memory

You can maintain context across AI sessions by storing summaries of conversations and key decisions in a local vector database. This allows you to search and retrieve past interactions when resuming work.

You store context by executing a command with a text summary of your actions, relevant tags, a project name, and a unique session ID. This saves your conversation details into the vector database for future retrieval.

Yes, this Skill requires ChromaDB as its dependency for local vector database storage. ChromaDB handles the underlying storage and retrieval mechanisms necessary to persist and query your session contexts.

Yes, you can search past conversations to recall previous actions and decisions. The Skill queries the local vector database to retrieve relevant information and context from your previous sessions.

The best way to remember code patterns is to explicitly save them as context with descriptive tags and a project name. This allows you to retrieve the exact code patterns and decisions later by querying the stored memory.

A limitation of using a local vector database for AI memory is that your stored context remains confined to the local environment. You cannot access this persistent memory from remote or distributed environments without manual configuration.