Loom Learning Graph

What it does

OpenClaw Loom transforms your learning materials into an interactive graph of interconnected knowledge. It combines mastery learning with spaced repetition and retrieval practice, allowing you to track progress through nodes, paths, and context captures all indexed for fast search within Markdown and QMD files. The system automatically recommends next steps and unlocks content based on your performance.

When to use it

• Structured Learning: Organize complex topics like Nix configuration or German grammar into a clear learning path with prerequisites and dependencies.
• Mastery Tracking: Monitor progress through a curriculum, ensuring each concept is truly understood before moving on.
• Real-World Application: Integrate "context captures" – real-life situations – to apply learned concepts in practical scenarios.
• Efficient Review: Leverage spaced repetition scheduling to reinforce knowledge and prevent forgetting.

Key capabilities

• Learning graph with prerequisites, unlocks, and mastery states
• Spaced repetition scheduling with review ratings
• Next-node recommendations with automatic unlocks
• Context captures for real-life application
• Local-first Markdown/QMD library with folder structure
• Semantic search using QMD indexing

Example prompts

• "Show me my next recommended node in the Nix path."
• "What are the prerequisites for understanding 'nix/derivations'?"
• "Review all nodes due today."

Tips & gotchas

• Nodes should be narrow, testable, and self-contained to maximize effectiveness.
• Use wikilinks (e.g., [[nix/derivations]]) within notes to connect them to other nodes in your learning graph.