Search stored memories and synthesize conversational summaries from matches.
npx skills add https://github.com/emmahyde/memesis --skill recall-emmahyde
Please help me install this Agent Skill. Skill: recall Source: https://github.com/emmahyde/memesis/tree/main/skills/recall Command: npx skills add https://github.com/emmahyde/memesis --skill recall-emmahyde
This Skill enables efficient searching across stored memories to retrieve pertinent information, reducing manual effort and delays in information access.
Ask the AI to recall relevant information by querying with your question, such as "Recall what we discussed about project deadlines."
High-intent search queries and answers about installing and using this skill.
To retrieve and synthesize memories, use semantic and full-text search to locate relevant stored data, then summarize the top matches into a natural conversational response for immediate use.
The best way to search stored notes is applying semantic search to find relevant past interactions, which synthesizes multiple memory matches into a single coherent summary for efficient data recall.
Yes, text embedding capabilities are required to perform semantic memory search, as the process depends on embedding, full-text, and semantic search functions to accurately locate and retrieve pertinent stored data.
You can summarize project timelines and deadlines from historical chat data by querying your stored memories, which triggers a search to locate related interactions and present a coherent summary of the information.
Memory synthesis works for retrieving specific notes without manual lookup by executing full-text and semantic searches across stored knowledge, efficiently reducing delays and manual effort in information access.
Semantic search is used instead of manual filtering because it quickly locates contextually relevant memories across stored knowledge, synthesizing them into natural responses and significantly reducing manual lookup delays.
HellblazerExtract text and metadata from PDFs and index them into the nx store.
23blocks-OSSearch conversation history using hybrid, semantic, or term-based modes.
zircoteRebuild BM25 full-text and vector indexes for Mnemonic semantic search.
Progery222Perform semantic vector searches across document collections using multiple distance metrics.
