For Agents
Pull a 7-day weather forecast for any latitude and longitude with no API key. Useful for agents that need temperature, precipitation, or wind data to drive a downstream decision.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Open-Meteo APIs, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Open-Meteo APIs.
Pull a 7-day hourly weather forecast for a latitude and longitude with selectable variables
Request daily aggregates such as max temperature, min temperature, and precipitation sum
Choose temperature, wind, and precipitation units to match the consuming application
GET STARTED
Use for: Get the 7-day weather forecast for these coordinates, Find tomorrow's max temperature in Berlin, Check whether it will rain in Paris on Saturday, Retrieve hourly wind speed for a sailing trip
Not supported: Does not provide severe-weather alerts, historical reanalysis, or air-quality data through this spec — use for 7-day hourly and daily forecast lookups only.
Open-Meteo is an open-source weather forecast service that exposes a free, no-key REST API for hourly and daily forecasts up to seven days ahead. The single GET /v1/forecast endpoint takes a latitude and longitude pair and a list of weather variables, and returns a structured time series for the requested location. The service is intended for open-source projects and non-commercial use, which keeps the agent integration cost effectively zero — no key handling, no quotas to negotiate, and a stable JSON response shape.
Switch timezone handling so timestamps return in UTC or the location's local time
Run the forecast call without any API key, making the integration safe for open-source distribution
Patterns agents use Open-Meteo APIs for, with concrete tasks.
★ Trip-Planning Forecast
Pull a 7-day forecast for a destination so a travel agent can recommend whether to go ahead with an outdoor activity. GET /v1/forecast accepts the destination's latitude and longitude plus a list of variables like temperature_2m and precipitation, and returns an hourly time series the agent can summarise into a plain-language outlook.
Call GET /v1/forecast for latitude 52.52, longitude 13.41 with daily=temperature_2m_max,precipitation_sum and return whether each of the next 7 days exceeds 5 mm of rain.
Operational Weather Trigger
Drive a downstream operational decision from a forecast variable — for example, postpone a delivery run when daily precipitation crosses a threshold. The single-endpoint design and no-key auth make it safe to call from a scheduled job without managing secrets, and the response is small enough to evaluate in line.
Each morning, call GET /v1/forecast for the warehouse coordinates with daily=precipitation_sum and pause outdoor pick-pack if today's value exceeds 10 mm.
Comparative Forecast Across Locations
Compare the 7-day forecast for several candidate locations to pick the best venue for an event. The agent fans out one GET /v1/forecast call per location and ranks the results by the variable that matters (lowest precipitation, highest temperature, lowest wind speed), without paying per call because the API is free for non-commercial use.
Call GET /v1/forecast for three candidate coordinates with daily=precipitation_sum and return the location with the lowest total over the next 5 days.
AI Agent Weather Tool
Expose Open-Meteo as a Jentic tool so an LLM agent can answer weather questions without bespoke HTTP code. Because the API has no auth, the Jentic flow is just a search and an execute, and the agent always sees a clean JSON response.
Search Jentic for 'get the 7-day weather forecast', load the GET /v1/forecast schema, and execute it for the user's coordinates returning the daily summary.
1 endpoints — open-meteo is an open-source weather forecast service that exposes a free, no-key rest api for hourly and daily forecasts up to seven days ahead.
METHOD
PATH
DESCRIPTION
/v1/forecast
7-day weather forecast for coordinates
/v1/forecast
7-day weather forecast for coordinates
Three things that make agents converge on Jentic-routed access.
Credential isolation
Open-Meteo's forecast endpoint requires no key. Jentic still proxies the call through its execution layer so the agent's request shape, retries, and logging are consistent with keyed APIs in the catalogue.
Intent-based discovery
Agents search Jentic with intents such as 'get the 7-day weather forecast' and receive the GET /v1/forecast operation with its full input schema, including the hourly and daily variable enums.
Time to first call
Direct Open-Meteo integration: 1-2 hours to read the docs and pick variables. Through Jentic: under 15 minutes — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Specific to using Open-Meteo APIs through Jentic.
What authentication does the Open-Meteo API use?
Open-Meteo's free forecast API requires no API key — GET /v1/forecast is a public endpoint. Through Jentic the call is still routed through the platform so the agent goes through the same search, load, and execute flow it uses for keyed APIs.
Can I get the forecast in Fahrenheit and a specific timezone?
Yes. GET /v1/forecast accepts temperature_unit, wind_speed_unit, precipitation_unit, and timezone query parameters, so the response can be returned in Fahrenheit, mph, inches, and a named timezone like 'America/New_York' without post-processing.
What are the rate limits for the Open-Meteo API?
Open-Meteo's documentation describes the free tier as suitable for non-commercial use with a fair-use limit roughly equivalent to 10,000 requests per day. Heavy commercial use should move to a paid plan or self-hosted deployment described on open-meteo.com.
How do I get a 7-day forecast for a coordinate through Jentic?
Run pip install jentic and search for 'get the 7-day weather forecast'. Jentic returns the GET /v1/forecast operation; load the schema, execute with latitude, longitude, and the desired hourly or daily variable list, and the call goes out without any key in the agent's context.
Is the Open-Meteo API free for commercial use?
Open-Meteo is free for open-source and non-commercial use. Commercial users should review the licensing on open-meteo.com and consider the paid tier or self-hosting before relying on the public endpoint for revenue-generating workloads.
Can I get historical weather data from this endpoint?
GET /v1/forecast returns forecast data starting from the present. Open-Meteo offers separate archive endpoints for historical reanalysis data; this spec only covers the forecast endpoint, so an agent that needs historical observations should add the archive API separately.