LangSmith Studio

Status: ACTIVE (pulled from docs.langchain.com) Source: https://docs.langchain.com/oss/python/langgraph/studio Timestamp: 2026-05-11

Studio is a free visual interface for developing and testing LangChain agents from your local machine. It connects to your locally running agent to show each step: prompts, tool calls, results, and final output.

Prerequisites

• A LangSmith account (free signup at smith.langchain.com)
• A LangSmith API key (Create an API key in settings)
• To prevent data tracing, set LANGSMITH_TRACING=false in .env

Setup

1. Install CLI

pip install --upgrade "langgraph-cli[inmem]"

2. Prepare Your Agent

```python title="agent.py" from langchain.agents import create_agent

def send_email(to: str, subject: str, body: str): """Send an email""" return f"Email sent to {to}"

agent = create_agent( "gpt-5.4", tools=[send_email], system_prompt="You are an email assistant. Always use the send_email tool.", )

### 3. Create langgraph.json

```json
{
  "dependencies": ["."],
  "graphs": {
    "agent": "./src/agent.py:agent"
  },
  "env": ".env"
}

4. Install Dependencies

pip install langchain langchain-openai

5. Launch Studio

langgraph dev

Studio is accessible at: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024

Key Features

• Hot-reloading: Code changes reflected immediately
• Full trace inspection: Prompts, tool arguments, return values, token/latency metrics
• Exception capture: Errors with surrounding state
• Re-run from any step: Test changes without starting over
• Iterate on prompts: Edit and test prompt variations in real-time

Safari Note

Safari blocks localhost connections to Studio. Use --tunnel to access via secure tunnel.