Articles tagged "llm"
Page 1 of 2
Build an MCP Server in Python 2026: Tools, Resources, and Prompts from Scratch
Build a working MCP (Model Context Protocol) server in Python from scratch. Covers tools, resources, and prompts using the FastMCP library. Connect to Claude Desktop and Claude Code in 2026.
Context Engineering 2026: AGENTS.md, CLAUDE.md, and .cursorrules That Actually Work
Context engineering tutorial 2026: write AGENTS.md, CLAUDE.md, and .cursorrules files that improve AI coding agent success rate from 30% to 90%. Real examples for Claude Code, Cursor, and Gemini CLI.
Vibe Coding 2026: Build a SaaS with Claude Code Without Writing Most of the Code
Vibe coding tutorial 2026: use Claude Code to build a real SaaS MVP — FastAPI backend, React frontend, Stripe payments, and Postgres — in hours instead of days. Includes prompt engineering tips and when to intervene manually.
Context Engineering for AI Agents 2026: The Complete Guide
Context engineering is the technique that raises AI agent success rates from 30% to 90%. Learn how to design context windows, implement RAG, manage memory, and build reliable AI agents in 2026.
Building a Local LLM Machine in 2026: Complete Hardware Guide
Complete 2026 guide to building a PC for running local LLMs. GPU VRAM requirements, RAM, storage, three full build examples from $800 to $6000, and Ollama/llama.cpp setup.
Build an MCP Server in Python: Complete Tutorial 2026
Learn to build a Model Context Protocol (MCP) server in Python from scratch. Expose tools, resources, and prompts to Claude and other LLMs with the official MCP SDK.
Embeddings Explained: What They Are and How to Use Them with Python and Ollama (2026)
Learn what embeddings are and how to use them with Python and Ollama for free. Generate embeddings with nomic-embed-text, compute cosine similarity, build semantic search, and store in pgvector.
LangGraph Tutorial 2026: Build Stateful AI Agents with Python
LangGraph tutorial 2026: build stateful AI agents in Python using StateGraph, nodes, edges, and checkpointers. Full ReAct agent example with tool calling and human-in-the-loop.
LiteLLM Tutorial 2026: Use OpenAI, Claude, and Ollama with One Python API
LiteLLM tutorial 2026: call OpenAI, Claude, Gemini, and Ollama with one unified Python API. Setup proxy server, fallbacks, cost tracking, and load balancing.
n8n + AI on Linux: Self-Hosted Workflow Automation with LLMs (2026)
Run n8n on Linux and automate workflows with AI and local LLMs. Install n8n via Docker, set up AI Agent nodes with Ollama, build real automations, and run as a systemd service. Free 2026 guide.