Memcord

Memcord

Privacy-first, self-hosted chat memory and context management for Claude and AI applications.

18
Stars
5
Forks
18
Watchers
1
Issues
Memcord serves as a self-hosted MCP (Model Context Protocol) server that enables users to securely organize, summarize, and search through their chat history with AI, especially for Claude, without compromising privacy. It offers intelligent memory management, conversation auto-summarization, deduplication, and context merging to build a searchable knowledge base across multiple conversations. Memcord also integrates seamlessly with Claude Desktop, VSCode, and supports various installation methods for flexibility.

Key Features

Infinite memory across unlimited conversations
Intelligent auto-summarization of chat history
100% local storage with no cloud dependence
Smart organization via tags and folders
Automatic deduplication and merging of related conversations
Quick setup and multiple installation methods
Integration with Claude Desktop and VSCode
Tool definition caching for improved performance
Lazy loading of heavy dependencies for faster startup
Search and retrieval of past conversations

Use Cases

Building a searchable, persistent memory of Claude interactions
Summarizing and reviewing past project discussions
Organizing AI-generated chat content into categorized knowledge bases
Ensuring secure, local-only storage of sensitive conversations
Integrating context memory features into developer workflows (e.g., VSCode)
Collaborative AI-assisted project documentation
Efficiently navigating long-term chat histories
Maintaining context across multiple parallel projects
Automating context management for AI assistants
Merging and deduplicating repetitive or related chat threads

README

MCP Server Claude Code Claude Desktop VSCode Python License Buy Me a Coffee

Never Lose Context Again

Transform your Claude conversations into a searchable, organized knowledge base that grows with you

✨ Core Benefits

  • 🧠 Infinite Memory - Claude remembers everything across unlimited conversations with intelligent auto-summarization
  • 🔒 Your Data, Your Control - 100% local storage with zero cloud dependencies or privacy concerns
  • 🎯 Effortless Organization - Smart tags and folders that organize themselves around your workflow
  • 🔗 Intelligent Merging - Automatically combines related conversations while eliminating duplicates

What's new in v2.3.3

text
Optimizations to improve speed, reduce startup time, and improve code maintainability without breaking changes:

 - Tool definition caching to eliminate redundant list_tools() calls
 - Lazy loading for heavy dependencies (TextSummarizer, SimpleQueryProcessor, ContentImporter, MemorySlotMerger) via @property decorators for faster startup
 - Error message constants to eliminate 30+ duplicate string literals and improve maintainability
 - LRU cache (@functools.lru_cache) to _get_mime_type() for faster repeated lookups

🚀 Quick Start

bash
curl -fsSL https://github.com/ukkit/memcord/raw/main/install.sh | bash

This will:

  • Download and setup memcord
  • Set Up Python Virtual Environment using uv
  • Update claude_desktop_config.json & README.md with Installation Path

Claude Desktop/VSCode

json
{
  "mcpServers": {
    "memcord": {
      "command": "uv",
      "args": [
        "--directory",
        "</path/to/memcord>",
        "run",
        "memcord"
      ],
      "env": {
        "PYTHONPATH": "</path/to/memcord>/src"
      }
    }
  }
}

Claude Code MCP (🧪 BETA)

Add MCP server for your project - check README.md for installation path

bash
claude mcp add-json memcord '{"type":"stdio","command":"uv","args":["--directory","</path/to/memcord>","run","memcord"],"env":{"PYTHONPATH":"</path/to/memcord>/src"}}'

Verify installation

bash
claude mcp list
claude mcp get memcord

Add at top of your CLAUDE.md file

bash
memcord_name "NAME_OF_YOUR_PROJECT"

Manual Installaion

bash
# Traditional installation method
git clone https://github.com/ukkit/memcord.git
cd memcord
uv venv
source .venv/bin/activate
uv pip install -e .

# Replace </path/to/memcord/> in claude_desktop_config.json to the path where you installed it manually

Complete Installation Guide - Detailed setup for Claude Code, Claude Desktop, and other MCP applications.

💻 Basic Usage

bash
# Create a memory slot and save conversation
memcord_name "project_meeting"
memcord_save "Our discussion about the new API design..."
memcord_save_progress

# Use existing memory slot
memcord_use "project_meeting" 🆕

# Navigate timeline - select specific entries
memcord_select_entry "2 hours ago"  # or "latest", index, timestamp 🆕

# Privacy control - activate zero mode (no saving)
memcord_zero  # No memory will be saved until switched to another slot

# Search and query your memories
memcord_search "API design decisions"
memcord_query "What did we decide about authentication?"

# Merge related conversations
memcord_merge ["project_meeting", "api_notes"] "consolidated_project" 🆕

Refer to 📖 Complete Tools Reference for Advanced Mode and detailed documentation for all 19 tools with examples and parameters.

