nashsu

nashsu / llm_wiki

Public

LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。

367
37
100% credibility
Found Apr 10, 2026 at 367 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

LLM Wiki is a desktop app that automatically builds and maintains an organized, interlinked personal knowledge base from your documents using AI.

How It Works

1
🚀 Launch the app

Open LLM Wiki on your computer — it's like a smart notebook that organizes your files.

2
Pick your project
✨
New project

Create a new knowledge base with helpful starting guides.

📂
Open existing

Jump back into your saved wiki.

3
🔗 Connect your AI helper

Link a smart AI service (like ChatGPT) so it can read and organize your notes.

4
📤 Add your documents

Drag in PDFs, articles, or notes — the AI reads them automatically.

5
⚡ Watch it build your wiki

See the magic: AI creates pages for people, ideas, and summaries, linking everything together.

6
💬 Ask questions

Chat with your wiki — get answers with sources, just like talking to an expert.

7
🌐 Explore connections

See your knowledge as a map, discover gaps, and research more with one click.

✅ Your wiki grows

Your personal knowledge base stays organized and expands as you add more files.

Sign up to see the full architecture

6 more

Sign Up Free

Star Growth

See how this repo grew from 367 to 367 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is llm_wiki?

LLM Wiki is a TypeScript-based Tauri desktop app that ingests your PDFs, DOCX files, web clips, and more into a self-building, interlinked knowledge base. Unlike traditional LLM Wikipedia RAG setups that retrieve from scratch every query, it uses a two-step LLM process to incrementally generate and maintain wiki pages with wikilinks, frontmatter, and Obsidian compatibility. You get a persistent graph of entities, concepts, and sources—ready for chat queries or graph exploration—inspired by Karpathy's llm wiki github pattern.

Why is it gaining traction?

It stands out with interactive knowledge graphs using Louvain clustering and relevance scoring, plus one-click deep research via web search that auto-ingests results. The Chrome extension web clipper and multi-conversation chat with cited references make it a seamless llm github local workflow, beating basic RAG tools. At 367 stars, this llm github projects gem hooks devs tired of reprocessing docs, especially with Ollama integration for private models.

Who should use this?

Researchers curating llm wikipedia datasets, lawyers building llm wiki law bases from case files, or devs maintaining project notes with llm github integration. Ideal for anyone with scattered docs needing a queryable wiki—think personal growth trackers or business intel from reports—without constant LLM token burn.

Verdict

Grab it from the llm github download for a fresh take on local knowledge management; the 1.0% credibility score reflects its early stage (low tests, solo maintainer), but solid docs and GPL3 make it worth prototyping. Strong for niche use, watch for community polish.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.