🚀NEW COURSEVibe Coding AI Apps with Claude Code 🤖✨Enroll now

Our Latest Insights

Stay informed with the latest trends, tutorials, and breakthroughs in artificial intelligence from the DAIR.AI team.

Wiki Builder: A Claude Code Plugin for Building LLM Knowledge Bases

May 1, 2026

Wiki Builder: A Claude Code Plugin for Building LLM Knowledge Bases

Wiki Builder is an open-source Claude Code plugin that turns the LLM-knowledge-base workflow into a one-command setup. Scaffold a configurable wiki, point Claude at sources, and let the agent compile durable pages, indexes, and concept maps for you.

llmknowledge-basesai-agentsclaude-codepluginsworkflowtutorial
By Elvis Saravia
How to Build an LLM Knowledge Base

April 27, 2026

How to Build an LLM Knowledge Base

A hands-on guide to building a simple LLM knowledge base with raw markdown sources, a compiled wiki, reusable prompts, and an agent that keeps improving the knowledge base over time.

llmknowledge-basesai-agentsworkflowtutorial
By Elvis Saravia
LLM Knowledge Bases

April 3, 2026

LLM Knowledge Bases

A visual breakdown of Andrej Karpathy's approach to building personal knowledge bases powered by LLMs. Learn the 4-phase pipeline: ingest, compile, query, and maintain - with an interactive architecture diagram.

llmknowledge-basesai-toolsworkflowkarpathy
By Elvis Saravia
Nano Banana 2: Hands-On Guide and Comparison with Nano Banana Pro

February 26, 2026

Nano Banana 2: Hands-On Guide and Comparison with Nano Banana Pro

We tested Google's new Nano Banana 2 image generation model (gemini-3.1-flash-image-preview) against Nano Banana Pro across six experiments. Here's what improved in text rendering, object fidelity, search grounding, and what it means for your image generation workflows.

nano-banana-2nano-bananaimage-generationgeminiai-agentstutorialclaude-codegoogle-ai
By Elvis Saravia
Does AGENTS.md Actually Help Coding Agents? A New Study Has Answers

February 25, 2026

Does AGENTS.md Actually Help Coding Agents? A New Study Has Answers

ETH Zurich evaluates whether AGENTS.md and CLAUDE.md context files actually improve coding agent performance. Human-written files help (+4%), LLM-generated files hurt (-2%), and all files add 20%+ cost. Introduces the AGENTbench benchmark.

researchagents-mdcoding-agentsbenchmarksdeep-dive
By Elvis Saravia
LCM: What If the Engine Managed Context Instead of the Model?

February 17, 2026

LCM: What If the Engine Managed Context Instead of the Model?

LCM introduces deterministic context management for LLM agents, replacing model-written recursion with engine-controlled primitives. Its coding agent, Volt, outperforms Claude Code on the OOLONG long-context benchmark. Here's how it works and why it matters.

researchlcmlong-contextai-agentsdeep-dive
By Elvis Saravia
Recursive Language Models: Stop Stuffing the Context Window

February 16, 2026

Recursive Language Models: Stop Stuffing the Context Window

The next big thing might be recursive language models (RLMs). Instead of cramming text into the context window, RLMs treat text as an external environment that the model programs against. Here's why an 8B model can rival GPT-5 on long-context tasks.

researchrlmlong-contextai-agentsdeep-dive
By Elvis Saravia
Agentic Image Generation

February 3, 2026

Agentic Image Generation

A hands-on tutorial on using the image generator plugin in Claude Code. Learn how to generate images from text prompts, edit existing photos, create blog covers, product mockups, logos, and more - all from your terminal.

ai-agentstutorialclaude-codeimage-generation
By Elvis Saravia
Welcome to DAIR.AI Academy

February 1, 2026

Welcome to DAIR.AI Academy

We're excited to launch DAIR.AI Academy, a new learning platform designed to help you master AI through expert-led courses, hands-on projects, and a vibrant community of builders.

announcementaieducation
By Elvis Saravia