Tutorials
Prompt Caching in Provider-Agnostic Agents
Learn how prompt caching works in provider-agnostic agents and how to configure it to save costs and reduce latency.
Hermes Agent Architecture Explained
Learn how Hermes is structured as an always-on AI agent with an agent loop, context, memory, gateways, and cron jobs.
DuoBench: Best LLM pairs for coding?
I used DuoBench to compare Kimi K2.7, Kimi K2.6, GPT-5.5, and Claude Opus 4.8 on a recent CPython bug fix by quality per dollar.
How Pi Works: Agent Architecture, Tools, TUI, and Skills
A practical walkthrough of Pi coding agent architecture, from the core agent loop to tools, sessions, extensions, compaction, and skills.
Using Pi as a VPS Admin: Chat With Your Server via Telegram
Learn how to run a Raspberry Pi agent as an always-on VPS administrator that you can chat with on Telegram to manage services, fix issues, and keep server documentation up to date.
Run Hermes Agent on a $15/Month VPS
Set up Hermes Agent on a low-cost VPS with a predictable monthly model budget using Hetzner or OVH, Minimax, and an AI-assisted server setup skill.
FineWeb Dataset Overview: Building LLM Training Data at Scale
A deep dive into how Hugging Face created the FineWeb dataset — from Common Crawl extraction to filtering, deduplication, and FineWeb-Edu.
Hermes Agent Crash Course: Run an Always-On AI Assistant on a VPS
Learn how to install Hermes Agent on a secure VPS, connect it to Telegram, configure model providers, and use it as an always-on AI assistant.
Building an Agentic RAG Workflow in n8n with Open Models
Learn how to build an agentic RAG system in n8n using open models from Hugging Face, vector search, and MCP tools.
Pi Agent — The Minimalist Coding Harness That Adapts to YOU
An introduction to Pi Agent, a minimal terminal coding harness with four built-in tools and infinite extensibility.
DeepSeek V4: SOTA Coding Agent at 12x Lower Cost
DeepSeek V4 matches GPT-5.5 and Opus 4.7 on agentic coding benchmarks while costing 3x less. Learn how to set it up and use it for building web apps.
GPT-5.5 Benchmark Analysis: Is the Best Model in the World Worth the Price?
A no-hype breakdown of GPT-5.5 benchmarks, pricing, and how it compares to open models like Kimi and Minimax.
Kimi K2.6: The Open-Source Model Challenging GPT-5.4 and Claude Opus
A deep dive into Kimi K2.6, Moonshot AI latest open-source foundation model that beats GPT-5.4 and Claude Opus 4.6 on several key benchmarks, with a live demo of redesigning a Hugo blog.
Life Science Research with AI Agents
How to use OpenAI's Life Science Research plugin with Claude Code, Codex, and open source models for bioinformatics research.
Agent Skills Explained - Full Crash Course
Learn how to create, install, and share agent skills for Claude Code and other AI assistants. Skills are markdown files that teach agents specialized workflows and best practices.
MedGemma 1.5: Open-Source Medical AI with 3D Imaging Support
Learn how to use Google's MedGemma 1.5, an open-source 4B parameter model for medical image classification, 3D CT/MRI interpretation, and clinical Q&A
Build Your Own Claude Cowork: Open-Source Local Agent with Shell Access
Build an open-source alternative to Claude Cowork using OpenAI Agents SDK. Grant folder access, run shell commands, and let an AI agent handle tasks autonomously.
Build an Airline Customer Service Agent with OpenAI Agents SDK
Create a multi-agent customer service system with handoffs, shared context, and specialized tools using the OpenAI Agents SDK.
Getting Started with OpenAI Agents SDK
Introduction to smolagents: A Minimalist Agent Framework
HuggingChat: Multi-Model Chat with Omni Router + MCP Tools
Explore HuggingChat's Omni model router and how to connect MCP servers for tools
Build an AI Agent from Scratch with Python (No Frameworks)
Build a Multi-Agent Deep Research with Open Models + Firecrawl
Learn how to create a multi-agent deep research pipeline that uses smolagents, Firecrawl, and open models to scrape and research the web.
Create and Deploy a Remote MCP Server
Learn how to create and deploy a remote Model Context Protocol (MCP) server. This guide will show you how to expose your tools and resources to any AI assistant, whether it's a local model or a hosted service like OpenAI.
Authentication for MCP servers
Learn how to implement authentication for your remote Model Context Protocol (MCP) server using OAuth 2.1.
Introduction to LlamaIndex
In this lesson, we will go through an introduction of LlamaIndex. We will see what you can do with it, how it deals with RAG and its main components. We will then implement a RAG pipeline with their famous 5-liner, which allows you to chat with your data in 5 lines of code. This tutorial is based on the original [LlamaIndex documentation](https://docs.llamaindex.ai/en/stable/).
Generate a Newsletter with Exa Research Agent and CrewAI
In this tutorial, we use Exa and CrewAI to build a team of AI research agents who, given any topic, can perform the following tasks for us: research and summarize the latest news on the given topic, verify that the sources are correct and that the articles are relevant to the selected topic, compile the top stories into a newsletter using an HTML template.
How to automate Instagram Strategy with CrewAI
In this tutorial, you will learn how to create a crew of AI agents to automate your Instagram content strategy. In it, these agents are able to do the following things for you: perform research, find SEO keywords, create a calendar of posts, write the copy of each post, and generate the AI images for each post.
Crew AI Crash Course (Step by Step)
In this crash course, we will explore the basics of CrewAI. We will start by installing the necessary libraries and setting up our development environment. Then, we will create a simple crew using a sequential process. Finally, we will run the crew and see how it works.
Chat With a MySQL Database Using Python and LangChain
In this tutorial, we will learn how to chat with a MySQL (or SQLite) database using Python and LangChain. We will use the LangChain wrapper of `sqlalchemy` to interact with the database. We will also use the `langchain` package to create a custom chain that will allow us to chat with the database using natural language.
Full setup for Python development with virtual environments
In this article, we will show you how to setup a Python development environment for AI. We will go through installing the python version that you need, a version manager, a package manager, a code editor, and a notebook environment. By the end of this article, you will have a fully functional Python development environment.
Create a Machine Learning App with Python and Logistic Regression
In this article, we will create a web application that predicts whether a tumor is malignant or benign. To do that, we will first train a model using the Logistic Regression algorithm. Then we will use the model to predict the diagnosis of a tumor. And finally, we will use Streamlit to create the web application.
How to create a Chrome Extension with Manifest V3
In this article, we will see how to create a Chrome extension. The extension we will build uses the latest version of the Chrome Manifest (`manifest.json`), which is V3. If you don’t know what is the Manifest, don’t worry. We will see that in a second.
A Simple Explanation of Linear Regression (Example using R)
In this tutorial, we will discuss what linear regression is and how to use it. We will also use R to implement a linear regression model to a test dataset.