Agent API Example — AI skill for Claude Code

AgentAPI

[](https://discord.gg/agora-999382051935506503) [](https://www.youtube.com/@kyegomez3242) [](https://www.linkedin.com/in/kye-g-38759a207/) [](https://x.com/kyegomezb)

[](https://github.com/kyegomez/swarms)

AgentAPI is a reference implementation for serving a [Swarms](https://github.com/kyegomez/swarms) agent as an HTTP service. It provides a minimal FastAPI application, a container image, and the configuration required to deploy a single agent to production.

Overview

The service exposes one agent, constructed once at application startup, behind two endpoints: a health check and a task execution endpoint. The complete application is contained in `api/api.py`.

from fastapi import FastAPI
from swarms import Agent

app = FastAPI()

agent = Agent(agent_name="Researcher", model_name="claude-sonnet-4-5", max_loops=1)


@app.get("/health")
def health():
    return {"status": "ok"}


@app.post("/run")
def run(body: dict):
    task = body.get("task")
    if task is None:
        return {"error": "Missing 'task' in request body"}
    output = agent.run(task)
    return {"output": output}

Repository layout:

Path	Description
api/api.py	FastAPI application and agent definition
api/requirements.txt	Python dependencie