Vector Search

Find a retrieval MCP server that works today: a daily-checked list of servers that search knowledge.

Local hybrid search for Korean Markdown notes and Obsidian vaults — BM25 with Korean particle stripping, Hangul bigram FTS, Qwen3 vector search and LLM reranking, as CLI, MCP server and SDK

Local-first image, vector and document toolkit that measures its own output. Nothing uploaded.

Cloud-persistent, semantic-search memory MCP — drop-in for server-memory, backed by ZeroDB.

Universal repo-to-MCP bridge with multi-harness configs and model/checkpoint adapters

MAMA MCP Server - Memory-Augmented MCP Assistant for Claude Code & Desktop

Official TypeScript Model Context Protocol (MCP) Server for ROMASHKA SLM & VectorRAT with Modular Facets (--mode=engine|builder|all)

Persistent self-improving agent memory with tree-of-thoughts reasoning: MCTS/beam search, PRM step verification, self-consistency voting, s1 budget forcing, REPL program-aided reasoning, reflexion self-correction, failure classification, experience replay

MCP server for VantagePeers — shared memory, messaging, and task coordination for AI agent teams

Chitta - permission-aware memory for AI agents: a knowledge-graph + vector memory MCP server + SDK with per-user access control. Runs on Bun. By 100xprompt.

End-to-end encrypted, agent-portable memory for OpenClaw and any LLM-agent runtime. XChaCha20-Poly1305 with protobuf v4 + on-chain Memory Taxonomy v1 (claim / preference / directive / commitment / episode / summary).

Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.

Temporal GraphRAG on libSQL/SQLite, Postgres, or DuckDB — typed schema, bitemporal graph, vector + FTS retrieval, a served HTTP API, React Query hooks, and an MCP server

Model Context Protocol (MCP) server for advanced GitHub repository analysis and code discovery. Provides AI assistants with powerful tools to search, analyze, and understand codebases across GitHub.

Local memory and context retrieval for AI agents through CueMap.

Obsidian-vault-first memory for AI agents: hybrid vector + keyword + graph retrieval over markdown, MCP server, git auto-sync

MCP server for Bildlag — search, retrieve, tag and upload photos in your libraries via Claude Desktop or Claude Code

Self-hosted permission-aware context layer. Search returns only what the caller may read.

On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.

Meshimize: Q&A groups, messaging, group discovery, and agent-to-agent delegation