s2b-dev/smart-second-brain

An Obsidian plugin to interact with your privacy focused AI-Assistant making your second brain even smarter!

What it solves

This project provides a way to turn an Obsidian vault into an interactive knowledge base. It eliminates the need to manually copy-paste notes into AI prompts by allowing a large language model (LLM) to directly access and query your personal notes.

How it works

The plugin uses a Retrieval-Augmented Generation (RAG) pipeline. It converts your notes into vector embeddings and stores them in a vector store (Orama). It then retrieves the most relevant notes based on the similarity of your query to generate an answer. It also uses hierarchical tree summarization to process notes.

Who it’s for

Obsidian users who want an AI assistant that can chat with their notes, with a preference for privacy-focused local LLMs (via Ollama) or high-performance cloud models (via OpenAI).

Highlights

  • Local AI Execution: Supports Ollama for completely offline, private data processing.
  • Reference Links: Answers include Obsidian links back to the original notes used as sources.
  • Model Flexibility: Allows users to quickly switch between different LLMs for different writing or analysis tasks.
  • Open Source: A free, open-source alternative to similar knowledge management plugins.

Related

  • Project
    green-dalii/obsidian-llm-wiki

    An Obsidian plugin that transforms notes into a connected, queryable knowledge base using graph-based retrieval instead of embeddings, enabling AI chat over personal notes.

  • Project
    bramses/chatgpt-md

    An AI writing companion for Obsidian that lets you chat with AI directly in your notes, reference other notes via wiki links, and use local or cloud-based models.

  • Dispatch
    Integrating Local LLMs with Obsidian Notes via Ollama

    Ollama demonstrates how to build an Obsidian plugin that uses Llama Index and local LLMs to enable conceptual search and conversational interaction with personal notes.

  • Project
    allenhutchison/obsidian-gemini

    An Obsidian plugin that integrates Gemini, Ollama, or OpenAI to provide an AI agent capable of managing your vault, performing semantic search, and automating note-taking tasks.

  • Project
    Lapis0x0/obsidian-yolo

    An agent-native AI assistant for Obsidian that integrates RAG, tool-calling agents, and a structured learning system directly into the user's vault.