Discover and explore top open-source AI tools and projects—updated daily.
breferrariAI-powered Obsidian vault for persistent AI memory and knowledge compounding
Top 25.9% on SourcePulse
This project provides an Obsidian vault template designed to give Claude Code a persistent memory and context, addressing the problem of AI sessions starting from scratch. It's targeted at engineers using Claude Code as a thinking partner, enabling knowledge compounding, automated note-taking, and performance tracking across conversations.
How It Works
The core approach utilizes an Obsidian vault structured with folders for purpose and links for meaning, creating a knowledge graph. Claude Code automatically maintains this graph, linking work notes to people, decisions, and competencies. Durable knowledge resides in brain/ topic notes, indexed by MEMORY.md. Five lifecycle hooks (SessionStart, UserPromptSubmit, PostToolUse, PreCompact, Stop) automate context injection, content classification, routing, and session wrap-up, ensuring Claude starts every session with relevant context and systematically organizes information.
Quick Start & Requirements
claude in the vault directory. Fill in brain/North Star.md with your goals.Highlighted Details
/standup, /dump, /wrap-up, /review-brief) for structured workflows.slack-archaeologist, review-prep, and brag-spotter.Home.md for quick access to organized data./vault-upgrade command facilitates migration from any existing Obsidian vault.Maintenance & Community
No specific details on contributors, sponsorships, or community channels (like Discord/Slack) are provided in the README. Interaction and development are centered around the GitHub repository.
Licensing & Compatibility
The project is released under the MIT license, permitting commercial use and integration with closed-source projects without significant restrictions.
Limitations & Caveats
This template requires specific versions of Obsidian and Claude Code. Its effectiveness is dependent on Claude Code's ability to follow the conventions outlined in CLAUDE.md. Users are expected to customize goals, organizational details, competencies, and tools to match their specific workflows. QMD is optional but recommended for advanced semantic search capabilities.
1 day ago
Inactive