This project addresses the challenge of managing and connecting information within large Obsidian vaults, where notes can become disconnected and context is easily lost. Obsidian Claw provides an intelligent layer, leveraging Claude AI and a CLI tool, to automatically link ideas, extract entities, and surface forgotten context, transforming a static note collection into a dynamic, interconnected knowledge graph. It benefits users by enhancing recall, improving knowledge organization, and streamlining the process of creating structured, atomic notes.

How It Works

Obsidian Claw operates via two primary modes: a conversational Claude Skill and an automated CLI pipeline. The Claude Skill allows users to paste raw notes into Claude, which then intelligently extracts entities, cross-references them with the user's existing vault (via an optional index), generates perfectly formatted, interlinked Obsidian notes, and utilizes an "Echo Engine" to surface relevant past context. The CLI mode offers commands for vault initialization, note import, batch processing, review generation, and knowledge graph export. The core pipeline involves entity extraction, vault scanning for related notes, generation of atomic notes with wikilinks, and surfacing past context before outputting Markdown files and optional Mermaid graphs.

Quick Start & Requirements

Installation is streamlined via a single command for macOS, Linux, and Windows (Git Bash/WSL): curl -fsSL https://raw.githubusercontent.com/EdsonAlacantara/Obsidian-Claw/main/install.sh | bash. A separate installer is available for Windows CMD/PowerShell. The primary requirement is Python 3.10+. Further details, demos, and documentation can be found at the project's GitHub repository.

Highlighted Details

• Auto-linking: Automatically generates [[wikilinks]] to connect new notes with existing ones in the vault.
• Entity Extraction: Identifies and categorizes key entities such as people, projects, dates, decisions, and concepts within notes.
• Echo Engine: Proactively reminds users of past discussions or related information pertinent to the current note.
• Knowledge Graph Generation: Creates visual representations of note interconnections using Mermaid diagrams.
• Atomic Formatting: Converts unstructured text into Zettelkasten-style atomic notes with proper frontmatter and metadata.
• Weekly Synthesis: Automates the generation of weekly review notes summarizing emerging patterns and outstanding questions.
• Entity Registry: Maintains a persistent, auto-updated registry of all identified people and concepts across the vault.

Maintenance & Community

The project is maintained by EdsonAlacantara, with contributions welcomed via GitHub Issues and Discussions. The repository provides a CONTRIBUTING.md file for guidance on submitting pull requests. Users are encouraged to star the repository to support continued development.

Licensing & Compatibility

Obsidian Claw is released under the MIT License, permitting broad use and modification. It is compatible with local Obsidian vaults, Claude.ai, the Claude API, Obsidian Sync, and cloud storage solutions like iCloud and Dropbox. Integrations for Logseq, Notion, and Roam Research are planned for future releases.

Limitations & Caveats

While Obsidian Claw offers robust local processing, users opting for the Claude API mode will send explicitly provided text to Claude's servers. Integrations for Logseq, Notion, and Roam Research are listed as "planned" and are not yet implemented. The effectiveness of cross-referencing relies on an indexed vault, which may require initial setup or indexing time.