"Chinese greeting or conversation starter" matching MCP servers:

Keyless local RAG over your own documents (ChromaDB) with traceable citations, exposed as MCP tools and a FastAPI endpoint.

Multi-modal RAG engine for AI assistants. Stores conversation history, conclusions, diffs, error traces, and other development artifacts in LanceDB with vector search, multi-factor scoring, and an LLM-driven consolidation pipeline.

A local-first personal RAG memory system that turns AI conversation history into a searchable, retrievable knowledge base via MCP, enabling LLMs to semantically search past conversations.

Agent memory for facts that change. When a user corrects something, Recall replaces the old fact, tells the agent what it replaced, and keeps the old value in a history. Ask what was believed on any date, see every change to a fact, or diff two dates. Runs locally on polign_db, Postgres with pgvector, MongoDB, or Qdrant. Apache 2.0.

A personal memory MCP server that ingests AI agent conversation logs from multiple platforms into a searchable PostgreSQL+pgvector database, enabling cross-session recall of past reasoning and decisions.

Provides AI agents with persistent, searchable memory using semantic search, auto-linking, and categorization, with zero-config local setup or production-ready external providers.

Enables agents to run semantic search across one or more local project directories by automatically maintaining a LAN-local Qdrant index with Ollama embeddings. Indexing, staleness checks, and incremental updates happen transparently, so users can query code by meaning without managing collections, chunks, or hashes.

An MCP server that retrieves resume/experience evidence relevant to a job description via vector RAG, and tracks fit-analysis results in a configurable tracking store (Notion or SQLite), with tools like match_job, push_to_tracker, and list_applications.

Turns a tools.yaml contract into typed, tenant-guarded vector database tools that agents can use via Python imports or MCP.

Lets AI assistants connect to Apache Solr deployments to enumerate collections and schemas, run full-text and filtered queries, apply faceting and sorting, and issue SQL or vector-semantic searches without building custom API glue. Communicates over stdio or SSE and requires minimal environment configuration instead of app-specific credentials or mandatory ZooKeeper wiring.

Enables users to build and manage a complete retrieval-augmented generation pipeline through conversation, including file ingestion, collection management, hybrid search, reranking, citations, and a guided setup wizard.

A fully-local, three-layer memory plugin for Claude Code with Chinese support, offering hybrid FTS5/trigram and HNSW vector search, self-iterating memory management, consolidation, and a web console.

An experimental MCP server that makes YouTube playlist transcripts available for AI assistants, enabling search and conversation about video content.

Enables Claude to build and query a local, folder-based knowledge base with hybrid vector and BM25 search, save and edit notes, ingest Markdown/text folders with source citations, and browse or restore version history — all running embedded on a laptop with no server or API key.

It connects an agent to a PostgreSQL database so it can inspect schemas, run validated reads and writes, resolve fuzzy names via trigram search, and perform or store pgvector embedding searches. Vector and hybrid search operate through an OpenAI-compatible embeddings endpoint, letting agents query by text without handling embedding arrays.

A flexible memory system for AI applications that supports multiple LLM providers and can be used either as an MCP server or as a direct library integration, enabling autonomous memory management without explicit commands.

MCP server providing context usage estimation, conversation compaction, and durable semantic memory via local embeddings and SQLite.

Gives AI agents a local-first, persistent memory backed by a single SQLite file, letting them save decisions, preferences, and facts, then recall them by meaning or keyword across sessions and projects. Exposes tools for loading pinned context, searching, adding, updating, listing, and deleting memories, so agents stop forgetting between sessions.

Mem0-compatible persistent memory for AI agents - write facts once, recall them semantically in any session. Self-hostable open-source server, or managed cloud with a remote MCP endpoint at https://deepmem.dev/mcp.

An offline-first, governed memory and knowledge server for AI agents that provides Remember, Search, Update, and Forget operations with hybrid retrieval, semantic embeddings, and NID-based authentication. It can be used as an MCP server via stdio or Streamable HTTP, enabling agents to persist and query memories and wiki knowledge.

Official MCP server for Stoolap, an embedded SQL database written in Rust. Lets assistants run SQL queries and transactions, inspect and change schemas, and do vector search over a local file or in-memory database, with a read-only mode.

Enables MCP clients like Claude, Cursor, and Windsurf to search a local document knowledge base using four-layer retrieval fusion (vector similarity, BM25 keywords, knowledge graph traversal, and metadata filtering) with cross-encoder reranking. Also lets agents index documents, add single documents, list indexed sources, and run health diagnostics, with models kept warm between queries so no GPU, PyTorch, or API keys are needed.

Enables GitHub Copilot Chat to semantically search locally indexed source code, documentation, and project statistics from reference projects through a fully local vector store. This lets Copilot find existing implementations and conventions so it generates new code homogeneous with established patterns, without any API keys or data leaving the machine.

Enables users to index and retrieve local documents through semantic, BM25, or hybrid search, with tools for chunk reads and page images accessible from MCP clients such as Codex and ChatGPT web.

A high-performance MCP server for semantic search and codebase indexing using the Qdrant vector database. It features optimized embedding pipelines, AST-aware chunking, and git metadata enrichment for fast, privacy-focused local or remote search.

Helps developers tackle legacy codebases by giving AI coding assistants context through Qdrant vector store and Agentic RAG with Ollama or DeepSeek.

Enables agents to search local Chinese text memories and fetch individual records through stdio tools, using bigram FTS5 recall with optional vector rank fusion.

Enables semantic and hybrid search over documents and codebases backed by a Qdrant vector database, with collection management, document CRUD, metadata filtering, and AST-aware code indexing using local or cloud embedding providers. Supports natural language queries, incremental re-indexing of changed files, and custom configurable prompts for guided workflows.

A fully-local AI memory system that saves notes, code, and terminal output to a vector database via Ollama and LanceDB, enabling context retrieval from terminal, API calls, or inside Claude Code.

A Model Context Protocol server for generating text embeddings using OpenAI, Anthropic, or Ollama, with tools for single and batch embedding operations.