# Aegis Multi-Agent Framework
A powerful, extensible platform for building and deploying AI agent systems with seamless local LLM integration.
## Overview
The Aegis Multi-Agent Framework provides a robust foundation for creating sophisticated multi-agent systems while maintaining simplicity and flexibility. Perfect for both researchers and developers looking to build advanced AI agent applications.
### Key Features
- **Modular Agent Architecture**
- Plug-and-play agent components
- Customizable agent behaviors
- Extensible design patterns
- **Local LLM Integration**
- Native Ollama support
- Multiple model compatibility
- Optimized inference pipeline
- **Advanced Task Management**
- Real-time task monitoring
- Parallel task execution
- Priority-based scheduling
## Quick Start
### Installation
```bash
pip install aegis-framework
```
### Basic Usage
```python
from aegis_framework import MasterAIAgent, DesignAgent
# Initialize a master agent
agent = MasterAIAgent(model="gemma2:9b")
# Generate responses
response = agent.answer_question(
"What are the key principles of multi-agent systems?"
)
print(response)
# Create a specialized design agent
designer = DesignAgent(model="gemma2:9b")
design = designer.generate_new_design(
context="Create a microservices architecture",
constraints=["scalability", "fault-tolerance"]
)
print(design)
```
## Creating Custom Agents
```python
from aegis_framework import MasterAIAgent
from typing import Dict, Any, Optional
class DataAnalysisAgent(MasterAIAgent):
def __init__(
self,
model: str = "gemma2:9b",
custom_tasks: Optional[Dict[str, List[str]]] = None
):
super().__init__(model=model)
# Add specialized tasks
self.agent_task_map.update({
"data_analysis": [
"analyze data",
"statistical analysis",
"trend analysis",
"data visualization"
]
})
if custom_tasks:
self.agent_task_map.update(custom_tasks)
def analyze_data(
self,
data: str,
analysis_type: str = "comprehensive"
) -> Dict[str, Any]:
"""Perform data analysis with specified parameters."""
prompt = f"Analyze this {analysis_type} data: {data}"
return self.perform_task(prompt)
# Usage
analyst = DataAnalysisAgent()
results = analyst.analyze_data(
data="your_data_here",
analysis_type="statistical"
)
```
## System Requirements
- Python 3.7+
- Ollama (for local LLM support)
- 8GB+ RAM (recommended)
- CUDA-compatible GPU (optional)
## Example Scripts
The framework includes several example scripts to help you get started:
1. `basic_usage.py`: Demonstrates core functionality
2. `design_agent_example.py`: Shows advanced design capabilities
3. `custom_agent_example.py`: Illustrates custom agent creation
Run any example with the `--help` flag to see available options:
```bash
python examples/basic_usage.py --help
```
## Version History
Current Version: 0.1.15
Key Updates:
- Enhanced local LLM integration
- Improved design agent capabilities
- Better error handling
- More comprehensive examples
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## Contact
- **Author**: Metis Analytics
- **Email**: cjohnson@metisos.com
- **GitHub Issues**: [Report a bug](https://github.com/metisos/aegis_framework/issues)
## Acknowledgments
Special thanks to:
- The Ollama team for their excellent LLM runtime
- Our contributors and early adopters
- The open-source AI community
---
Made with ❤️ by Metis Analytics
Raw data
{
"_id": null,
"home_page": "https://github.com/metisos/aegis-framework",
"name": "aegis-framework",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": "ai, agents, llm, machine-learning, artificial-intelligence, multi-agent, ollama",
"author": "Metis Analytics",
"author_email": "cjohnson@metisos.com",
"download_url": "https://files.pythonhosted.org/packages/d4/d1/7f60d039011b809a3eb4d72f2195e350dfc7c95b8d30c2e5cb6294f4444d/aegis_framework-0.1.18.tar.gz",
"platform": null,
"description": "# Aegis Multi-Agent Framework\n\nA powerful, extensible platform for building and deploying AI agent systems with seamless local LLM integration.\n\n## Overview\n\nThe Aegis Multi-Agent Framework provides a robust foundation for creating sophisticated multi-agent systems while maintaining simplicity and flexibility. Perfect for both researchers and developers looking to build advanced AI agent applications.\n\n### Key Features\n\n- **Modular Agent Architecture**\n - Plug-and-play agent components\n - Customizable agent behaviors\n - Extensible design patterns\n\n- **Local LLM Integration**\n - Native Ollama support\n - Multiple model compatibility\n - Optimized inference pipeline\n\n- **Advanced Task Management**\n - Real-time task monitoring\n - Parallel task execution\n - Priority-based scheduling\n\n## Quick Start\n\n### Installation\n\n```bash\npip install aegis-framework\n```\n\n### Basic Usage\n\n```python\nfrom aegis_framework import MasterAIAgent, DesignAgent\n\n# Initialize a master agent\nagent = MasterAIAgent(model=\"gemma2:9b\")\n\n# Generate responses\nresponse = agent.answer_question(\n \"What are the key principles of multi-agent systems?