Claude Mem
Claude Code plugin that captures every action in a session, compresses it with AI, and re-injects relevant context into future sessions.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Claude Mem, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
An automatic memory plugin that records everything Claude does during coding sessions, compresses it using the agent-sdk, and injects the relevant context back into later sessions. It is built from skills and hooks — the hooks capture session activity on events and the compression/retrieval runs behind the scenes. This gives Claude Code persistent cross-session memory.
Key features and capabilities
- Automatic capture of all session activity via hooks
- AI compression of session history using agent-sdk
- Context re-injection into future sessions
Use cases
- Giving Claude Code persistent memory across coding sessions
- Recalling prior decisions and context automatically