RAGDown
Related Servers
Alternatives to RAGDown
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search, read, create, and maintain a local-first knowledge base using hybrid retrieval and Markdown note management through the Model Context Protocol.14 npm1MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to search and query a local knowledge base of scattered notes and docs through hybrid vector plus BM25 retrieval with section-level citations, and to store, retract and explore durable memories, note links and agent harness memories. It also exposes note resources plus briefing, study-plan and contradiction-check prompts, all backed by a shared local index.-
- AlicenseNot gradedqualityCmaintenanceEnables agents to search and retrieve relevant Markdown knowledge-base chunks through local hybrid retrieval, with tools for reindexing and viewing index statistics, without external services or LLM tokens.MIT
- AlicenseNot gradedqualityBmaintenanceTurns a folder of Markdown notes into an agent-native knowledge base, providing long-term memory with provenance, token-budgeted retrieval, and safe write-back with versioning.MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to search and question a personal knowledge base of notes and documents through hybrid vector and BM25 retrieval, with section-level citations. It also lets agents store, retract, and explore durable memories, links, and indexing statistics across tools.-
- AlicenseNot gradedqualityBmaintenanceLets AI agents retrieve source-linked passages from a local folder of Markdown notes or an Obsidian vault, optionally following the explicit links between notes, and can also fetch passages from pinned public GitHub files you configure. It returns bounded evidence packets with original text, file paths and hashes so agents can answer from your material rather than generating content themselves.1MIT
TDQS
Scored across 12 tools
Most tools target clearly distinct operations (search vs. read vs. edit vs. move vs. delete), and the descriptions actively steer callers between overlapping pairs—recall vs. context (hook-oriented, dedup, min_score) and remember vs. write (never-overwrite create vs. arbitrary path write). The remaining overlaps (remember/write both creating files, write/edit both mutating content) are explicitly resolved in prose rather than by name, so an agent must read carefully, but no two tools are truly interchangeable.
Every tool uses the same ragdown_ prefix and snake_case with no camelCase or style mixing, which makes the set easy to scan. However the suffix convention is inconsistent in kind—action verbs (recall, reindex, read_doc, write, edit, move, delete) mixed with bare nouns (context, backlinks, list, stats)—so it is predictable in formatting but not in verb_noun grammar.
Twelve tools is well within the sweet spot and every one earns its place: read/write/edit/move/delete cover file lifecycle, recall/context/list cover retrieval, and backlinks/stats/reindex/remember cover graph awareness, observability and persistence. Nothing looks like filler or a redundant variant of another tool.
The surface covers the full Markdown-knowledge-base lifecycle: retrieval (recall, context, list), reading (read_doc, backlinks), mutation (remember, write, edit, move, delete with link rewriting and hash-based conflict checks), and maintenance (reindex, stats). Notably, moves rewrite links and remember supports supersedes, closing the gaps that would otherwise break a link-based document graph.