StackMap
Subscribe
Explore / llm_wiki
nashsu

llm_wiki

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.

20,011 2,264 TypeScript NOASSERTIONupdated yesterday
ragknowledge-graphs
View on GitHubDispute this mapping →
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.

Mapped by ShipWithAI editors · links verified

Continue your stack

What teams reach for next — and why each earns a place beside llm_wiki. Ranked by curator confidence.

pairs wellalternativealternativealternativeMinerUarkonopen-notebookHyper-Extractllm_wiki
pairs wellalternativebuilt withpick a node for the why · open it from the panel
Weekly digest
README.md2 min read

LLM Wiki

LLM Wiki Logo

A personal knowledge base that builds itself.
LLM reads your documents, builds a structured wiki, and keeps it current.

What is this? • Features • Tech Stack • Installation • Credits • License

English | 中文 | 日本語 | 한국어

Overview

Features

  • Two-Step Chain-of-Thought Ingest — LLM analyzes first, then generates wiki pages with source traceability and incremental cache
  • Multimodal Image Ingestion — extract embedded images from PDFs, generate factual captions with a vision LLM, surface them in image-aware search results with lightbox preview and jump-to-source
  • Multi-format Document Parsing — ingest PDF, Office documents, EPUB/MOBI, Org mode, images, media, web clips, and batches of URLs, with built-in, cloud, or local MinerU PDF processing
  • Flexible Model Configuration — configure models per project, route Chat and Ingest independently, and manage custom providers, headers, and streaming output
  • Source-grounded Retrieval — use Read Sources Only mode to answer exclusively from original imported material
  • Project Management & Migration — export and import complete project archives across devices, and rebuild the Wiki index from existing pages
  • 4-Signal Knowledge Graph — relevance model with direct links, source overlap, Adamic-Adar, and type affinity
  • Louvain Community Detection — automatic knowledge cluster discovery with cohesion scoring
  • Graph Insights — surprising connections and knowledge gaps with one-click Deep Research
  • Vector Semantic Search — optional embedding-based retrieval via LanceDB, supports any OpenAI-compatible endpoint
  • Persistent Ingest Queue — serial processing with crash recovery, cancel, retry, and progress visualization
  • Folder Import — recursive folder import preserving directory structure, folder context as LLM classification hint
  • Source Folder Auto-Watch — detects external changes in raw/sources/ and keeps ingest/delete cleanup in sync
  • Deep Research — LLM-optimized search topics, multi-query web search via Tavily, SerpApi, or SearXNG, auto-ingest results into wiki
  • Rust Backend Chat Agent — tool-using chat runtime with wiki/source/graph/web retrieval, workspace file generation, shell approval, cancellation, and streaming tool events
  • Agent Skills — scan and enable local SKILL.md folders, select skills with /skill, and let the Agent read skill instructions on demand
  • Generated Outputs Preview — Agent-created Markdown, HTML, images, and other workspace files appear as outputs with preview and quick folder access
  • Mermaid Diagram Rendering — render Mermaid code blocks directly in chat and preview, with compact syntax-error cards instead of raw parser output
  • Async Review System — LLM flags items for human judgment, predefined actions, pre-generated search queries
  • Chrome Web Clipper — one-click web page capture with auto-ingest into knowledge base
  • Local HTTP API + MCP Server + AI Agent Skill — built-in 127.0.0.1:19828 JSON API and bundled MCP server for hybrid search, file read, graph traversal, and source rescan; ready-made agent skill installs into Claude Code / Codex with one command (npx skills add …)

What is this?

LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional