Found something good?

Here is what I Found

TLDR; If you don't wanna read 3000 words of article simply give this to your agent https://github.com/codejunkie99/familiar-second-brain

Introduction

The problem is that most builders who try to build a second brain end up with a second filing cabinet.

Some set up Obsidian because the graph view looks incredible in YouTube demos.

Some try to wire Claude Code into their vault and never get past the initial setup friction.

Others jump straight into RAG pipelines and vector databases without understanding that the real problem is capture, not retrieval.

The result is always the same: a beautiful vault with 12 notes, a broken cron job, and a plugin graveyard.

If your goal is a knowledge system that actually compounds, you do not need RAG. You do not need a vector database. You do not need a cloud subscription.

You need to learn how to:

This article is the full build. Every skill file is included. Every cron expression is exact. Every architectural decision has a reason behind it.

My vault currently has 347 notes. A 50-file inbox batch processes in under 4 minutes with KIMI Work's Agent Swarm. The system has been running for 11 weeks.

Now let's build it.

Before the Theory, Here Is What It Actually Does

A raw note dropped into inbox/:

What KIMI Work's agent writes back into notes/wiki/:

The agent created a structured wiki page, linked it to your existing knowledge graph, and surfaced a contradiction you had not noticed. You dropped a messy note. You got structured thinking back.

That is the loop. Everything below is how it works.

Why I Built Familiar

The Claude Code + Obsidian setup went viral in early April 2026. Over 50,000 likes in under a week. The idea was simple: point an AI agent at a markdown vault and passive note storage becomes active infrastructure.

But it has a ceiling.

I wanted one vault that any agent could read from, write to, and maintain on a schedule. Local-first. Heavy lifting automated. I called it Familiar.

The Vault Architecture

Everything lives as plain .md files on disk. No proprietary database. No cloud sync.

Markdown is the one format every AI agent reads and writes without friction

Rule 7 is the one that matters most. Without it, the agent fills knowledge gaps with plausible-sounding information that looks exactly like your real thinking. Your vault starts generating confident fiction

Building It: The Decisions That Actually Matter

Step 1: Version control before anything else

Before mounting the vault in any agent, run this:

Step 2: Tiered memory, or why flat vaults become noise

A flat vault breaks within weeks. The agent accumulates assumptions from projects that closed two months ago and synthesises from context that no longer reflects your actual priorities

The agent reads the right tier for the right kind of question. Stale warm-tier project notes never contaminate cold-tier synthesis.

Step 3: The YAML frontmatter convention

Every wiki page carries metadata the agent writes and maintains:

he last_updated_by field is how you audit the vault during weekly lint passes:

Twenty minutes a week keeps the system clean.

Step 4: The inbox-first capture loop

The biggest friction in most note-taking setups is the gap between "I found something interesting" and "it is in my system, linked and usable." Familiar's inbox pattern collapses this:

Source files stay immutable. The agent creates a corresponding wiki page, but the origin is always traceable.

Inside the Familiar Build: Graph, Quick Capture, and Every Feature

The vault scaffold is the foundation. The features that make it feel like a real second brain rather than a folder of markdown files are in the layer built on top.

The Graph View

Familiar inherits Obsidian's [[wikilinks]] convention directly. Every backlink the agent creates becomes a bidirectional edge. Over time the graph reflects the actual shape of your thinking: which concepts cluster, which are heavily linked, where orphaned notes have never connected to anything.

The difference from vanilla Obsidian: the links are created by the agent, not by you manually. You write a raw note, the agent processes it, the graph grows. After 11 weeks and 347 notes, the clusters that have formed are not the ones I would have predicted when I started. That is the point.

How to read the graph:

Cmd+Shift+K: Instant Capture from Anywhere on Your Desktop

This is the feature that changed how I use the whole system day to day.

KIMI Work's agent has a global hotkey bar. Hit Cmd+Shift+K from anywhere on your Mac and a command bar drops down. You do not need to switch windows. You do not need to open Familiar. You do not need to touch the terminal.

You type a thought, a question, or a half-formed idea, then tell it where to put it:

You can also use the bar to query the vault on the fly:

KIMI Work's agent reads your vault via the local file mount, answers from your actual notes, and you can tell it to append the answer as a new note or open the source file directly.

Patterns I use with the quick bar every day:

The bar is modal and keyboard-native. For anyone who lives in the terminal, it feels exactly like the right abstraction.

Feature: Graph Health Skill

The graph health skill is an open issue actively in development. It runs on a weekly schedule and writes a full audit report back into the vault:

Run this alongside the weekly lint pass. The health report tells you exactly where the vault is drifting and what needs a human decision before the next processing run. This is the feature that turns a static graph view into an active maintenance loop.

Feature: Voice Memo Ingestion

Voice memo ingestion via a local Whisper instance is another open issue in active development. The intended flow:

This closes the last manual capture gap. Right now the only way to get a thought into the vault while away from a keyboard is to voice-memo it and paste it manually later. The Whisper skill removes that step entirely. Combined with Cmd+Shift+K, every capture surface is covered.

Feature: WebBridge Reading List Capture

Currently in development as an open issue. Instead of manually maintaining a reading list file, WebBridge monitors a bookmarks folder or a shared URL list, auto-crawls new additions on the morning cron, and drops the full extracted text into /inbox/. The reading list becomes a queue. The agent drains it every morning.

Feature: MCP Server Exposure

Feature: Wiki Template Library

A set of pre-built YAML frontmatter templates for the most common note types:

Every new page the agent creates will start from the right template instead of a blank file. Consistent structure means consistent graph quality from day one.

What Already Ships in the Repo Today

KIMI Work Is Not a Chatbot. It Is a Desktop Agent.

For a while I was self-hosting Kimi K2.6 on my Mac mini. Pulled the weights via Ollama, ran it entirely offline, pointed my vault at it.

Zero cloud. Zero API costs. It worked well enough for querying notes but it was still me manually invoking it every single time I wanted something processed.

KIMI Work changed that. It is the desktop application Moonshot built on top of K2.6, launched in June 2026.

The numbers that matter for this build:

The five capabilities

Skills: How KIMI Work's Agent Actually Runs Your Vault

KIMI Work uses a skills system. A skill is a markdown file that defines a workflow. The cron job is the schedule. The skill file is the playbook. You edit the skill. The cron stays the same.

Three skills run Familiar today.

Skill 1: Morning capture (0 7 * * *)

Skill 2: Inbox processing (0 8 * * *)

Skill 3: Weekly review (0 18 * * 5)

Cron reference:

Connecting Everything via MCP

KIMI Code CLI supports MCP. You can expose your Familiar vault as an MCP server, making it queryable from Claude Code, Cursor, any agent that speaks the protocol. One vault. Every agent.

Step 1: Start the notes-mcp server

Step 2: Register in KIMI Code CLI

Step 3: Verify the connection

Step 4: Query your vault from any agent session

The agent calls search_notes, reads the relevant wiki pages, and answers from your actual thinking, not its training data. The vault becomes infrastructure shared across every tool in your stack.

What Actually Compounds

This is what the 60-second demo videos never show.

Week 1

Week 4

Month 3

Three rules that keep vaults compounding instead of rotting:

Get the Repo

Familiar is open source. The vault scaffold, AGENTS.md template, all skill files, the desktop page skill, and cron configuration ship ready to use.

github.com/codejunkie99/familiar-second-brain

The full stack:

Drop questions in the replies. I read all of them.