StackMap
Subscribe

llm_wiki vs open-notebook

Desktop app implementing Karpathy's LLM Wiki pattern: an LLM ingests your documents into a persistent, interlinked wiki with a knowledge graph, hybrid search, deep research and an MCP server. — versus — Self-hosted NotebookLM alternative: multi-modal sources, vector plus full-text search, context-aware chat and multi-speaker podcast generation — 18+ model providers incl. Ollama, full REST API.

The curated verdict

Both are personal 'chat with your sources' apps; open-notebook retrieves over raw sources per question, NotebookLM-style, while LLM Wiki compiles them into a maintained wiki first.

llm_wikiopen-notebook
Stars20k39k
Forks2.3k4.6k
LanguageTypeScriptTypeScript
LicenseNOASSERTIONMIT
Last activityyesterday8 days ago
Topicsrag, knowledge-graphsrag, storage
Curated connections44

llm_wiki — the curator's take

Pick LLM Wiki if you like Karpathy's 'compile knowledge once instead of re-retrieving it every query' idea but don't want to wire it up yourself: drop in PDFs, Office docs, EPUBs or web clips and an LLM writes and maintains source-traced wiki pages, with Louvain clusters, gap-finding and deep research on top, plus an MCP server and a skill so Claude Code or Codex can query it. It's a personal, single-user desktop app — not a team knowledge service (see arkon) — and every ingest spends LLM tokens on a two-step analyse-then-write pass, so big corpora cost real money. Licence is GPL-3.0 (the GitHub API reports NOASSERTION): fine to use, copyleft if you fork and redistribute.

open-notebook — the curator's take

The default answer to 'NotebookLM but private': drop in PDFs, videos, audio and web pages, search and chat across them, and generate podcasts with 1-4 custom speakers where Google caps you at two. Provider freedom is the real lever — 18+ backends down to Ollama/LM Studio keeps sensitive research fully local, and the REST API makes it automatable where NotebookLM is a closed app. NOT ahead on citations — it concedes NotebookLM's source-grounding is stronger (theirs is 'basic, will improve'), which matters if research integrity is the whole point. A product you deploy (Docker), not a library you embed.