This repository delivers a customizable multi-agent framework simulating a taxi call center. It defines distinct AI agents: CustomerAgent to request rides, DispatchAgent to select drivers based on proximity, DriverAgent to confirm assignments and update statuses, and NotificationAgent for billing and messages. Agents interact through an orchestrator loop using OpenAI GPT calls and memory, enabling asynchronous dialogue, error handling, and logging. Developers can extend or adapt agent prompts, integrate real-time systems, and prototype AI-driven customer service and dispatch workflows with ease.

The LLM Agents Simulation Framework enables the design, execution, and analysis of simulated environments where autonomous agents interact through large language models. Users can register multiple agent instances, assign customizable prompts and roles, and specify communication channels such as message passing or shared state. The framework orchestrates simulation cycles, collects logs, and calculates metrics like turn-taking frequency, response latency, and success rates. It supports seamless integration with OpenAI, Hugging Face, and local LLMs. Researchers can create complex scenarios—negotiation, resource allocation, or collaborative problem-solving—to observe emergent behaviors. Extensible plugin architecture allows addition of new agent behaviors, environment constraints, or visualization modules, fostering reproducible experiments.

AgenticIR (Agentic Information Retrieval) provides a modular framework where LLM-powered agents autonomously plan and execute IR workflows. It enables the definition of agent roles — such as query generator, document retriever, and summarizer — running in customizable sequences. Agents can fetch raw text, refine queries based on intermediate results, and merge extracted passages into concise summaries. The framework supports multi-step pipelines including iterative web search, API-based data ingestion, and local document parsing. Developers can adjust agent parameters, plug in different LLMs, and fine-tune behavior policies. AgenticIR also offers logging, error handling, and parallel agent execution to accelerate large-scale information gathering. With a minimal code setup, researchers and engineers can prototype and deploy autonomous retrieval systems.

AgentFarm provides a comprehensive framework to coordinate diverse AI agents in a unified system. Users can script specialized agent behaviors in Python, assign roles (manager, worker, analyzer), and establish task queues for parallel processing. It integrates seamlessly with major LLM services (OpenAI, Azure OpenAI), enabling dynamic prompt routing and model selection. The built-in dashboard tracks agent status, logs interactions, and visualizes workflow performance. With modular plug-ins for custom APIs, developers can extend functionality, automate error handling, and monitor resource utilization. Ideal for deploying multi-stage pipelines, AgentFarm enhances reliability, scalability, and maintainability in AI-driven automation.