AgentSmith - Visual LangGraph Agent Builder

Powerful Features for Agent Development

Drag & Drop Builder

Design nodes, edges, and async flows using an intuitive visual interface powered by React Flow.

Python Code Export

Export your agent as a standalone Python module using LangGraph. Ready to run with no modifications.

Custom Tools

Define and reuse custom tools via code or natural language descriptions.

Multi-LLM Support

Built-in support for OpenAI, Anthropic, Hugging Face, and local LLMs like Llama.cpp.

State Management

Visually define TypedDict-based agent state and message schemas.

Code Editor

Edit node logic directly in a Monaco (VSCode-style) editor with syntax highlighting.

Built With Modern Technologies

Frontend

React
React Flow
TailwindCSS
Monaco Editor

Backend

Python 3.13
FastAPI
LangChain
LangGraph

LLM Support

OpenAI
Anthropic
HuggingFace
Local LLMs

Get Started in Minutes

Follow these simple steps to start building your first AI agent with AgentSmith.

1 Clone the Repository

                        git clone https://github.com/nMaroulis/agent-smith
                        
                        cd agent-smith

2 Set Up the Backend

                        cd backend
                        
                        uv venv .venv
                        
                        source .venv/bin/activate
                        
                        uv pip install -r requirements.txt

3 Set Up the Frontend

                        cd ../frontend
                        
                        npm install

4 Start the Application

In one terminal, start the backend:

                        cd backend
                        
                        python main.py

In another terminal, start the frontend:

                        cd frontend
                        
                        npm start

Build AI Agents Visually