by ukkit
Organize, summarize, and search Claude Desktop chat histories locally, providing infinite memory with privacy‑first storage.
Memcord is a self‑hosted MCP server that turns Claude conversations into a searchable, organized knowledge base. It keeps every message on your machine, automatically tags, merges, and summarizes chats so you never lose context.
curl -fsSL https://github.com/ukkit/memcord/raw/main/install.sh | bash
This downloads the repo, creates a Python virtual environment with uv, and updates the Claude Desktop configuration.git clone https://github.com/ukkit/memcord.git
cd memcord
uv venv
source .venv/bin/activate
uv pip install -e .
Then point claude_desktop_config.json to the installation path.mcpServers section of your Claude config:
{
"memcord": {
"command": "uv",
"args": ["--directory", "</path/to/memcord>", "run", "memcord"],
"env": { "PYTHONPATH": "</path/to/memcord>/src" }
}
}
memcord_name "project_meeting"
memcord_save "Discussion about the new API design..."
memcord_save_progress
memcord_use "project_meeting"
memcord_search "API design decisions"
memcord_query "What did we decide about authentication?"
memcord_merge ["project_meeting","api_notes"] "consolidated_project"
All commands are available as MCP tools; invoke them through Claude Code or Claude Desktop.Q: Do I need an internet connection? A: No. All data stays on your machine; the server runs locally.
Q: Can I use Memcord with other AI models? A: Memcord follows the Model Context Protocol, so any compatible client can connect, though the README focuses on Claude Desktop.
Q: How is data secured? A: Files are stored in a local directory you control. You can encrypt the folder or run the server inside a sandbox.
Q: What if the storage health check reports "UNHEALTHY"? A: Update to v2.3.2; the release fixes async/await issues in the diagnostic tools.
Q: How do I upgrade?
A: Pull the latest changes from the GitHub repo and rerun the install script or uv pip install -e . inside the virtual environment.
Transform your Claude conversations into a searchable, organized knowledge base that grows with you
Storage health reports as UNHEALTHY due to async/await issue.
Updated methods to async that were missed earliers
- DiagnosticTool.run_health_checks()
- DiagnosticTool._check_storage_health()
- DiagnosticTool.generate_system_report()
- StatusMonitoringSystem.get_system_status()
- StatusMonitoringSystem.generate_full_report()
curl -fsSL https://github.com/ukkit/memcord/raw/main/install.sh | bash
This will:
{
"mcpServers": {
"memcord": {
"command": "uv",
"args": [
"--directory",
"</path/to/memcord>",
"run",
"memcord"
],
"env": {
"PYTHONPATH": "</path/to/memcord>/src"
}
}
}
}
Add MCP server for your project - check README.md for installation path
claude mcp add-json memcord '{"type":"stdio","command":"uv","args":["--directory","</path/to/memcord>","run","memcord"],"env":{"PYTHONPATH":"</path/to/memcord>/src"}}'
Verify installation
claude mcp list
claude mcp get memcord
Add at top of your CLAUDE.md file
memcord_name "NAME_OF_YOUR_PROJECT"
# 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.
# 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.
💎 If you find this project helpful, consider:
MIT License - see LICENSE file for details.
Please log in to share your review and rating for this MCP.
Explore related MCPs that share similar capabilities and solve comparable challenges
by modelcontextprotocol
A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.
by topoteretes
Provides dynamic memory for AI agents through modular ECL (Extract, Cognify, Load) pipelines, enabling seamless integration with graph and vector stores using minimal code.
by basicmachines-co
Enables persistent, local‑first knowledge management by allowing LLMs to read and write Markdown files during natural conversations, building a traversable knowledge graph that stays under the user’s control.
by smithery-ai
Provides read and search capabilities for Markdown notes in an Obsidian vault for Claude Desktop and other MCP clients.
by chatmcp
Summarize chat messages by querying a local chat database and returning concise overviews.
by dmayboroda
Provides on‑premises conversational retrieval‑augmented generation (RAG) with configurable Docker containers, supporting fully local execution, ChatGPT‑based custom GPTs, and Anthropic Claude integration.
by qdrant
Provides a Model Context Protocol server that stores and retrieves semantic memories using Qdrant vector search, acting as a semantic memory layer.
by doobidoo
Provides a universal memory service with semantic search, intelligent memory triggers, OAuth‑enabled team collaboration, and multi‑client support for Claude Desktop, Claude Code, VS Code, Cursor and over a dozen AI applications.
by GreatScottyMac
Provides a project‑specific memory bank that stores decisions, progress, architecture, and custom data, exposing a structured knowledge graph via MCP for AI assistants and IDE tools.