\"\n)\nprint(response)\n\n# Create a specialized design agent\ndesigner = DesignAgent(model=\"gemma2:9b\")\ndesign = designer.generate_new_design(\n context=\"Create a microservices architecture\",\n constraints=[\"scalability\", \"fault-tolerance\"]\n)\nprint(design)\n```\n\n## Creating Custom Agents\n\n```python\nfrom aegis_framework import MasterAIAgent\nfrom typing import Dict, Any, Optional\n\nclass DataAnalysisAgent(MasterAIAgent):\n def __init__(\n self,\n model: str = \"gemma2:9b\",\n custom_tasks: Optional[Dict[str, List[str]]] = None\n ):\n super().__init__(model=model)\n \n # Add specialized tasks\n self.agent_task_map.update({\n \"data_analysis\": [\n \"analyze data\",\n \"statistical analysis\",\n \"trend analysis\",\n \"data visualization\"\n ]\n })\n \n if custom_tasks:\n self.agent_task_map.update(custom_tasks)\n \n def analyze_data(\n self,\n data: str,\n analysis_type: str = \"comprehensive\"\n ) -> Dict[str, Any]:\n \"\"\"Perform data analysis with specified parameters.\"\"\"\n prompt = f\"Analyze this {analysis_type} data: {data}\"\n return self.perform_task(prompt)\n\n# Usage\nanalyst = DataAnalysisAgent()\nresults = analyst.analyze_data(\n data=\"your_data_here\",\n analysis_type=\"statistical\"\n)\n```\n\n## System Requirements\n\n- Python 3.7+\n- Ollama (for local LLM support)\n- 8GB+ RAM (recommended)\n- CUDA-compatible GPU (optional)\n\n## Example Scripts\n\nThe framework includes several example scripts to help you get started:\n\n1. `basic_usage.py`: Demonstrates core functionality\n2. `design_agent_example.py`: Shows advanced design capabilities\n3. `custom_agent_example.py`: Illustrates custom agent creation\n\nRun any example with the `--help` flag to see available options:\n```bash\npython examples/basic_usage.py --help\n```\n\n## Version History\n\nCurrent Version: 0.1.15\n\nKey Updates:\n- Enhanced local LLM integration\n- Improved design agent capabilities\n- Better error handling\n- More comprehensive examples\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Contact\n\n- **Author**: Metis Analytics\n- **Email**: cjohnson@metisos.com\n- **GitHub Issues**: [Report a bug](https://github.com/metisos/aegis_framework/issues)\n\n## Acknowledgments\n\nSpecial thanks to:\n- The Ollama team for their excellent LLM runtime\n- Our contributors and early adopters\n- The open-source AI community\n\n---\n\nMade with \u2764\ufe0f by Metis Analytics\n",
"bugtrack_url": null,
"license": null,
"summary": "A comprehensive, extensible AI agent framework with local LLM integration",
"version": "0.1.18",
"project_urls": {
"Bug Tracker": "https://github.com/metisos/aegis-framework/issues",
"Homepage": "https://github.com/metisos/aegis-framework"
},
"split_keywords": [
"ai",
" agents",
" llm",
" machine-learning",
" artificial-intelligence",
" multi-agent",
" ollama"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "9582a707fa8f4a9cfa7cf164035d6debd0ecb57c01215f3872ef422c6fa87f61",
"md5": "347e0e9aed76d930c331e516619e5300",
"sha256": "78966ce348fe51b4b7aa57b685f1565781b9f07f4952c0179373b007e98475b9"
},
"downloads": -1,
"filename": "aegis_framework-0.1.18-py3-none-any.whl",
"has_sig": false,
"md5_digest": "347e0e9aed76d930c331e516619e5300",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 25935,
"upload_time": "2024-11-25T16:52:27",
"upload_time_iso_8601": "2024-11-25T16:52:27.527719Z",
"url": "https://files.pythonhosted.org/packages/95/82/a707fa8f4a9cfa7cf164035d6debd0ecb57c01215f3872ef422c6fa87f61/aegis_framework-0.1.18-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "d4d17f60d039011b809a3eb4d72f2195e350dfc7c95b8d30c2e5cb6294f4444d",
"md5": "ed2f5a1e85ce2dda145f4b363021ab6e",
"sha256": "5b2765662da4c4f31bada6505832451b0def5971371dffec2b306b29d2c1d430"
},
"downloads": -1,
"filename": "aegis_framework-0.1.18.tar.gz",
"has_sig": false,
"md5_digest": "ed2f5a1e85ce2dda145f4b363021ab6e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 26848,
"upload_time": "2024-11-25T16:52:28",
"upload_time_iso_8601": "2024-11-25T16:52:28.537420Z",
"url": "https://files.pythonhosted.org/packages/d4/d1/7f60d039011b809a3eb4d72f2195e350dfc7c95b8d30c2e5cb6294f4444d/aegis_framework-0.1.18.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-25 16:52:28",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "metisos",
"github_project": "aegis-framework",
"github_not_found": true,
"lcname": "aegis-framework"
}
JSON
