@noahduck283: Mom, my knowledge base is saved! Shopify founder Tobi and Karpathy jointly recommend it! Completely local, free, simple to use, and saves you a ton of tokens! Configuration prompt: Help me install qmd, connect the current directory for retrieval, I take Chinese notes. 1. npm inst...

X AI KOLs Timeline Tools
local-knowledge-base free-tool cli vector-embedding knowledge-retrieval open-source

Summary

Introducing a fully local, free AI knowledge base tool called qmd, supporting Chinese note retrieval, recommended by Shopify founder and Karpathy, saving token costs.

Mom, my knowledge base is saved! Shopify founder Tobi and Karpathy jointly recommend it! Completely local, free, simple to use, and saves you a ton of tokens! Configuration prompt: Help me install qmd, connect the current directory for retrieval, I take Chinese notes. 1. npm install -g @tobilu/qmd — install qmd CLI itself 2. claude plugin marketplace add tobi/qmd && claude plugin install qmd@qmd — install plugin (automatically registers MCP server + matching skill) 3. qmd collection add . --name brain — configure current directory as knowledge base 4. Switch to Qwen3-Embedding-0.6B multilingual model (mandatory for Chinese knowledge base) 5. qmd pull — pull the local small model required by qmd query 6. qmd embed -f — generate vector index
Original Article
View Cached Full Text

Cached at: 05/21/26, 05:37 PM

Mom, my knowledge base is saved!

Recommended by Shopify founder Tobi and Karpathy! Fully local, free, simple to use, and saves you a ton on tokens!

Configuration prompts: Help me install qmd, hook up the current directory for retrieval, these are my Chinese notes.

  1. npm install -g @tobilu/qmd — install the qmd CLI itself
  2. claude plugin marketplace add tobi/qmd && claude plugin install qmd@qmd — install the plugin (automatically registers MCP server + matching skill)
  3. qmd collection add . --name brain — configure the current directory as the knowledge base
  4. Switch to the Qwen3-Embedding-0.6B multilingual model (required for Chinese knowledge bases)
  5. qmd pull — pull the local small model needed for qmd query
  6. qmd embed -f — generate vector index

Similar Articles

@QingQ77: A beautiful Markdown editor + LLM knowledge base, WYSIWYG, with deep integration of AI agents like Claude, Codex, Cursor, etc. Comes with MCP, Skills, and agent search, AI can read and write documents directly in the knowledge base. htt…

X AI KOLs Timeline

OpenKnowledge is a beautiful Markdown IDE with a WYSIWYG editor, deeply integrated with AI agents like Claude, Codex, Cursor. It can be used as an LLM knowledge base, with built-in MCP, Skills, and agent search, supporting local private deployment.

@grgerwcwetwet: Recommending an open-source project: qiaomu-anything-to-notebooklm. Someone built a hardcore tool with Claude, and after seeing it, I just want to say: Knowledge management folks should definitely bookmark this. You can throw in any content—WeChat public accounts, YouTube, podcasts, PDFs, Word, Excel…

X AI KOLs Timeline

Recommending an open-source project qiaomu-anything-to-notebooklm, based on Claude to automatically organize multi-source content (WeChat public accounts, YouTube, PDFs, etc.) and generate podcasts, PPTs, mind maps, all through natural language operations.

@huoshan007: Folks, the crazy thing about this is: You can build your own AI second brain without buying a $1000 course or joining a coding bootcamp. Just three and a half steps. Throw your Obsidian, Markdown, PDFs, old documents all into one folder. Install Khoj, an open-source project, 3...

X AI KOLs Timeline

Khoj is an open-source personal AI second brain tool that supports connecting to local or cloud large models, indexing personal documents such as Obsidian, Markdown, PDFs, etc., and helps users discover knowledge connections through semantic search, all without needing a programming background.

@rwayne: https://x.com/rwayne/status/2054523563248611675

X AI KOLs Timeline

This article details how to build a fully automated local knowledge base system using Hermes Agent, Obsidian, and LLM Wiki, enabling automatic note organization, bidirectional linking, and persistent accumulation.