Store a piece of text as a semantic memory in the local vector database.

Call this tool whenever the user explicitly asks you to remember something, or whenever you observe context that should survive the current session:

• Architectural decisions or design rationale

• User preferences and working-style notes

• Frequently-referenced file paths or API endpoints

• Summaries of long conversations or research findings

One focused idea per memory retrieves better than a large wall of text.

Search local vector memory for context semantically similar to query.

Call this at the start of a task to surface relevant context from past sessions before you begin reasoning or writing code. The search is embedding-based (not keyword-based), so natural-language questions work better than exact terms.

Example queries:

• "how does authentication work in this project?"

• "user's preferred code style and formatting rules"

• "database schema decisions"

Permanently delete all memories stored under project_tag.

This action is irreversible — vectors and metadata are removed from disk immediately. Only call this when the user has explicitly asked to clear or reset memory for a project. When in doubt, confirm with the user before calling.