Side-by-side comparison of LangChain, LlamaIndex, AutoGen, CrewAI, Haystack, and Semantic Kernel for building LLM-powered applications and agent systems. Covers strengths, weaknesses, and when to pick each.
Build LLM programs in DSPy with declarative signatures, modules, and optimisers. Covers Predict, ChainOfThought, ReAct, BootstrapFewShot, COPRO, MIPRO, MIPROv2, and inference compilation.
Build production-grade LLM pipelines with Haystack 2.x. Covers components, the pipeline graph, indexing and querying, retrievers, generators, RAG patterns, and evaluation.
Model Context Protocol (MCP) framework overview. Covers client/server architecture, stdio vs SSE vs streamable HTTP transports, FastMCP, mcp-go, the Python and TypeScript SDKs, and comparison with custom tool servers.
Build LLM-powered applications with Microsoft Semantic Kernel. Covers the kernel, plugins, prompt templates, planners, function calling, Kernel Memory, Python and .NET SDKs.
Astro is a multi-page, content-first web framework with an islands architecture — server-render Markdown, MDX, and component pages to static HTML, then hydrate interactive widgets selectively with React, Vue, Svelte, or Solid.
Foundational React patterns — function components, JSX, props, hooks (useState, useEffect, useRef, useContext), list rendering, and form handling — with TypeScript throughout.
Type-safe React patterns — function components, prop types, children, event handlers, refs, generic components, polymorphic `as` props, and Zod-powered forms.
Hugging Face Transformers, LangChain, Google Gemini SDK, and LangSmith — practical reference for AI/ML frameworks and observability tools.
navigation
actions
cheat sheet pages