- Conduid
- Marketplace
- #vector-search
MCP servers tagged vector-search
546 live MCP servers tagged "vector-search", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with vector-search.
Inkwell Memory
MCP server giving AI agents persistent memory: Markdown files as source of truth, hybrid BM25 + embedding search, typed graph relations. Self-hosted, single Docker image.
Minni
Local-first memory and governance layer for AI agents, with per-agent vaults, hybrid recall, review-first learning, handoffs, audit trails, and native AFM/bridge provider support.
Smara
Persistent memory for AI tools. Give Claude, Cursor, and Codex shared context that survives across sessions.
Vector Rules
The model measures, your rules decide — and prove it. Vector math as a first-class operand in a deterministic Rete engine: policy lives in Git, every decision returns a proof tree…
Stele Context
Local context cache for LLM agents. 100% offline, zero dependencies.
2dph
Fact evidence-first brain with property graph + hybrid RAG. Search is deduction. ETL included.
MindForge
Production-grade lifelong memory for AI agents — 4-tier memory, knowledge graph, E2EE, federated P2P, MCP server.
Memory Plugin
Local-first memory, hybrid RAG, and agent personalization for AI coding agents. MCP + CLI for OpenCode, Claude Code, Codex, Gemini CLI, Antigravity, and Jules.
AI Memory Comparison
Interactive comparison of persistent memory systems for AI coding agents and chatbots
MidMem
Middleware memory layer for LLM agents: a shared knowledge store with hybrid retrieval, tiered memory, a knowledge graph, and governance, exposed over MCP, CLI, and API.
Devonsdb
Embedded graph database written from scratch in Rust: stable on-disk format, MVCC concurrent writers, first-class vectors + full-text + geo, plain-English queries compiled to dete…
Wisprnote AI
AI chief of staff for your meetings. No bot joins the call — Wisprnote listens on your Mac, turns months of meetings into a searchable knowledge graph, connects Jira, GitHub, Slac…
Treeloom
GraphRAG code search over MCP. Parses code with tree-sitter, weaves a Neo4j code graph, and serves hybrid semantic search to AI agents at lower cost than grep.
Hermes Agent Harness Plus
🧸✨ Hermes Agent companion toolbox for task evidence, local recall, reusable skills, and optional Prime minion orchestration.
Local File Assistant MCP
AI-powered local filesystem assistant with semantic search using MCP, Claude Desktop, and Ollama.
Myrmo
Shared memory for AI agents. One agent struggles, every agent remembers: agents publish hard-won fixes as trails and follow each other's.
Kortex Memory
Production-grade, multi-tenant memory layer for LLMs and AI coding agents (Claude Code, Codex, OpenCode). Plug it in via MCP and your agents get a shared, durable, scoped, access-…
Vantadb
Embedded persistent memory and vector retrieval engine for local-first AI apps, with HNSW, BM25, and RRF hybrid retrieval.
Nqlite
A context-first, deterministic, single-file database for AI agents — SQLite for AI memory. Records, typed graph relations, BYO embeddings, and time under one ACID transaction. No-…
Magento MCP Server
🧠 MCP server that gives AI agents symbolic, GraphRAG-style reasoning over a Magento, Adobe Commerce, MageOS and PHP codebase, plus semantic search over its admin configuration.
Pinterest Vision MCP
Visual intelligence pipeline for AI agents — search Pinterest, analyze with LLM vision, store and retrieve by semantic similarity
Anchor
Source-grounded chunk validation as a primitive. Spring Boot service exposing two interfaces (LLM-to-LLM and human-facing) over the same hierarchical document model.
Hippocampus
Self-hosted persistent long-term memory for Claude Code and MCP clients. One memory for every session and machine: hybrid BM25 + local vector + knowledge-graph search over plain M…
Qdrant MCP Server
MCP server for semantic code search using Qdrant vector database and OpenAI embeddings
Mnemo MCP
A portable cognitive memory for AI agents. An MCP server with semantic search and decay.
