A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

An immersive language learning feature. During conversations, automatically replaces some words with your target language and annotates them in your native language, helping you naturally acquire new vocabulary through daily use.

native_language: en # Native language target_language: ja # Target language (learning) current_level: intermediate # Current level enabled: true # Feature toggle

Skills are an increasingly powerful tool for creating custom AI workflows and agents, but where do they fit in the Claude stack? We explain what tool to use when - and how they all work together.

Date: November 13, 2025 | Reading time: 5 min | Category: Agents

Since introducing Skills, there's been interest in understanding how the various components of Claude's agentic ecosystem work together.

Learn how Skills can help you package your team's workflows, schemas, and business logic into reusable instructions that Claude Code loads automatically.

Category: Coding
Product: Claude Code
Date: December 2, 2025
Reading time: 5 min

Get better AI results with prompt engineering techniques from the team behind Claude.

Source: Claude Blog
Date: November 10, 2025
Reading time: 5 min

Brief one-line summary from AI analysis of what each pattern does.

• Key pattern to use: suggest_pattern, suggests appropriate fabric patterns or commands based on user input.**

1. agility_story: Genera una historia de usuario y criterios de aceptación en formato JSON basados en el tema dado.
2. ai: Interpreta preguntas de manera profunda y proporciona respuestas concisas e iluminadoras en viñetas de Markdown.
3. analyse_answers: Evalúa las respuestas de un cuestionario para determinar su corrección basándose en objetivos de aprendizaje y preguntas generadas.
4. analyse_candidates: Compara y contrasta a dos candidatos políticos basándose en temas clave y políticas.
5. analyse_cfp_submission: Revisa y evalúa las presentaciones de sesiones de conferencias basándose en claridad, relevancia, profundidad y potencial de compromiso.
6. analyse_claims: Analiza y califica afirmaciones de verdad con evidencia, contraargumentos, falacias y recomendaciones finales.