The official source code for "Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling" (ACL 2024, Findings)

Simple Code Creator & Debugger using LLM Reflection

Chat-with-Your-Documents is an AI-powered document chatbot using RAG, FastAPI, and React.js for local PDF question answering.

LLM Agent Routing Project: This project implements a routing system for user queries using LangChain and Groq's Gemma2-9b-It model. The system intelligently routes questions to arxiv, Wikipedia, or an LLM based on the context, offering efficient and targeted responses for AI research, human information, or general queries.

Synapse: A Collaborative AI Dashboard | Think Together. Build Faster.

NEWSimplify is a cutting-edge AI-powered news assistant built using Python and seamlessly integrating custom tools with the powerful Llama 3.1-70B large language model (LLM). This smart AI agent fetches and summarizes the latest news articles on any topic of interest, offering users a dynamic, chat-based interface for effortless interaction.

A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.

Source code for Automated Profile Inference with Language Model Agents

How to build LLM agents with Magentic

The Dating Agent is a voice-enabled AI assistant designed for matchmaking and general information, integrating with Locanto for enhanced browsing. With features like real-time chat and LLM-based tool orchestration, it provides a seamless user experience. 🛠️💬

Source code for our paper: "Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents".

Official code of "The Automated but Risky Game: Modeling Agent-to-Agent Negotiations and Transactions in Consumer Markets"

[ICML 2025] Official resources of "KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search".

The LLMAgentOps Toolkit is a repository that provides a foundational structure for building LLM Agent-based applications using the Semantic Kernel. It serves as a starting point for data scientists and developers, facilitating experimentation, evaluation, and deployment of LLM Agent-based applications to production.

MCP server built with Google’s Agent Development(ADK) Kit featuring multiple specialised agents that collaborate through intelligent routing. The system provides RESTful API endpoints for various capabilities including web searches, data analysis, and code generation while maintaining extensibility through a modular architecture

A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.

The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Bench

All the code and materials

[Up-to-date] Large Language Model Agent: A Survey on Methodology, Applications and Challenges