Rag MCP
Self-hosted RAG-over-MCP server for searchable long-term memory over your markdown/PDF docs — hybrid dense+BM25 retrieval, pluggable embeddings, optional reranking
Mnema
Mnema — one memory for every AI agent. Shared memory, RAG and project maps over MCP + REST; SQLite hybrid search, multi-device sync, self-hosted.
AI Memory
🧠 Manage semantic memory for AI agents with this production-ready Model Context Protocol server, enabling efficient storage and retrieval of contextual knowledge.
Agentdb
AgentDB — Single-file embedded database for AI agents. SQL + Vector Search + Memory Graphs. Built in Rust.
Nexus Memory
Universal shared memory for AI agents — one brain for all your agents, 100% local & private. Works with Hermes, OpenClaw, Claude Code, Cursor. (Not the PyPI 'nexus-memory' package)
AI Engineer
AI engineering portfolio with Next.js demos for LLMs, RAG, vector search, embeddings, agents, MCP, guardrails, observability, prompt engineering, and token economics.
Agentmemory
Public fork of rohitg00/agentmemory focused on Docker-first local deployment, Codex-native lifecycle ingestion, freshness-oriented retrieval, diagnostics.
Atlas
Local-first memory, knowledge and evidence infrastructure for AI agents. Persistent state, hybrid search, graph + MCP. Signed releases, one-line install. Free tier.
DocMind
轻量向量知识库工具 — 本地 ONNX 嵌入 + sqlite-vec 混合检索 + MCP 工具接口 + RAG 对话
Agentic Memory
6-layer persistent memory (sensory, working, episodic, semantic, long-term, procedural) with non-destructive belief revision and injection-safe context synthesis — an MCP server f…
AI Memory MCP
MCP server giving Claude, ChatGPT and any AI assistant long-term memory: 100% local semantic search over your conversation history. No cloud, no API keys.
Agentic Rag MCP
Multi-agent RAG (LangGraph) exposed as an MCP server: plan -> retrieve -> synthesize -> self-critique with citations. Claude + pgvector + Voyage + Firecrawl.
Membrain
Production-grade agentic memory that lets AI agents revise beliefs, invalidate unsafe decisions, and block stale actions — powered by CockroachDB + AWS.
NeuroVault
NeuroVault - A self-evolving 3D knowledge brain that runs entirely on your machine. SQLite + FTS5, 31 autonomous circuits, HNSW vector search, Obsidian vault, MCP integration.
AI Memory Free
Free MIT-licensed, LLM-agnostic memory for any AI project — Supabase, pgvector, Vault, HTTPS, and MCP.
Fornixdb
Persistent local memory for any AI — private, model-agnostic, and inspectable.
Prbe Knowledge
Self-hosted knowledge engine: ingest your team's tools, hybrid (vector+keyword+graph) retrieval, cited LLM answers.
Stratanote
A modern collaborative Markdown knowledge base and note-taking application inspired by Obsidian.
Memory Core MCP
Self-hosted MCP memory server over Oracle ADB 23ai (native AI Vector Search). z-mesh gateway + n8n workflows. Local-first, no cloud memory API.
Grepogram
Semantic search for your Telegram chats — fully local hybrid retrieval, MCP server + CLI for any AI agent
Claudebase
Local infrastructure for LLM agents — hybrid retrieval, cognitive memory, persistent channels
X402seek Web
Public reviewer preview of x402Seek: semantic discovery for x402-payable services on Stellar testnet. Real embedding-based ranking with abstention over a frozen evidence catalog,…
Obsidian Chromadb Self Evolving Kb
面向 Markdown 知识库的自进化 RAG 检索引擎：BGE 向量 + BM25 + RRF 融合检索，两阶段 Rerank，反馈驱动 BGE 微调闭环（离线闸门保障安全上线）。开箱自证检索质量，支持 Obsidian 同步与 FastAPI/MCP 服务。
Semlith
A fast local vector store for AI agents — index files once, keep it current as you save, and answer questions across all of it in milliseconds without leaving the machine.
Enterprise Shared Memory Poc
Governed shared-memory control plane for coding agents: PostgreSQL-authoritative experience cards, replaceable vector index, and a utility-aware USE/ABSTAIN router with auditable…