📚 Documentation


💎 If you find this project helpful, consider:

  • 🌟 Starring the repository on GitHub
  • 🤝 Support Development
  • 🐛 Reporting bugs and suggesting features

MIT License - see LICENSE file for details.

Star History

Star History Chart

Repository Owner

ukkit
ukkit

User

Repository Details

Language Python
Default Branch main
Size 2,165 KB
Contributors 2
License MIT License
MCP Verified Nov 12, 2025

Programming Languages

Python
99.72%
Shell
0.28%

Tags

Topics

ai-assistant ai-memory chat-history claude-desktop conversation-management developer-tools local-storage mcp-server memory-management memory-slots model-context-protocol model-context-protocol-server privacy-first privacy-focused python

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • In Memoria

    In Memoria

    Persistent memory and instant context for AI coding assistants, integrated via MCP.

    In Memoria is an MCP server that enables AI coding assistants such as Claude or Copilot to retain, recall, and provide context about codebases across sessions. It learns patterns, architecture, and conventions from user code, offering persistent intelligence that eliminates repetitive explanations and generic suggestions. Through the Model Context Protocol, it allows AI tools to perform semantic search, smart file routing, and track project-specific decisions efficiently.

    • 94
    • MCP
    • pi22by7/In-Memoria
  • Membase-MCP Server

    Membase-MCP Server

    Decentralized memory layer server for AI agents using the Model Context Protocol.

    Membase-MCP Server provides decentralized and persistent storage of conversation history and agent knowledge for AI agents using Unibase and the Model Context Protocol. It supports secure, traceable storage and retrieval of messages to ensure agent continuity and personalization within interactions. The server offers integration with Claude, Windsurf, Cursor, and Cline, allowing dynamic context management such as switching conversations and saving or retrieving messages. The server leverages the Unibase DA network for verifiable storage and agent data interoperability.

    • 15
    • MCP
    • unibaseio/membase-mcp
  • Memory MCP

    Memory MCP

    A Model Context Protocol server for managing LLM conversation memories with intelligent context window caching.

    Memory MCP provides a Model Context Protocol (MCP) server for logging, retrieving, and managing memories from large language model (LLM) conversations. It offers features such as context window caching, relevance scoring, and tag-based context retrieval, leveraging MongoDB for persistent storage. The system is designed to efficiently archive, score, and summarize conversational context, supporting external orchestration and advanced memory management tools. This enables seamless handling of conversation history and dynamic context for enhanced LLM applications.

    • 10
    • MCP
    • JamesANZ/memory-mcp
  • Zettelkasten MCP Server

    Zettelkasten MCP Server

    A Zettelkasten-based knowledge management system implementing the Model Context Protocol.

    Zettelkasten MCP Server provides an implementation of the Zettelkasten note-taking methodology, enriched with bidirectional linking, semantic relationships, and categorization of notes. It enables creation, exploration, and synthesis of atomic knowledge using MCP for AI-assisted workflows. The system integrates with clients such as Claude and supports markdown, advanced search, and a structured prompt framework for large language models. The dual storage architecture and synchronous operation model ensure flexibility and reliability for managing personal or collaborative knowledge bases.

    • 114
    • MCP
    • entanglr/zettelkasten-mcp
  • MCP Manager for Claude Desktop

    MCP Manager for Claude Desktop

    A desktop app to manage Model Context Protocol (MCP) servers for Claude Desktop on MacOS.

    MCP Manager for Claude Desktop provides a user-friendly interface to manage Model Context Protocol (MCP) servers, enabling Claude to access private data, APIs, and local or remote services securely from a MacOS desktop. It facilitates rapid configuration and integration with a wide variety of MCP servers, including productivity tools, databases, and web APIs. The app runs locally to ensure data privacy and streamlines connecting Claude to new sources through simple environment and server settings management.

    • 270
    • MCP
    • zueai/mcp-manager
  • Unichat MCP Server

    Unichat MCP Server

    Universal MCP server providing context-aware AI chat and code tools across major model vendors.

    Unichat MCP Server enables sending standardized requests to leading AI model vendors, including OpenAI, MistralAI, Anthropic, xAI, Google AI, DeepSeek, Alibaba, and Inception, utilizing the Model Context Protocol. It features unified endpoints for chat interactions and provides specialized tools for code review, documentation generation, code explanation, and programmatic code reworking. The server is designed for seamless integration with platforms like Claude Desktop and installation via Smithery. Vendor API keys are required for secure access to supported providers.

    • 37
    • MCP
    • amidabuddha/unichat-mcp-server
  • Didn't find tool you were looking for?

    Be as detailed as possible for better results