$ loading_
Search, trace, and enrich your local knowledge graph with provenance-aware retrieval.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "loom" yet — see the docs or source repo.
Search my local knowledge vault for “vector database performance optimization”, ranked by relevance, and include the source file, excerpt, and linked notes for each result.
A ranked list of relevant notes with evidence snippets, source paths, and linked relationships.
Trace the evidence chain for the conclusion “user retention dropped because the first-use path is too long” in my vault, including the earliest note, related notes, and cited sources.
A provenance trail showing the conclusion’s origin, key evidence nodes, and cross-references.
From my meeting notes and research notes, extract entity relationships like “Project A—owner—Zhang Min” and “Project A—depends on—System B”, write them into the knowledge graph, and preserve the original citations.
Structured entities and relationships ready to write, each with its original source citation.
Search and read indexed local documents with full-text and fuzzy matching.
Automatically extract, merge, and query learned CS knowledge as a graph.
Search custom knowledge bases in Claude Desktop with RAG via MCP.
Expose a pgvector knowledge base to AI clients through MCP search.
Search markdown knowledge bases with hybrid ranking and intelligent reranking.
Connect AI to an Obsidian vault for notes, semantic search, and memory.