Example: Weather Agent

This example builds a fully functional weather agent with a custom Python capability that calls a weather API. By the end, you’ll have an agent package you can test locally and publish to the marketplace.

Project structure

Directoryweather-agent/
- agent.yaml
- agent.md
- Directorycapabilities/
  - Directoryweather/
    manifest.yaml
    prompt.md
    Dockerfile
    requirements.txt
    server.py

Step-by-step

agent.yaml

name: weather-agent
version: 1.0.0
display_name: Weather Agent
description: Answers weather questions with real-time data.
author: selu-examples
license: MIT
model:
  default: anthropic/claude-sonnet
  temperature: 0.5
routing:
  mode: inline
  triggers:
    - keyword: weather
    - keyword: forecast
    - intent: weather_query
  priority: 10
capabilities:
  - name: weather
    path: ./capabilities/weather
memory:
  session_ttl: 1800
  max_history: 30
  long_term: false

agent.md

You are Weather Agent, a helpful assistant that provides accurate,
real-time weather information.

## Instructions
- Use the `weather_lookup` tool to answer any weather question.
- Always ask for a location if the user doesn't provide one.
- Report temperature, conditions, humidity, and wind speed.

## Constraints
- Only answer weather-related questions.
- Never guess weather data — always use the tool.

manifest.yaml

name: weather
class: tool
display_name: Weather Lookup
description: Fetches current weather data from OpenWeatherMap.
version: 1.0.0

tools:
  - name: weather_lookup
    description: Get current weather conditions for a location.
    parameters:
      - name: location
        type: string
        required: true
        description: City name (e.g. "Berlin") or coordinates ("52.52,13.405").
      - name: units
        type: string
        required: false
        default: metric
        description: "metric or imperial."

resources:
  memory: 128Mi
  cpu: 0.25
  timeout: 10s

env:
  - name: OPENWEATHER_API_KEY
    required: true
    description: Your OpenWeatherMap API key.

server.py — the gRPC capability

import grpc, json, os, requests
from concurrent import futures
import capability_pb2 as pb2
import capability_pb2_grpc as pb2_grpc

API_KEY = os.environ["OPENWEATHER_API_KEY"]
BASE_URL = "https://api.openweathermap.org/data/2.5/weather"

class WeatherService(pb2_grpc.CapabilityServiceServicer):
    def Invoke(self, request, context):
        params = json.loads(request.parameters)
        location = params.get("location", "")
        units = params.get("units", "metric")

        try:
            resp = requests.get(BASE_URL, params={
                "q": location, "units": units,
                "appid": API_KEY,
            }, timeout=5)
            resp.raise_for_status()
            data = resp.json()

            result = {
                "location": data["name"],
                "temperature": data["main"]["temp"],
                "conditions": data["weather"][0]["description"],
                "humidity": data["main"]["humidity"],
                "wind_speed": data["wind"]["speed"],
            }
            return pb2.InvokeResponse(
                result=json.dumps(result), success=True
            )
        except Exception as e:
            return pb2.InvokeResponse(
                success=False, error=str(e)
            )

def serve():
    server = grpc.server(futures.ThreadPoolExecutor(max_workers=4))
    pb2_grpc.add_CapabilityServiceServicer_to_server(
        WeatherService(), server
    )
    server.add_insecure_port("[::]:50051")
    server.start()
    server.wait_for_termination()

if __name__ == "__main__":
    serve()

Dockerfile

FROM python:3.12-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY . .
USER 1000
EXPOSE 50051
CMD ["python", "server.py"]

Test it
Terminal window
```
export OPENWEATHER_API_KEY=your-key-here
selu dev .
```
Open http://localhost:4840 and ask: “What’s the weather in Tokyo?”

Next steps

Ready to publish? Check the Marketplace Guidelines.