Agentic AI is a framework for building intelligent agents that can autonomously perform tasks by leveraging various tools and APIs. The system is designed to select the most suitable agent for a given task based on its capabilities and the tools it has access to.
- Agent Selection: The framework includes a mechanism to suggest the most appropriate agents for a given task using a pre-trained language model.
- Tool Integration: Agents can be equipped with various tools such as web search, calculator, and more to enhance their capabilities.
- Customizable Agents: Users can define their own agents with specific tools and functionalities.
- Clone the repository:
git clone https://github.com/ankushbisht01/Selecting-Agentic-AI- cd agentic-ai - Install the required dependencies:
pip install -r requirements.txt
- Run the inference script to suggest agents for a given task:
python -m src.inference
from src.inference import suggest_agents
suggestions = suggest_agents("I need to search the web")
for agent in suggestions:
print(agent['agent_name'], agent['score'])- LiveMCPBench: GitHub Repository
- Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems Paper