Moss

Moss is a real-time semantic search runtime for conversational and voice AI agents. Indexes and queries live next to the agent (server, browser, or device) so retrieval lands in under 10 ms.

Official docs: https://docs.moss.dev/docs/start/quickstart

When to Use

Use this skill when you need to:

• Build a low-latency retrieval layer for a voice or chat agent
• Manage a Moss index (create, add docs, search, update, delete)
• Bulk-load knowledge base content into a Moss project
• Inspect or list the indexes that already exist in a Moss project