Enables AI assistants to query a project's unified graph (code, documents, decisions) with token-budgeted, ranked context, including focus, impact, and find operations.
Enables AI agents to search and retrieve past chat transcripts from Cursor, Claude Code, and Kiro, providing a global, local memory for context-aware assistance.
Enables LLM clients to query a comprehensive Midnight knowledge workspace using indexed evidence from code, Confluence, and Google Drive, with source integrity enforcement and audience-specific answer shaping.