para-knowledge-base

PARA Knowledge Base — Claude Code Plugin

LLM as Knowledge Compiler — Karpathy's LLM Knowledge Base pattern, optimized for PARA Obsidian vaults

---

Inspiration

Inspired by Karpathy's llm-wiki — the idea that an LLM should act as a knowledge compiler, not a search engine. Rather than re-retrieving and re-summarizing raw notes on every query, knowledge is compiled once into structured wiki-style articles, then maintained incrementally as new information arrives.

This plugin applies that pattern to PARA-structured Obsidian vaults.

See examples/ for a fictional initialized vault snapshot, including indexes, a project hub, a change log, and optional query telemetry.

---

Why this plugin?

If you already have a PARA vault with hundreds of notes, Claude Code can read them — but every conversation starts from scratch. Each query re-reads files, re-discovers structure, and burns tokens figuring out what's where.

This plugin fixes that by adding a persistent knowledge layer on top of your existing vault:

The problem without a KB:

User: "What do I know about distributed systems?"
Claude: reads 30+ files → 15K tokens → synthesizes answer → forgotten next session
User: (asks again next week)
Claude: reads the same 30+ files again → 15K tokens again

With this plugin:

/kb-ingest              → new notes classified, linked, indexed (once)
/kb-query "distributed systems"  → reads _index.md (50 tokens) → targets 2 files (400 tokens) → done

What you get on top of your existing PARA vault

Already have	This plugin adds
Folders organized by PARA	_index.md per category — Claude reads 10 lines instead of scanning 100 files
Notes with some tags	Tag convention detection + consistency enforcement across vault
Manual wikilinks	Auto-generated wikilinks on ingest — first occurrence of known terms linked automatically
CLAUDE.md with basic rules	Full vault schema — structure, KB operations, tag system, navigation strategies
Raw notes in Inbox	One-command classification + move + metadata + linking
Unmeasured ad-hoc searches	Optional query telemetry — request-level route, document count, tool/time/token signals for later analysis

Token efficiency

Operation	Without plugin	With plugin
"What projects am I working on?"	Scan all project folders ~3K tokens	Read _index.md ~50 tokens
"Find everything about topic X"	Grep entire vault ~5K tokens	Tag search via index ~200 tokens
Ingest a new document	Manual: move, tag, link, update index	/kb-ingest — all automated, ~500 tokens
Weekly health check	Not possible	/kb-lint — orphans, broken links, stale content

The key insight: indexes are cheap to read, and they tell Claude exactly where to look. Instead of scanning your whole vault every time, Claude reads a 10-line index, picks the right folder, and reads only what's needed.

---

Concept

The 3-Layer Architecture

Inbox/          ← raw capture (fleeting notes, clippings, meeting notes)
PARA/           ← compiled knowledge wiki (Projects / Areas / Resources / Archives)
CLAUDE.md       ← vault schema (topics, conventions, wikilink vocabulary)

• Inbox is the staging area. Raw, unprocessed, low-friction.
• PARA is the knowledge base. LLM-compiled, structured, cross-linked.
• CLAUDE.md is the schema. Tells the LLM what topics exist, how notes are organized, what wikilinks are canonical.

Project Lifecycle

PARA categories aren't static bins — knowledge flows between them as a project moves through its lifecycle. A project starts by promoting its own deliverables into 1. Projects/ while linking (not moving) the Areas/Resources material it draws on; during the project, anything that would stay useful after the project ends gets written into 3. Resources/ and linked back rather than buried in the project folder; and on completion, kb-ingest runs a decompose pass before archiving — reusable knowledge returns to Resources, standing responsibilities move to Areas, and only the project-unique record goes to 4. Archive/. This keeps 4. Archive/ a true cold-storage layer instead of a dumping ground where reusable knowledge quietly becomes unsearchable.

The 3 Core Operations

Operation	What it does
Ingest	Takes raw Inbox notes, extracts knowledge, merges into PARA wiki pages
Query	Answers questions by reading compiled PARA pages (not raw notes)
Lint	Audits knowledge base for gaps, broken wikilinks, stale content

RAG vs. Knowledge Base