Knowledge & MemoryGo

tomohiro-owada/devrag

Lightweight local RAG MCP server for semantic vector search over markdown documents. Reduces token consumption by 40x with sqlite-vec and multilingual-e5-small embeddings. Supports filtered search by directory and filename patterns.

tomohiro-owada View Repository

knowledge-memorylocal-servicemacoswindowslinux

Quick Start

Clone the repository:

git clone https://github.com/tomohiro-owada/devrag

Claude Desktop configuration example:

{
  "mcpServers": {
    "devrag": {
      "command": "npx",
      "args": [
        "-y",
        "tomohiro-owada/devrag"
      ]
    }
  }
}

Check the repository README for specific installation and configuration instructions.

Details

More Knowledge & Memory Servers

0xshellming/mcp-summarizer

AI Summarization MCP Server, Support for multiple content types: Plain text, Web pages, PDF documents, EPUB books, HTML content

Unknown

20alexl/mini_claude

Persistent memory and guardrails for Claude Code. Features mistake tracking, loop detection, scope guard, and hooks that block risky edits. Runs locally with Ollama.

Python

agentic-mcp-tools/memora

Persistent memory with knowledge graph visualization, semantic/hybrid search, cloud sync (S3/R2), and cross-session context management.

Python

apecloud/ApeRAG

Production-ready RAG platform combining Graph RAG, vector search, and full-text search. Best choice for building your own Knowledge Graph and for Context Engineering

Python

bh-rat/context-awesome

MCP server for querying 8,500+ curated awesome lists (1M+ items) and fetching the best resources for your agent.

TypeScript

bitbonsai/mcp-obsidian

Universal AI bridge for Obsidian vaults using MCP. Provides safe read/write access to notes with 11 comprehensive methods for vault operations including search, batch operations, tag management, and frontmatter handling. Works with Claude, ChatGPT, and any MCP-compatible AI assistant.

TypeScript