yoloshii/ClawMem — On-device memory layer for AI agents.

Description and use

ClawMem is an open‑source, on‑device memory layer designed for AI agents such as Claude Code, Hermes and OpenClaw. It provides a unified interface of hooks, an MCP server, and a hybrid Retrieval‑Augmented Generation (RAG) search system that enables fast, local context storage and retrieval without relying on external services. The project fits within orchestration, AI/ML, and backend domains, offering developers a lightweight yet powerful way to manage agent memory efficiently.

Problem

yoloshii/ClawMem helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

On-device memory layer for AI agents. Claude Code, Hermes and OpenClaw. Hooks + MCP server + hybrid RAG search.

Source