Wax
Active·★ 805·Apache-2.0·Updated 2026-10-01
Wax provides persistent, searchable, and private on-device memory for iOS and macOS AI agents, eliminating the need for servers or cloud services. It integrates document storage, semantic search (HNSW), full-text search (BM25), and token budgeting into a single, crash-safe .wax file.
Wax sits in the RAG / Knowledge Base category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Hybrid retrieval (BM25 + HNSW). A representative use case is Conversational agents remembering user preferences. The listed license is Apache-2.0. GitHub stars are currently 805. Relevant tags include AI Agents, On-device AI.
