Back to directory

obsidian-second-brain

A persistent-memory system for Claude Code and other CLI agents, stored as plain markdown notes in an Obsidian vault that rewrites and reconciles itself as new information arrives.

obsidian-second-brain

obsidian-second-brain gives Claude Code, Grok Bot, Codex and several other CLI agents a shared, persistent memory stored as plain markdown files in an Obsidian vault, so the same knowledge base outlives whichever agent is currently in use. Rather than only appending new notes, each new piece of information updates existing pages, and contradictions are reconciled automatically, following what the project calls Open Knowledge Metabolism, where every stored fact is marked timeless, dated, or a pointer, so the vault does not fill up with facts that are no longer true.

It provides 45 commands, including hybrid semantic search, self-rewriting notes, web research that needs no API key, and scheduled agents that maintain the vault unattended. Presets tailor the vault for developers, founders and operators, writers, or researchers, and it can be installed with a setup script or by cloning the vault directly.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.