by lcbcFoo
Your AI Coding Assistant's Long-Term Memory
# Add to your Claude Code skills
git clone https://github.com/lcbcFoo/heimdall-mcp-serverThe Problem: Your AI coding assistant has short-lived memory. Every chat session starts from a blank slate.
The Solution: Heimdall gives your LLM a persistent, growing, cognitive memory of your specific codebase, lessons and memories carry over time.
https://github.com/user-attachments/assets/120b3d32-72d1-4d42-b3ab-285e8a711981
Prerequisites: Python 3.11+ and Docker (for Qdrant vector database).
Heimdall provides a unified heimdall CLI that manages everything from project setup to MCP integration.
pip install heimdall-mcp
This installs the heimdall command-line tool with all necessary dependencies.
Navigate to your project directory and set up Heimdall:
cd /path/to/your/project
# Initialize project memory (starts Qdrant, creates collections, sets up config)
heimdall project init
This single command interactively builds up everything asking user preferences:
.heimdall/ configuration directoryNote: this creates a .heimdall/ directory in your project for configuration - you should NOT commit this - add to .gitignore!
Recommended: Use automatic file monitoring and place files in .heimdall/docs/:
# Copy or symlink your documentation to the monitored directory
ln -r -s my-project-docs ./.heimdall/docs/project-docs
# Start automatic monitoring (files are loaded instantl...
No comments yet. Be the first to share your thoughts!