Runs on Claude Code · MIT License

A second brAIn that
learns with you

Powered by Claude

Lore uses Claude to research your goals, write knowledge articles, and quiz you on what you've learned — all in plain Markdown files you own.

claude · my-brain
/learn
Reading goals.md...
Goal 1: Master personal finance concepts
Gap: No articles on mutual funds or SIP yet
Searching: "mutual funds India beginner free guide"
✓ Found: Freefincal — Beginner's Guide
✓ Writing brain/wiki/mutual-funds.md
✓ Trivia (Science): Polar bears have jet-black skin...
✓ Done — 2 articles written, 1 trivia added

Built differently

Not a note-taking app. Not a reader. An agent that builds knowledge for you — organised by what you're trying to achieve.

Goals-first

Every /learn run starts from your goals.md — not a random topic feed. Claude reads what you're working toward and finds resources aligned to it.

Agent does the work

You set intent. Claude searches, reads, summarises, writes wiki articles, and links them together. You read, not research.

Files you own

Everything is plain Markdown in a git repo. No proprietary format, no lock-in, no server storing your thoughts. Fork it, back it up, share it.

Backlinked wiki

Articles connect to each other with [[slug]] backlinks. /lint keeps the graph healthy — finds orphans, stale index lines, and missing links.

Get started in 4 steps

You need Claude Code and an Anthropic API key. Everything else is already in the template.

1

Install Claude Code

Claude Code is the CLI that powers Lore's agent commands.

npm install -g @anthropic-ai/claude-code
2

Use this template

Click "Use this template" on GitHub, or clone directly.

git clone https://github.com/pradnk/lore my-brain
cd my-brain
3

Set your goals

Edit brain/self/goals.md. Add 1–3 specific goals with a Why and measurable signals. The more concrete, the better /learn performs.

# Goals

## Goal 1 — Learn machine learning
- Why: Career shift into ML engineering
- Signals: Complete fast.ai; build 2 projects
- Status: in progress
4

Fill in your profile

optional

Edit brain/self/profile.md — your background, working style, and values. This gives /ask and /review better context about who you are and how you think.

# Profile

## Background
Software engineer, 5 years in fintech.
New to ML; strong in Python and system design.

## Working Style
Prefer depth over breadth. Learn by building.

## Values
Continuous improvement, teaching others.
5

Open in Claude Code and learn

Launch Claude Code in your brain directory. Run /learn and watch it go.

claude

> /learn

8 commands. That's it.

Each command is a Claude Code slash command stored in .claude/commands/. You can read, edit, and extend them.

/learn [topic]

Fetches free resources aligned to your goals, writes wiki articles, and adds a daily trivia fact.

/ingest

Processes files in brain/raw/inbox/ — articles, PDFs, Discord DMs — into wiki articles and journal entries.

/assess [topic]

Interactive knowledge quiz on your wiki. Tracks weak areas and scores per article over time.

/ask <question>

Answers any question using only what your brain contains. Cites sources and flags gaps.

/lint

Health-checks the wiki: finds orphans, stale index lines, missing backlinks, and contradictions.

/reflect [notes]

Writes today's journal entry: decisions made, what worked, open loops, energy signals.

/review weekly|monthly

Progress review against your goals. Weekly consolidates journal; monthly proposes profile updates.

/ngo <url>

Profiles an NGO or nonprofit from its website into a structured wiki article.

Your files. Your structure.

Everything lives in one brain/ directory. Plain Markdown. In git. Yours.

brain/
brain/
├── CLAUDE.md          ← operating manual
├── wiki/
│   ├── INDEX.md       ← one line per article
│   ├── mutual-funds.md
│   ├── jlpt-n5.md
│   └── ngo/           ← NGO profiles
├── raw/               ← append-only source material
│   └── inbox/         ← drop anything here
├── self/              ← your personal model
│   ├── goals.md       ← what you're working toward
│   ├── profile.md     ← values + priority lens
│   └── journal/       ← daily episodic memory
└── outputs/           ← answers and reports

Start building your lore

Clone the template, set your goals, run /learn.

Use template on GitHub

MIT license · No account required · Your data stays local