langchain-ai/react-agent

LangGraph template for a simple ReAct agent

What it solves

This project provides a template for building a ReAct agent, a prototypical AI agent that can iteratively reason about a user's query and execute actions using external tools to find an answer.

How it works

Built with LangGraph, the agent follows a continuous loop: it analyzes a user query, decides on a necessary action, executes that action via a tool, observes the result, and repeats this cycle until it has enough information to provide a final response.

Who it’s for

Developers looking for a starting point to build flexible, tool-using AI agents that can be customized with specific Python functions as tools or different LLM providers like Anthropic and OpenAI.

Highlights

  • Tool Extensibility: Easily add new capabilities by defining custom Python functions in the tools configuration.
  • Model Flexibility: Supports multiple chat models, including Claude and GPT-4.
  • Interactive Debugging: Designed for LangGraph Studio, allowing developers to edit past states and rerun the app to debug specific nodes.
  • Integration: Works with LangSmith for detailed tracing and collaboration.

Related

  • Project
    langchain-ai/langgraph

    A low-level orchestration framework for building, managing, and deploying long-running, stateful AI agents with durable execution and human-in-the-loop capabilities.

  • Project
    tablegpt/tablegpt-agent

    A pre-built agent built on Langgraph that provides a user-friendly interface for interacting with TableGPT2 models for table-based question answering.

  • Project
    GiovanniPasq/agentic-rag-for-dummies

    A modular Agentic RAG framework using LangGraph that implements hierarchical indexing, multi-agent parallel retrieval, and human-in-the-loop query clarification.

  • Project
    cqzyys/lang-agent

    A visual configuration platform based on LangGraph that allows users to build complex AI agents using a drag-and-drop interface with customizable state variables for precise logic control.

  • Project
    JoshuaC215/agent-service-toolkit

    A full-stack toolkit for building and deploying AI agents using LangGraph, FastAPI, and Streamlit, providing a complete template from agent definition to user interface.