Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
cuba-memorys
MCP serversPersistent memory MCP server. 28 tools, BM25+MMR+OOD retrieval, tamper-evident audit, code graph.
cuba-memorys@0.24.0 -
Chronicle MCP
MCP serversLocal, private AI chat history search & memory: BM25 over your Cursor, Claude and ChatGPT chats.
chronicle-mcp-server@1.6.2 -
N3MemoryCore Lite (Working Memory)
MCP serversEphemeral 7-day hybrid vector+BM25 working memory, multilingual, backed by Redis Stack.
n3memorycore-mcp-lite@1.6.2 -
claude-remind-mcp
MCP serversSearch past Claude Code conversations. Local BM25 over JSONL with one-click claude --resume.
claude-remind-mcp@0.1.1 -
doctree-mcp
MCP serversBM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.
doctree-mcp@1.0.1 -
llmstxt-doc-search
MCP serversBM25 search over llms.txt doc indexes (Strands, Kiro, AWS); sources addable at runtime.
@praveenc/llmstxt-doc-search@1.0.0 -
rapidbm25
MCP serversFast local BM25 keyword search over texts or a code/docs folder. Rust core, no network.
rapidbm25@0.2.0 -
md-semantic-search
MCP serversLocal semantic search + citation-first RAG over Markdown. Hybrid dense+BM25F, ANN, MCP server.
md-semantic-search@3.1.0 -
CogniRepo
MCP serversFAISS, call graph, AST, BM25 — 34 MCP tools for AI agents. 50-80% token reduction. Offline.
cognirepo@1.1.1 -
vanguard-memory-node
MCP serversLocal deterministic BM25 memory for AI agents via MCP. Offline-first, SHA-256 shards, stdio.
@lnes/vanguard-memory-node@2.1.1 -
LocalSynapse - Local File Search MCP Server
MCP serversOffline AI-powered local file search. BM25 + semantic hybrid search across all documents.
https://github.com/LocalSynapse/LocalSynapse/releases/download/v2.1.0/localsynapse-mcp.mcpb -
LocalSynapse - Local File Search MCP Server
MCP serversOffline AI-powered local file search. BM25 + semantic hybrid search across all documents.
https://github.com/LocalSynapse/LocalSynapse/releases/download/v2.1.0/localsynapse-mcp.mcpb -
ToolRoute
MCP serversRoute each agent task to the few tools it needs (BM25 shortlist). Free tier; x402 or credits.
-
Qdrant MCP
MCP serversThe full Qdrant API as 58 MCP tools: plain-text semantic/BM25/hybrid search and a search advisor.
mcp-qdrant@2.12.0 -
mcp-sap-docs
MCP serversFast MCP server for unified SAP docs search (SAPUI5, CAP, OpenUI5, wdi5) with BM25 full-text search
mcp-sap-docs@0.3.9 -
MedXpert 图书馆连接器(通用版)
MCP serversLocal RAG MCP server for your own .md knowledge base: BM25 + local Ollama, offline, zero egress.
medxpert-library-connector@1.0.2 -
agentdiet
MCP serversStrips 85-97% of HTML bloat into clean Markdown, <200-token skeletons, or BM25 excerpts via MCP.
-
dompruner-mcp
MCP serversStrips layout noise via DOM AST; with a query, BM25 filters to relevant sections. No model or API.
dompruner-mcp@0.5.2 -
cognicore-env
Tools & appsPersistent memory, reflection & safety for AI agents. No vector DB, no embedding server — BM25 + multi-hop retrieval runs in-process. MCP server with 10 tools. Apache 2.0.
git clone https://github.com/cognicore-dev/cognicore-env.git -
Strips 85-97% of HTML/DOM boilerplate into clean Markdown, skeletons, or BM25-ranked RAG chunks.
-
Kwipu
AI repositoriesAsk questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.
git clone https://github.com/benmaster82/Kwipu.git -
HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, Contact Screening, Stocks, Crypto, News
MCP servers75 paid agent tools: website audits and research; BM25, MiniLM vector and hybrid discovery are free.
-
TeamAgentMemory
MCP serversSelf-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + vector recall, and department/team/member isolation. SQLite or Postgres, any OpenAI-compatible LLM.
git clone https://github.com/hsuanshao/TeamAgentMemory.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.