Goldentrii

agent-recall

Persistent compounding memory for AI agents. 10 MCP tools: session_start, remember, recall, session_end, check, digest, project_board, project_status, bootstrap_scan, bootstrap_import. Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.