Skip to main content

LLM-wiki: A Personal Wiki Written and Maintained by LLM

Traditional notes: you write and maintain everything. Typical RAG tools: retrieval starts fresh each time and often does not accumulate. LLM-wiki: LLM writes and maintains the knowledge layer while you focus on thinking and direction.

How Is This Different from RAG or Q&A over Documents?​

DimensionTypical RAG / NotebookLMLLM-wiki
StorageRetrieval index over source docsSource docs plus AI-maintained knowledge pages
Query pathRetrieve and compose ad hoc each timeQuery maintained pages first, then source docs when needed
AccumulationLimited long-term accumulationContinuous accumulation of summaries, topics, links
Contradiction trackingMinimalPeriodic checks for contradictions, outdated notes, orphan notes
Output persistenceAnswer is often one-offStrong answers can be saved as new notes
Data locationUsually cloudFully local in your Obsidian vault

Three Layers​

LayerContentOwner
Your source layernotes, articles, highlights, transcriptsyou
AI organization layersummaries, topic pages, comparisons, indexes, logsAI
Rule layerconventions and operating guidelinesyou + AI

Core idea: you lead strategy and thinking, AI handles routine maintenance.

Three Core Operations​

Ingest​

When you add a new source, AI can:

  1. read and discuss key points
  2. write a summary page
  3. update related topic links
  4. log the update

Query​

AI first consults maintained wiki pages, then pulls source evidence when needed. High-value answers can be saved directly as new notes.

Lint​

AI periodically checks your wiki for:

  • contradictions
  • outdated statements
  • isolated notes
  • missing high-priority topics

Two Special Files​

  • index.md: navigation and one-line summaries
  • log.md: chronological operation log

How GPT AI Flow Supports This Paradigm​

LLM-wiki NeedGPT AI Flow Capability
AI can read your noteslocal semantic indexing over vault content
AI can write backdirect read/write to Obsidian files
reusable workflowsskill system with one-command workflows
proactive rhythmscheduled prompts and writing rhythm support
traceabilityversion-aware workflow and history support
result persistencesave conversation outcomes to notes

Typical Use Cases​

  • personal growth journaling and reflection
  • long-cycle topic research
  • reading companion workflows
  • product research and competitive analysis
  • course notes and hobby deep dives

Privacy and Local-First Design​

  • wiki pages, source docs, and indexes stay on your local disk
  • external calls are limited to chosen model interactions and indexing operations
  • all notes remain plain markdown and portable

Further Reading​

Join Us​

  • Product Feedback:
  • πŸ’¬ Have a question? Check out the FAQ for quick solutions: Click here

Thank you for choosing GPT AI Flow, together building the essential tools for the super individuals of the future!