#828 · Primary category: AI Agents & Automation

digital-oracle

agent-skills ai-agent claude-code codex cursor finance kalshi llm macroeconomics market-data openclaw polymarket prediction-markets quantitative-finance

AI agent skill that answers macro questions — housing, gold, BTC, geopolitics — with probability estimates mined from 13 financial data sources (Polymarket, Kalshi, CFTC, SEC & more). For Claude Code / Cursor / Codex / OpenClaw. | 让 AI Agent 从金融数据中挖掘宏观趋势的数字先知

Project last updated:07/26/26

GitHub Stars

802

Forks

162

Contributors

1

License

MIT

Why we included this project

Digital Oracle is a skill that gives an AI agent a way to answer questions like "is gold a buy right now?" or "how likely is a conflict in the next year?" with a probability estimate instead of a gut feeling. It installs as a SKILL.md file plus a small Python package, and it pulls from 13 free data sources: prediction markets like Polymarket and Kalshi, Treasury yields, CFTC positioning, SEC insider filings, crypto derivatives, and China A-share fund flow. The agent combines those signals into a structured estimate with a reasoning chain. The setup stays light, most providers run on the Python standard library alone, and the skill keeps going even when one source fails. If you already work inside Claude Code, Cursor, Codex, or OpenClaw, this is a practical way to turn market data into forecasts you can defend.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category