sound_classification\"\n)\n```\n\n### \ud83d\udce6 Batch Processing\n\n```python\ninputs = [\n {\"data\": \"Message 1\", \"task_type\": \"general\"},\n {\"data\": \"URGENT: Alert message\", \"task_type\": \"alert\"},\n {\"data\": image_data, \"sense_type\": \"vision\"}\n]\n\nresults = await cortex.batch_process(inputs)\n```\n\n## \u2699\ufe0f Configuration\n\n### \ud83d\udd04 Processing Modes\n\n| Mode | Behavior | Use Case |\n|------|----------|----------|\n| **REACTIVE** | Only Layer 3 when Layer 2 decides | Cost-effective, intelligent filtering |\n| **PROACTIVE** | Always use all layers | Maximum intelligence, higher cost |\n| **SELECTIVE** | Custom logic for Layer 3 | Custom filtering rules |\n\n```python\nfrom cortex.core import CortexConfig, ProcessingMode\n\nconfig = CortexConfig(\n processing_mode=ProcessingMode.REACTIVE,\n layer2_threshold=0.6,\n enable_layer3=True,\n max_processing_time=30.0\n)\n\ncortex = Cortex(config)\n```\n\n### \ud83e\udd16 LLM Provider Configuration\n\n```python\nfrom cortex.layers.layer3 import LLMConfig, LLMProvider\n\n# OpenAI Configuration\nopenai_config = LLMConfig(\n provider=LLMProvider.OPENAI,\n api_key=\"your_key\",\n model=\"gpt-3.5-turbo\",\n max_tokens=1000,\n temperature=0.7\n)\n\n# Claude Configuration\nclaude_config = LLMConfig(\n provider=LLMProvider.CLAUDE,\n api_key=\"your_key\",\n model=\"claude-3-sonnet-20240229\",\n max_tokens=1000,\n temperature=0.7\n)\n\ncortex.add_llm_provider(openai_config, is_primary=True)\ncortex.add_llm_provider(claude_config, is_primary=False) # Fallback\n```\n\n## \ud83e\udd16 Open Agent Spec Integration\n\nCortex is designed as a **drop-in replacement** for standard OAS intelligence engines:\n\n### Basic OAS Configuration\n\n```yaml\nname: \"my_cortex_agent\"\nintelligence:\n type: \"cortex\"\n engine: \"cortex-hybrid\"\n config:\n processing_mode: \"reactive\"\n layer2_threshold: 0.6\n enable_layer3: true\n external_engine: \"openai\"\n external_model: \"gpt-4\"\n external_endpoint: \"https://api.openai.com/v1\"\n temperature: 0.7\n max_tokens: 150\n trigger_keywords: [\"help\", \"urgent\", \"error\", \"assist\"]\n```\n\n### Response Format\n\nCortex returns OAS-compatible responses:\n\n```json\n{\n \"success\": true,\n \"response\": \"Analysis and response from Cortex\",\n \"actions\": [\"suggested_action_1\", \"suggested_action_2\"],\n \"metadata\": {\n \"layers_used\": [\"layer1\", \"layer2\", \"layer3\"],\n \"processing_time\": 1.23,\n \"confidence\": 0.85,\n \"cortex_stats\": {\n \"total_requests\": 100,\n \"layer2_only\": 70,\n \"layer3_triggered\": 30,\n \"average_response_time\": 0.5\n },\n \"triggered_layer3\": true\n },\n \"error\": null\n}\n```\n\n\ud83d\udcd6 **For comprehensive OAS integration guide, see [docs/OAS_INTEGRATION.md](docs/OAS_INTEGRATION.md)**\n\n## \ud83d\udcca Monitoring and Metrics\n\n### Performance Statistics\n\n```python\n# Get current status\nstatus = cortex.get_status()\nprint(f\"Performance metrics: {status['cortex']['performance_metrics']}\")\n\n# Get processing history\nhistory = cortex.get_recent_history(limit=10)\n\n# Reset metrics\ncortex.reset_metrics()\n```\n\n### \ud83d\udcc8 Example Output\n\n```\nPerformance Statistics:\n Total Requests: 100\n Layer 2 Only: 70 (70.0%)\n Layer 3 Triggered: 30 (30.0%)\n Average Response Time: 0.5s\n```\n\n## \ud83d\udd14 Callback System\n\n```python\nasync def on_high_priority(data):\n print(f\"High priority reaction detected: {data}\")\n\ncortex.add_callback(\"on_reaction_decision\", on_high_priority)\n```\n\n## \ud83d\udee0\ufe0f Development\n\n### \ud83e\uddea Running Tests\n\n```bash\npip install pytest pytest-asyncio\npython -m pytest tests/ -v\n```\n\n### \ud83d\ude80 Running Examples\n\n```bash\n# Basic usage examples\npython examples/basic_usage.py\n\n# OAS integration examples\npython examples/oas_integration_example.py\n```\n\n### \ud83d\udcc1 Project Structure\n\n```\ncortex/\n\u251c\u2500\u2500 cortex/\n\u2502 \u251c\u2500\u2500 __init__.py\n\u2502 \u251c\u2500\u2500 core.py # Main Cortex class\n\u2502 \u251c\u2500\u2500 oas_integration.py # OAS integration module\n\u2502 \u2514\u2500\u2500 layers/\n\u2502 \u251c\u2500\u2500 __init__.py\n\u2502 \u251c\u2500\u2500 layer1.py # Sensory processing\n\u2502 \u251c\u2500\u2500 layer2.py # Interpretation and reaction decisions\n\u2502 \u2514\u2500\u2500 layer3.py # External LLM reasoning\n\u251c\u2500\u2500 examples/\n\u2502 \u251c\u2500\u2500 