ClawMem

ClawMem is a local context engine providing retrieval-augmented memory for AI agents like Claude Code, OpenClaw, and Hermes. It combines multiple retrieval and scoring techniques (BM25, vector search, intent classification, graph traversal) to surface relevant context. It integrates via hooks, MCP server, or plugins, and shares a single SQLite vault across runtimes.

ClawMem 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 Retrieval-augmented memory with hybrid search (BM25 + vector + reranking). A representative use case is Persistent memory for AI coding assistants across sessions. The listed license is MIT. GitHub stars are currently 211. Relevant tags include ai-agent-memory, ai-agents.