Streaming Research Agent

A real-time streaming research agent built with LangGraph that demonstrates multi-mode streaming (updates, custom, messages) for token-by-token output, custom status events, and node completion tracking. Includes a production-ready FastAPI SSE endpoint and LangSmith-traced evaluations.

Prerequisites

• Python 3.11+
• Anthropic API key
• LangSmith API key

Setup

python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env
# Edit .env with your API keys

Environment Variables

Variable	Required	Description
ANTHROPIC_API_KEY	Yes	Anthropic API key for Claude
LANGSMITH_API_KEY	Yes	LangSmith API key for tracing and evals
LANGSMITH_TRACING	Yes	Set to true to enable tracing

Running

Run the CLI streaming demo:

python streaming_agent.py

Run the FastAPI SSE endpoint:

uvicorn sse_endpoint:app --reload

To run evaluations:

python evals.py

Article

Your Users Think Your Agent Is Frozen