{"skill":{"slug":"enhanced-memory","displayName":"Enhanced Memory","summary":"Enhanced memory search with hybrid vector+keyword scoring, temporal routing, filepath scoring, adaptive weighting, pseudo-relevance feedback, salience scoring, and knowledge graph cross-references. Replaces the default memory search with a 4-signal fusion retrieval system. Use when searching memories, indexing memory files, building cross-references, or scoring memory salience. Requires Ollama with nomic-embed-text model.","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":999,"installsAllTime":1,"installsCurrent":1,"stars":0,"versions":1},"createdAt":1770693884415,"updatedAt":1777525070719},"latestVersion":{"version":"1.0.0","createdAt":1770693884415,"changelog":"- Initial release of enhanced-memory: a drop-in replacement for OpenClaw's memory search with a 4-signal hybrid retrieval system (vector, keyword, header, filepath).\n- Adds adaptive weighting, temporal routing for date queries, pseudo-relevance feedback, and salience scoring for important/stale memory items.\n- Introduces memory cross-reference knowledge graph building and graph statistics tools.\n- Indexes and embeds markdown files using Ollama’s nomic-embed-text model; tunable parameters in each script.\n- Includes standalone scripts for memory search, indexing, salience scoring, and cross-reference management; no external Python dependencies required.","license":null},"metadata":null,"owner":{"handle":"jameseball","userId":"publishers:jameseball","displayName":"JamesEBall","image":"https://avatars.githubusercontent.com/u/73405337?v=4"},"moderation":null}