hot-memory-mcp

@michael-denyer/hot-memory-mcp

0 Stars 9 次浏览 michael-denyer 更新于 2026-08-23

Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.

MCP 服务配置

复制以下 JSON 到 OPClaw 或其他 MCP 客户端的配置文件中即可使用

{
  "mcpServers": {
    "hot-memory-mcp": {
      "args": [
        "hot-memory-mcp@0.7.3"
      ],
      "command": "uvx"
    }
  }
}

可用工具（5 个）

该服务在 MCP 协议中暴露的工具，AI 可按需调用

tavily_search 14 个参数需填 1 项 Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.

Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.

必填参数：query

tavily_extract 6 个参数需填 1 项 Extract content from URLs. Returns raw page content in markdown or text format.

Extract content from URLs. Returns raw page content in markdown or text format.

必填参数：urls

tavily_crawl 11 个参数需填 1 项 Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.

Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.

必填参数：url

tavily_map 8 个参数需填 1 项 Map a website's structure. Returns a list of URLs found starting from the base URL.

Map a website's structure. Returns a list of URLs found starting from the base URL.

必填参数：url

tavily_research 2 个参数需填 1 项 Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings.

Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings.

必填参数：input

服务介绍

<!- - mcp-name: io.github.michael-denyer/hot-memory-mcp - ->

🧠 Memory MCP

# # Give your AI assistant a persistent second brain

Stop re-explaining your project every session.

Memory MCP learns what matters and keeps it ready — instant recall for the stuff you use most, semantic search for everything else.

# The Problem

Every new chat starts from scratch. You explain your architecture again. You paste the same patterns again. Your context window bloats with repetition.

Other memory solutions help, but they still require tool calls for every lookup — adding latency and eating into Claude's thinking budget.

Memory MCP fixes this with a two-tier architecture:

Hot cache (0ms) — Frequently-used knowledge auto-injected into context before Claude even starts thinking. No tool call needed.
Cold storage (~50ms) — Everything else, searchable by meaning via semantic similarity.

The system learns what you use and promotes it automatically. Your most valuable knowledge becomes instantly available. No manual curation required.

# Before & After

# Install

#  Install package
uv tool install hot-memory-mcp   #  or: pip install hot-memory-mcp

#  Add plugin (recommended)
claude plugins add michael-denyer/memory-mcp

The plugin gives you auto-configured hooks, slash commands, and the Memory Analyst agent. MLX is auto-detected on Apple Silicon.

Add to ~/.claude.json:

{
  "mcpServers": {
    "memory": {
      "command": "memory-mcp"
    }
  }
}

See Reference for full configuration options.

Restart Claude Code. The hot cache auto-populates from your project docs.

First run: Embedding model (~90MB) downloads automatically. Takes 30-60 seconds once.

# How It Works

flowchart LR
    subgraph LLM["Claude"]
        REQ((Request))
    end

    subgraph Hot["HOT CACHE · 0ms"]
        HC[Session context]
        PM[(Promoted memories)]
    end

    subgraph Cold["COLD STORAGE · ~50ms"]
        VS[(Vector search)]
        KG[(Knowledge graph)]
    end

    REQ - ->|"auto-injected"| HC
    HC -.->|"draws from"| PM
    REQ - ->|"recall()"| VS
    VS <- ->|"related"| KG

The hot cache (~10 items) is injected into every request — it combines recent recalls, predicted next memories, and top promoted items. Promoted memories (~20 items) is the backing store of frequently-used memories. Memories used 3+ times auto-promote; unused ones demote after 14 days.

# What Makes It Different

Most memory systems make you pay a tool-call tax on every lookup. Memory MCP's hot cache bypasses this entirely — your most-used knowledge is already in context when Claude starts thinking.

The Engram Insight: Human memory doesn't search — frequently-used patterns are already there. That's what hot cache does for Claude.

# Quick Reference

See Reference for all 14 slash commands and full tool API.

# # Dashboard

memory-mcp-cli dashboard    #  Opens at http://localhost:8765

Dashboard

Browse memories, hot cache, mining candidates, sessions, and knowledge graph.

# How to Use

Memory MCP is designed to run as three complementary components:

The plugin is recommended for most users — it auto-configures the MCP server and adds productivity features. Run the dashboard alongside when you want visibility into what's being stored.

# Documentation

# License

MIT

查看源码项目主页