xai-org/xai-cookbook

A collection of pragmatic, real-world examples guiding you from basic to advanced use of xAI's Grok APIs.

What it solves

This cookbook provides a practical starting point for developers who want to build applications with Grok, the AI model from xAI. Instead of figuring out the SpaceXSI SDK from scratch, you get a set of complete, runnable examples that show how to accomplish real tasks — like turning an article into a podcast, creating a voice agent you can talk to, or analyzing live sentiment on posts from X. It saves you time by giving you copy‑paste code that teaches one idea end to end.

How it works

The repository is organised into three types of examples: Recipes (simple starting points), Guides (deeper technical insights), and Apps (full working applications). Each example lives in its own folder under examples/ and includes a README that explains what it teaches and how to run it. All TypeScript apps are standalone npm projects built with the SpaceXSI TypeScript SDK, requiring Node.js 22.13 or newer and an API key from the SpaceXSI Console. Python notebooks (for sentiment analysis) use Python 3.12, uv, and Jupyter. The code is meant to be copied, so you can drop it into your own project and adapt it.

Who it’s for

This is for developers who want to build with Grok and learn by example. The examples range from beginner to advanced, so it suits newcomers looking for a guided first project as well as experienced builders who need to quickly prototype a specific feature (voice, video generation, real‑time search, and more). Remember that the apps are for learning and are not production‑ready as they are.

Highlights

  • 25+ runnable examples covering podcasts, voice agents, video generation, sentiment analysis, and more.
  • Examples are labeled by difficulty (Beginner, Intermediate, Advanced) and grouped as Recipes, Guides, or Apps.
  • Each example is self‑contained and its README explains exactly what you’ll learn.
  • Includes practical guides on prompt caching and prompt injection defenses.
  • Code is copy‑ready for both TypeScript and Python ecosystems.
  • Contribution guidelines make it easy to add your own example.

Related

  • Project
    inulute/simplexity-ai-app

    A community-built desktop wrapper for P AI that adds native system features like global shortcuts and tray integration for faster AI search access.

  • Project
    aliyun/qwen-dianjin

    Qwen DianJin is an open‑source hub delivering finance‑focused LLMs, benchmarks, and skill libraries to enable reliable financial reasoning and agentic tool use.

  • Project
    NeuroDong/Ai-Review

    An AI-powered paper review system that provides structured feedback, visual layout analysis, and competitiveness ranking against other manuscripts.

  • Project
    FengZhenfei/carrel

    Carrel is a self‑hosted knowledge‑base platform for AI agents. It parses many document types, builds vector/keyword indexes and optional Neo4j knowledge graphs, and exposes a REST API (with a ready‑made search skill) that returns passages, images and graph evidence. Deployable via Docker Compose/systemd, it works with local or remote embedding, vision and chat models.