basic_usage.py # Basic usage examples\n\u2502 \u2514\u2500\u2500 oas_integration_example.py # OAS integration examples\n\u251c\u2500\u2500 docs/\n\u2502 \u2514\u2500\u2500 OAS_INTEGRATION.md # Detailed OAS integration guide\n\u251c\u2500\u2500 tests/\n\u2502 \u2514\u2500\u2500 test_basic.py # Test suite\n\u251c\u2500\u2500 pyproject.toml # Project configuration\n\u2514\u2500\u2500 README.md\n```\n\n## \ud83e\udd1d Contributing\n\n1. Fork the repository\n2. Create a feature branch\n3. Make your changes\n4. Add tests for new functionality\n5. Run the test suite\n6. Submit a pull request\n\n## \ud83d\udcc4 License\n\nMIT License - see LICENSE file for details.\n\n## \ud83d\udcda API Reference\n\n### \ud83e\udde0 Core Classes\n\n- `Cortex`: Main intelligence engine\n- `SenseLayer`: Layer 1 sensory processing\n- `InterpretationLayer`: Layer 2 interpretation and reaction decisions\n- `ReasoningLayer`: Layer 3 external LLM reasoning\n\n### \ud83d\udee0\ufe0f Utility Functions\n\n- `create_simple_cortex()`: Quick Cortex setup\n- `create_cortex_function()`: Create Open Agent Spec compatible function\n- `create_cortex_oas_intelligence()`: Create OAS intelligence engine\n- `create_cortex_oas_function()`: Create OAS-compatible function\n\n### \u2699\ufe0f Configuration Classes\n\n- `CortexConfig`: Main configuration\n- `CortexOASConfig`: OAS-specific configuration\n- `LLMConfig`: LLM provider configuration\n- `ProcessingMode`: Processing mode enumeration\n\n## \ud83c\udfaf Use Cases\n\n### \ud83d\udcb0 Cost Optimization\n- **Problem**: High LLM API costs for simple queries\n- **Solution**: Cortex filters out simple requests\n- **Result**: 60-80% cost reduction\n\n### \u26a1 Response Speed\n- **Problem**: Slow responses for simple questions\n- **Solution**: Layer 2 handles simple queries instantly\n- **Result**: Sub-second responses for basic requests\n\n### \ud83e\udde0 Intelligent Routing\n- **Problem**: All requests treated equally\n- **Solution**: Cortex analyzes complexity and urgency\n- **Result**: Appropriate resource allocation\n\n### \ud83d\udd04 Multi-modal Support\n- **Problem**: Text-only intelligence engines\n- **Solution**: Cortex handles text, images, and audio\n- **Result**: Rich multi-modal interactions\n\n---\n\n**Cortex** - Intelligent filtering for Open Agent Spec agents. \ud83e\udde0\u26a1\n",
"bugtrack_url": null,
"license": null,
"summary": "A three-layer intelligence engine with ONNX integration for Open Agent Spec",
"version": "0.1.0",
"project_urls": {
"Bug Tracker": "https://github.com/prime-vector/cortex/issues",
"Documentation": "https://github.com/prime-vector/cortex#readme",
"Homepage": "https://github.com/prime-vector/cortex",
"Repository": "https://github.com/prime-vector/cortex"
},
"split_keywords": [
"ai",
" intelligence",
" onnx",
" open-agent-spec",
" machine-learning",
" neural-networks"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "e907b746c10383daea7cf2311de24d838aa4102ecd71a5079c2b0fbab8c34862",
"md5": "31b118b19616f07cc89096c09316576c",
"sha256": "be7bf2f3af3d1910fb9223ad78d129df7b267f3c60b60f2147b7933bf51c8c1b"
},
"downloads": -1,
"filename": "cortex_intelligence-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "31b118b19616f07cc89096c09316576c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 31496,
"upload_time": "2025-08-03T02:25:24",
"upload_time_iso_8601": "2025-08-03T02:25:24.389994Z",
"url": "https://files.pythonhosted.org/packages/e9/07/b746c10383daea7cf2311de24d838aa4102ecd71a5079c2b0fbab8c34862/cortex_intelligence-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "84e882fef2814c54e78f01ecf1e2b6fd32aeaf196b4d9b5eb08661e06b76eb9d",
"md5": "455af14c835fe7e733cf9f60614d8b27",
"sha256": "35a8b71619c3ccf383689e592e5f016a3396622d73e5213b6613363544636b72"
},
"downloads": -1,
"filename": "cortex_intelligence-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "455af14c835fe7e733cf9f60614d8b27",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 51192,
"upload_time": "2025-08-03T02:25:26",
"upload_time_iso_8601": "2025-08-03T02:25:26.091904Z",
"url": "https://files.pythonhosted.org/packages/84/e8/82fef2814c54e78f01ecf1e2b6fd32aeaf196b4d9b5eb08661e06b76eb9d/cortex_intelligence-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-03 02:25:26",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "prime-vector",
"github_project": "cortex",
"github_not_found": true,
"lcname": "cortex-intelligence"
}
JSON
