polyweather agent

    1

    A Python agent for simulated weather market trading using real-time forecasts, LLM analysis, and Kelly sizing.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    polyweather agent

    Example session with this skill installed

    Run a single trading cycle to analyze current weather markets and log the results to the paper ledger.

    • Read your context and instructions
    • Compiled the polyweather agent

    One trading cycle completed. Fetched weather data for 7 cities, scanned Polymarket Gamma API, and updated the local JSON ledger with simulated positions.

    Simulation Report: Cycle #0412

    MarketOutcomeForecast ProbMarket PriceEdgeActionKelly Size
    NYC Temp > 90°F (July 20)YES72%0.6111%BUY_YES$45.00
    London Rain > 5mm (July 21)NO85%0.787%BUY_NO$28.00
    Dubai Max Temp < 110°FYES15%0.22-7%SKIP$0.00
    Tokyo Humidity > 80%YES55%0.523%SKIP$0.00

    Cycle Statistics

    • Simulated Bankroll: $1,073.00
    • Active Paper Positions: 2
    • Daily P&L: +$12.50 (Simulated)
    • Dashboard Status: Active at http://localhost:5000

    Next steps

    • Open results/paper_trades.json to view the full trade history.
    • Run python main.py --ui-only to visualize performance trends in the browser.
    • Check logs/ for the detailed LLM reasoning behind the NYC and London recommendations.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Testing weather market strategies often requires manual data collection and complex probability modeling. This skill automates the entire pipeline, from fetching real-time meteorological data to simulating fractional Kelly-sized trades on Polymarket.

    What it does

    • Forecast aggregation pulls data from Open-Meteo and Apify for major global cities including New York, London, and Tokyo.
    • Market discovery scans the Polymarket Gamma API for active weather-related prediction markets.
    • Probability modeling estimates outcome likelihoods by comparing raw forecast data against current market odds.
    • LLM analysis uses OpenRouter models to evaluate market conditions and provide confidence-weighted trade recommendations.
    • Position sizing applies a quarter-Kelly criterion with a 5% edge threshold to manage a simulated bankroll.
    • Simulated hedging runs a secondary agent to identify and offset risk in open paper positions.

    How it works

    1. Install dependencies from the scripts/ folder and configure API keys for OpenRouter and Apify in a local .env file.
    2. Run the main.py script to start a trading cycle or launch the local web dashboard.
    3. Review simulated trade logs and performance metrics in the results/ directory.
    4. Adjust risk parameters like MAX_BET_FRACTION or STARTING_BANKROLL in the configuration files to test different strategies.

    Frameworks & tools

    The agent is built with Python 3.11+. It integrates with the Polymarket Gamma API, OpenRouter (supporting models like Hermes), Open-Meteo, and Flask for the local dashboard.

    Why this beats prompting it yourself

    Manual prompts cannot stay synced with live weather APIs or track a persistent ledger of simulated P&L. This skill handles the math for Kelly sizing and data ingestion, ensuring your "paper" bankroll stays consistent across sessions.

    Use cases

    • Test weather-market trading strategies without risking real capital.
    • Compare meteorological forecast accuracy against prediction market probabilities.
    • Audit LLM reasoning for financial decision-making in niche markets.
    • Build a historical dataset of weather market price movements and outcomes.

    Known limitations

    This is a paper-trading simulation only and cannot execute real orders or hold private keys. It is limited to specific tracked cities and requires an OpenRouter API key for the LLM analysis.

    Paper trading simulation only. Requires Python 3.11+. Limited to specific cities like NY, London, and Tokyo. No real wallet or execution support.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Requires

    Cloudflare
    Open Meteo
    Polymarket
    Python
    OpenRouter

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Environment Variables

    Allowed Hosts

    cdnjs.cloudflare.com
    api.open-meteo.com
    polymarket.com
    Listedtoday

    What's inside

    Frequently Asked Questions

    The skill automates the data-heavy pipeline of weather trading by fetching live forecasts, calculating trade probabilities via the Kelly criterion, and logging simulated P&L—tasks that are impossible to maintain through manual prompting alone.

    The purchase includes the full Python source code, a local Flask dashboard for monitoring performance, and pre-configured scripts for integrating with Open-Meteo and Polymarket APIs.

    No, this is a dedicated 'paper trading' environment designed for strategy testing; it executes trades within a simulated ledger and does not connect to private crypto wallets or execute live blockchain transactions.

    You will need Python 3.11+, an OpenRouter API key to power the LLM analysis, and an Apify API key for specific meteorological data scraping.

    The agent currently tracks major global hubs like New York, London, and Tokyo, but you can add additional cities by modifying the city coordinate list in the configuration file.

    The skill is built as a standalone Python application that can be integrated into larger agent workflows via its local API or by importing its core logic into existing Python-based AI frameworks.

    New in Trading & Investing