Quickstart
From an empty directory to an agent serving REST, MCP, and A2A — in about ten minutes.
1. Install
Python 3.10+ is required.
pip install fastagentic2. Wrap an agent in an endpoint
One decorator emits every protocol surface. This example uses PydanticAI; swap the adapter for LangGraph, CrewAI, or LangChain.
from fastagentic import App, agent_endpoint
from fastagentic.adapters import PydanticAIAdapter
from pydantic_ai import Agent
agent = Agent("openai:gpt-4o", system_prompt="You are a helpful research assistant.")
app = App(title="Research Service")
@agent_endpoint("/research", adapter=PydanticAIAdapter(agent))
async def research(query: str) -> str:
"""Answer research questions with cited sources."""
...3. Run it
# start the app (REST + MCP + A2A all come up together)
fastagentic run app:app --reload
# POST /research REST + streaming SSE
# MCP tool research for Claude / Cursor
# A2A skill research for other agents4. Go to production
Add durability and governance when you're ready. The production deployment guide walks through StepTracker backends, cost budgets, and observability.
Need FastAPI, LangGraph, or agent platform expertise?
Neul Labs — the team behind FastAgentic — takes on a limited number of consulting engagements each quarter. We help teams ship agents to production, fix broken LangGraph pipelines, and design governance for multi-tenant LLM platforms.