Melchizedek
@louis49
Melchizedek について
Persistent memory for Claude Code. Automatically indexes every conversation transcript and provides 16 MCP tools for hybrid search (BM25 + vectors + reranker). Works offline, zero config, single SQLite file. Claude never forgets again.
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"melchizedek": {
"command": "npx",
"args": [
"-y",
"melchizedek@latest"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Melchizedek?
Melchizedek is a persistent memory server for Claude Code that automatically indexes every conversation and provides production-grade hybrid search (BM25 + vectors + reranker) via MCP tools. It runs 100% locally with zero configuration, zero API keys, and no cloud dependencies.
How to use Melchizedek?
Install via npm install -g melchizedek, then add the MCP server to Claude Code with claude mcp add --scope user melchizedek -- melchizedek-server. For automatic indexing, hooks need to be configured in ~/.claude/settings.json (pre-configured for marketplace installs). After setup, restart Claude Code. Indexing starts automatically. Use MCP tools like m9k_search, m9k_context, and m9k_full to search and retrieve past conversations.
Key features of Melchizedek
- 100% local, zero config, zero API keys
- Hybrid search: BM25 + text and code vectors + reranker
- Progressive retrieval (search/context/full) to save tokens
- Automatic indexing of all Claude Code conversations
- 16 MCP tools for search, memory management, and configuration
- Retroactive indexing of existing conversation history
Use cases of Melchizedek
- Quickly find past debugging sessions and error solutions
- Recall architectural decisions and code patterns across projects
- Automatically index every conversation without manual saving
- Retrieve full context of past Claude Code interactions
FAQ from Melchizedek
What runtime does Melchizedek require?
Melchizedek runs on Node.js and is installed via npm. It requires no external services or API keys.
Where is conversation data stored?
All data is stored locally in a single SQLite file at ~/.melchizedek/memory.db. The file uses WAL mode and is not sent to any cloud service.
Does Melchizedek work offline?
Yes, Melchizedek is 100% offline. No cloud, no API keys, no internet connection required for search or indexing.
How is Melchizedek different from other memory plugins?
Melchizedek acts as a search engine that indexes raw conversation transcripts, supporting hybrid search (BM25 + vectors + reranker), progressive retrieval, and zero-config automatic indexing. It offers 16 MCP tools, supports dual embeddings (text + code), and runs as a singleton daemon for multi-window use.
Is Melchizedek free and open source?
Yes, Melchizedek is released under the MIT license and is completely free to use. Donations are accepted via PayPal or Buy Me a Coffee.
「AI とエージェント」の他のコンテンツ
meGPT - upload an author's content into an LLM
adriancoCode to process many kinds of content by an author into an MCP server
Gemini MCP Server
aliargunMCP server implementation for Google's Gemini API
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
Unreal Engine Generative AI Support Plugin
prajwalshettydevUnreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agenti
MCP Claude Code
SDGLBLMCP implementation of Claude Code capabilities and more
コメント