Your Personal AI Assistant That Never Forgets

2026-05-06 · Source: Matt Wolfe · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, extended

Summary

The content details the creation of a "second brain" knowledge management system featuring an AI-powered wiki, an integrated CRM, and a journaling function. This system, built using Obsidian for knowledge storage and Codeex for AI processing, addresses the limitations of traditional knowledge dumps by actively processing and interlinking information. It ingests web content like YouTube transcripts and articles into a raw folder, which an automated AI agent then processes into a structured wiki. The system also allows users to journal, with AI responses grounded in the wiki, past journal entries, and CRM data. A key feature is the ability to chat with the wiki for information retrieval and to automatically update CRM records for contacts. The setup involves configuring Obsidian's web clipper, setting up a Codeex project, and leveraging Andrej Karpathy's LLM wiki architecture, with Hostinger offering a simplified deployment option for AI agents like OpenClaw.

Key takeaway

For AI Engineers or knowledge workers looking to build a personalized, intelligent information system, consider implementing this Obsidian and Codeex-based second brain. Your ability to actively query, journal against, and manage contacts within a dynamically interlinked knowledge base will significantly enhance information recall and contextual understanding, moving beyond passive data storage. Start by setting up the core wiki architecture and then integrate journaling and CRM functionalities to maximize its utility.

Key insights

An AI-powered second brain integrates a wiki, CRM, and journaling for active knowledge processing and retrieval.

Principles

• Knowledge bases should be active, not passive storage.
• AI can interlink and contextualize diverse information sources.
• Automated processing enhances knowledge system utility.

Method

Build a knowledge management system by integrating Obsidian for content storage with Codeex for AI processing, using a web clipper for ingestion, and automating file processing and GitHub backups.

In practice

• Use Obsidian as a markdown organizer for your knowledge vault.
• Configure a web clipper to automatically ingest content into a "raw" folder.
• Automate AI processing of raw files and GitHub backups hourly.

Topics

• "Second Brain" System
• AI Knowledge Management
• Obsidian Integration
• LLM Wiki Architecture
• CRM & Journaling

Best for: AI Engineer, Software Engineer, AI Student

Related on AIssential

• Turn 10,994 Notes Into Memory - Paul Iusztin, Decoding AI & Louis-François Bouchard, Towards AI — A personalized, file-based AI research OS dynamically manages and evolves knowledge from diverse sources for complex projects.
• 7 Obsidian + Claude Code Commands for Your AI Second Brain — An AI second brain becomes powerful when structured notes are processed by an agent for complex information synthesis.
• Your AI forgets you every session. — A git-based markdown "second brain" provides persistent memory for AI agents, enabling knowledge compounding across sessions.
• Building Knowledge Immortality Through the Second Brain Architecture and The Curator App — Externalizing and compounding knowledge through an AI-maintained, interlinked markdown wiki ensures its persistence and growth.
• Your Brain Is Full. Here’s How AI Can Empty It — And Make You Smarter — Andrej Karpathy proposes using AI to externalize and organize personal knowledge, overcoming human information management limitations.
• Becoming a Company Where Every Team Shares One Brain — AI can integrate disparate internal knowledge systems to rapidly diagnose complex operational issues.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Matt Wolfe.