eugeniughelbur/obsidian-second-brain

Persistent memory for Claude Code and 6 other CLI agents, stored as plain markdown in your Obsidian vault. Stop re-explaining your projects, decisions and people every session. 45 commands: hybrid semantic search, self-rewriting notes, key-less web research, and scheduled agents that maintain the vault while you sleep.

What it solves

This project addresses the "institutional amnesia" of AI assistants like Claude and Grok, where every session starts from scratch. It bridges the gap between an AI's reasoning capabilities and a user's long-term memory stored in Obsidian, creating a persistent, self-maintaining knowledge base that evolves as the user interacts with the AI.

How it works

It functions as a cross-platform skill for various AI CLIs (Claude Code, Grok Bot, Gemini, etc.) that interacts directly with an Obsidian vault. Instead of simply appending new notes, it uses an "Open Knowledge Metabolism" (OKM) approach to rewrite existing pages, reconcile contradictions automatically, and synthesize patterns across sources. It utilizes a system of 47 commands divided into four layers: operations for memory management, thinking tools for ideation, a context engine for identity loading, and a research toolkit for ingesting external data from X, YouTube, and the web.

Who it’s for

Developers, founders, operators, writers, and researchers who use Obsidian for note-taking and want their AI assistants to have a persistent, AI-first memory that can ingest and organize information automatically.

Highlights

  • Self-Maintaining Vault: Automatically rewrites pages and resolves contradictions via /obsidian-reconcile and /obsidian-synthesize.
  • Multimodal Ingestion: Converts URLs, PDFs, audio files (via Whisper), and screenshots into structured, cross-linked notes.
  • Cros-Platform Support: Works across Claude Code, Grok Bot, Codex, Gemini, and others.
  • AI-First Note Format: Uses a specific preamble and frontmatter designed for LLM retrieval rather than human reading.
  • Automated Agents: Includes scheduled agents for morning briefs, nightly consolidation, and vault health checks.
  • Deep Research: Combines vault-first scanning with external tools like Perplexity and Grok to fill knowledge gaps without re-researching known facts.

Related

  • Project
    breferrari/obsidian-mind

    An Obsidian vault template that provides AI coding agents with persistent, cross-session memory through automated hooks and semantic search.

  • Project
    jaredrhod/ai-memory-vault

    A system that turns an Obsidian vault into a persistent, external memory for AI agents, allowing them to remember information across sessions without context limits.

  • Project
    Ar9av/obsidian-wiki

    A tool that allows AI agents to build and maintain a persistent, interconnected markdown knowledge base (a "second brain") from chat logs and documents.

  • Project
    itechmeat/open-second-brain

    An Obsidian-native memory layer for AI agents that stores knowledge as plain Markdown files, allowing users to own and edit their agent's memory.

  • Project
    smixs/agent-second-brain

    An always-on AI personal assistant that converts Telegram voice notes and messages into a structured, linked knowledge graph in a self-hosted Obsidian vault.