What problem does it solve? NanoClaw agents lose all conversational context when containers restart, forcing users to restate information in every session. This Skill wires the mnemon memory engine into the agent container so agents recall past context before responding and store new insights after each turn. ## Core Features & Use Cases - Container Image Integration: Adds the mnemon binary install layer to the Dockerfile and registers Claude Code memory hooks via mnemon setup in the container entrypoint. - Persistent Memory Storage: Writes memory to the per-agent-group .claude/ mount so it survives container restarts, with commands to locate and reset the host-side storage path. - Structural Test Guards: Ships vitest tests that fail if the Dockerfile install layer or entrypoint wiring is dropped during upgrades. - Use Case: After applying this Skill, have a conversation with your agent, start a new session days later, and reference an earlier topic — the agent surfaces the relevant prior context automatically without you repeating it. ## Quick Start Ask the agent to apply the add-mnemon skill to install persistent memory into the NanoClaw agent container and rebuild the image.
