c8c27141d7
Critical fixes: - marketplace.json: fix version 1.0.0→1.2.0, fix email to ***REMOVED*** - main.canvas: remove 5 broken file references (gitignored files) - community-plugins.json: deduplicate from 6→4 canonical entries Vault onboarding: - wiki/getting-started.md: new onboarding page inside the vault - wiki/index.md: populate Entities, Sources, Questions, Comparisons sections - wiki/meta/dashboard.md: fix Dataview queries (was referencing non-existent fields) - welcome.canvas: add CTA node pointing to getting-started - CLAUDE.md: replace placeholder text with actual vault description Docs: - README.md: complete Plugins section (pre-installed + recommended), CSS Snippets section, Banner usage section, file structure updated - bin/setup-vault.sh: expanded success message listing all plugins and CSS snippets - docs/install-guide.md + docs/install-guide.pdf: printable community install guide Version: 1.1.0 → 1.2.0 Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
1.5 KiB
1.5 KiB
type, title, updated, tags, status, related
| type | title | updated | tags | status | related | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| meta | Wiki Index | 2026-04-07 |
|
evergreen |
|
Wiki Index
Last updated: 2026-04-07 | Total pages: 15 | Sources ingested: 1
Navigation: overview | log | hot | dashboard | Wiki Map | getting-started
Concepts
- LLM Wiki Pattern — the pattern for building persistent, compounding knowledge bases using LLMs (status: mature)
- Hot Cache — ~500-word session context file, updated after every ingest and session (status: mature)
- Compounding Knowledge — why wiki knowledge grows more valuable over time, unlike RAG (status: mature)
Entities
- Andrej Karpathy — AI researcher, creator of the LLM Wiki pattern, former Tesla AI director (status: developing)
Sources
Questions
- How does the LLM Wiki pattern work — how the pattern works and why it outperforms RAG at human scale (status: developing)
Comparisons
- Wiki vs RAG — when to use a wiki knowledge base versus RAG; verdict: wiki wins at <1000 pages