Build an Infinite Context Engine: Claude + Obsidian Second Brain (Free Setup with Omi)
The video explains how to build a free āinfinite context engineā by wiring Claude (or other AI agents) to an Obsidian vault so every conversation starts with full context instead of fragmented native AI memory. The creator shows a color-coded Obsidian knowledge graph that links goals, projects, people, tools, and daily work, and introduces a three-part stack: Omi (open source capture layer that listens, records, and creates notes/tasks), Obsidian (local Markdown-based storage and graph), and Claude (reader/organizer that can restructure the vault). It covers organizing the vault with Tiago Forteās PARA (Projects, Areas, Resources, Archive), using a two-way loop where chats both read from and write back to the vault, and two ways to connect Claude to Obsidian (MCP Obsidian or a local folder), plus mentions community resources and Q&A about Hermes and multi-website SEO.
00:00 Claude Second Brain Intro
01:00 Obsidian Memory Graph Tour
02:48 Why Claude Memory Fails
04:31 Omi Capture Layer Setup
06:40 Obsidian Vault Basics
07:29 Claude Reads and Organizes
08:33 Markdown Graph and Tags
10:01 Connect Claude to Vault
11:37 PARA Structure Explained
12:52 Two Way Feedback Loop
13:37 Objections and Recap
15:39 Boardroom Resources Pitch
17:02 Live Q&A Wrap Up