quarry
Related Servers
Alternatives to quarry
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceProvides Claude Code with local semantic search and indexing of your codebase using AST-aware chunking and hybrid search, enabling deep code understanding without sending data to the cloud.34 PyPIMIT
- FlicenseNot gradedqualityDmaintenanceEnables semantic code search across codebases using AI embeddings and vector similarity, integrated with Claude Desktop and Cursor.-
- AlicenseNot gradedqualityBmaintenanceProvides persistent semantic memory for Claude Code and Claude Desktop with fully offline local embeddings and HNSW indexing, enabling memory storage, semantic search, listing, and deletion across sessions.MIT
- AlicenseNot gradedqualityDmaintenanceProvides local-first, cross-session memory for Claude Code, enabling semantic search across past sessions to retrieve procedures, decisions, or answers without exposing secrets.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables Claude Desktop to search and query personal document collections (PDF, Word, Markdown, text) using semantic search and conversational AI with full context preservation across exchanges.MIT
- AlicenseNot gradedqualityCmaintenanceEnables Claude Code to search and retrieve from a local knowledge base of markdown notes using hybrid semantic+keyword search, keeping data entirely offline.18 npmMIT
TDQS
Scored across 14 tools
The potentially confusing trio (remember = fact, ingest = URL, learn = lesson) is explicitly disambiguated in each description, and search/read tools (find, show, list) have clearly different scopes. Minor overlap remains between sync_all_registrations and missions_sync, and between 'use' and list(kind="databases"), but neither is likely to cause misselection.
Mostly bare verbs (find, show, delete, use, learn) which is readable but not the verb_noun pattern; the compound names conflict in ordering — sync_all_registrations is verb-first while missions_sync is noun-first. It stays interpretable, but there is no single predictable convention across all 14 tools.
14 tools sits comfortably in the well-scoped range, and each earns its place: memory write, retrieval, ingestion, index management, and database targeting are all separate concerns. Slightly on the heavy side for a personal knowledge daemon, but nothing looks redundant.
The memory lifecycle is well covered — write (remember/learn/ingest), retrieve (find/show/list), remove (delete), plus source registration, sync, status, insights, and database switching. Gaps are minor: no true edit/update of an existing memory beyond the overwrite flag, and no collection creation or export path.