quarry
Related Servers
Alternatives to quarry
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceProvides 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.MIT
- 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 gradedqualityCmaintenanceProvides 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 gradedqualityBmaintenanceEnables Claude Code to search and retrieve from a local knowledge base of markdown notes using hybrid semantic+keyword search, keeping data entirely offline.6 npmMIT
TDQS
Scored across 14 tools
Most tools map to clearly distinct operations: search, read, ingest, remember, learn, delete, register, and status all have separate purposes. The only real ambiguity is between remember and learn, since both save durable knowledge and the distinction relies on subtle phrasing like 'specific fact' versus 'distilled lesson'.
All names are lowercase and readable, but the set mixes bare verbs like find, show, and use with verb_noun compounds like register_directory and sync_all_registrations, plus one inverted noun_verb compound, missions_sync, and noun-only names like status and insights.
Fourteen tools is within a reasonable range for a knowledge-base and recall server, and each tool has a real role. The surface feels slightly heavy due to the cluster of status/list/insights tools and the niche missions_sync tool, but nothing is clearly redundant.
The core lifecycle is well covered: content can be added via ingest, remember, learn, or register_directory; retrieved via find, show, and list; and removed via delete or deregister_directory, with overwrite flags supporting updates. Minor gaps exist around explicit database or collection creation and editing existing indexed content, but agents can work around them.