Vector Search

Generic markdown vault MCP with hybrid search

Local document search over your folders: hybrid keyword+semantic, fully offline, read-only

Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.

Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.

Git-versioned markdown memory for AI agents: save, search, compact, lint, and audit.

Academic paper knowledge-base MCP server: PDF ingest, vector search with reranking, KB management.

Local-first persistent memory for AI coding agents.

Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.

Everything plus the kitchen sink for PowerPoint: native editable diagrams, live editing, 138 tools.

Version-controlled golden datasets and RAG evaluation, no API key needed.

Shared, project-aware memory for Claude Code, Codex, and other agents with human review.

Knowledge base for Claude Code with semantic search, feed intelligence, and teams

Fresh, attributed facts from your sources — cached, and invalidated the moment a source changes.

Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.

Similarity search, hybrid search, and index management for pgvector-backed PostgreSQL tables

MCP server for jPOS and ISO 8583. Deterministic payment protocol tools for AI agents.

Zero-config MCP server for searchable documentation. SQLite or PostgreSQL.

Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.

Compress logs, retrieval chunks, and code context into structured LLM-ready signal.

LynxMCP: 100% local MCP server for the code questions grep can't answer: call graph, hybrid search