Kenjaku — Second Brain Generator  

<img src="docs/img/kenjaku.png" alt="Kenjaku — the Second Brain Generator's mascot" align="right" width="160">

# Kenjaku — Second Brain Generator &nbsp;<img src="docs/img/rag-inside.svg" alt="RAG inside" height="34" valign="middle">

*By Thomas Pierrain (VP Tech at [shodo](https://shodo.io/))*

[![Latest release](https://img.shields.io/github/v/release/tpierrain/second-brain-generator?sort=semver&display_name=tag&label=latest&color=7c4dff&style=flat-square&logo=github&logoColor=white)](https://github.com/tpierrain/second-brain-generator/releases/latest)
&nbsp;[![Engine: self-upgradable since v3.0.0](https://img.shields.io/badge/engine-self--upgradable%20since%20v3.0.0-651fff?style=flat-square&logo=rocket&logoColor=white)](#keeping-your-brain-up-to-date-its-engine)
&nbsp;[![Privacy: local by default](https://img.shields.io/badge/privacy-local%20by%20default-3d5afe?style=flat-square&logo=lock&logoColor=white)](#and-the-privacy-of-my-data)
&nbsp;[![Runs on macOS and Windows](https://img.shields.io/badge/runs%20on-macOS%20%C2%B7%20Windows-2979ff?style=flat-square)](#ready-to-try-it)

**Ask it like you'd ask a personal assistant — no dev skills required — and pull up any decision or piece of info from your work in seconds, always with the sources.**
*In Claude Desktop or on the command line, your call.*

**🧲 Search by meaning, not keywords.** Ask in your own words — even in another language than your notes — and it finds the right passage, with its source.

**🔒 Private by default, search à la carte.** Your notes are indexed **on your machine by default (local RAG & embedding) — nothing leaves it**. Or hand the job to the API of your choice, right down to your company's own endpoint: **you decide who touches your data**.

**🛟 Bulletproof & zero chores.** Backup, freshness, recovery after a glitch: **its** job, not yours. *You just have to talk.*

**🔄 Self-upgradable — new in v3.0.0.** Your brain keeps **its own engine** up to date: *ask in plain words, confirm,* and it pulls the latest search engine — **without ever touching a single one of your notes.** No terminal, no re-install. *([how it works](#keeping-your-brain-up-to-date-its-engine))*

**[🧠 What's a second brain?](#what-is-a-second-brain) · [🚀 Install yours now](#ready-to-try-it) · [📖 View the articles](#the-article-series)**

> 🧑 *"Where are we on the billing project — who owns what, and what's been decided?"*
>
> 🧠 *"At the January 15 team sync: the database was settled (PostgreSQL over MongoDB),
> and Jane Doe — platform Tech Lead — is pushing to get ahead of technical debt as early
> as sprint 1.*
> *→ decision of January 10 · → team sync of January 15"*

> 🧑 *"What does 'MEDDIC' mean — that thing the sales team keeps repeating in their meetings?"*
>
> 🧠 *"MEDDIC = the opportunity-qualification method adopted by sales: Metrics, Economic
> buyer, Decision criteria, Decision process, Identify pain, Champion. Introduced by John Smith (VP
> Sales) at the sales kickoff on February 12 to make the forecast more reliable.*
> *→ sales kickoff of February 12 · → sales playbook"*

Instead of digging through Slack, your emails, Google Drive and your meeting notes yourself, you
just ask — and your **second brain** answers right away, with the sources to back it up. It
**retrieves by meaning**, so you can ask in French about notes written in English (or the other way
around).

> ⚠️ This repo is **not** a ready-made brain: it's a **generator** that **produces** a **seed** (a
> skeleton) for you, which you grow into **one of your own**. We explain why below — and that's
> exactly what makes it useful.

---

## What is a "second brain"?

A **memory external to you**: your notes, your decisions and your work exchanges gathered in one
place, that you query in natural language and that answers you **instantly, with the sources to back
it up**.

A few properties define it:

- **It's yours.** Everything lives in a folder of notes (a *vault*) versioned in **your private git
  repo**. You're not renting from an online service: you own your data.
- **It remembers.** Every answer, every new piece of info is persisted (local git commit). Your
  brain builds up an actionable record — and can **follow you from one machine to another** as soon
  as you wire it to a remote repository (optional).
- **It keeps itself up to date — on its own.** Once you've connected your sources (Slack, Drive,
  email, calendar, meeting transcripts…), it **pulls in what's new automatically**, with **no explicit
  request from you**: you never have to tell it to "go sync". When you ask a question, it quietly
  catches up in the background and folds anything new into its answer.
- **It cites its sources.** No answers out of thin air: you can always trace back to the original
  note or message, with its date.

> 📂 **An open, human-readable format.** The substrate of your second brain is just a set of
> **Markdown (`.md`)** files — linked together with `[[wikilink]]` links where it makes sens

... (truncated)