Melchizedek
@louis49
About Melchizedek
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.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"melchizedek": {
"command": "npx",
"args": [
"-y",
"melchizedek@latest"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
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.
More AI & Agents MCP servers
🛡️ A.I.G(AI-Infra-Guard)
TencentA full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
MCP Server - Remote MacOs Use
baryhuangThe only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App
1Panel
1Panel-dev🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
Perplexity MCP Server
DaInfernalCoderA Model Context Protocol (MCP) server for research and documentation assistance using Perplexity AI. Won 1st @ Cline Hackathon
Comments