Memory Extension

This extension provides a persistent memory layer for the Gemini CLI using MongoDB Atlas. It enables the AI to "remember" previous interactions, user preferences, and project-specific context across different terminal sessions.

Workflow

• Session Persistence: Maintains a sliding window of the last 20 interactions for immediate context.
• Semantic Long-Term Memory: Uses MongoDB Atlas Vector Search to recall relevant facts from past weeks/months.
• Preference Management: Store environment-specific configurations (e.g., "always use Yarn over NPM").
• Automatic Context Injection: Automatically fetches relevant "memory documents" before Gemini generates a response.

🛠️ Skills Included

1. store_memory

Saves a specific fact or interaction to the long-term database.

• Input: fact (string), category (string: 'preference', 'project', 'snippet')