This gives Claude persistent memory backed by a knowledge graph with full-text search and cryptographic proofs via Starknet. You can store and query structured knowledge locally or in the cloud, with each memory operation optionally generating a verifiable proof on-chain. Reach for this when you need AI agents to maintain long-term context across conversations with guarantees about what was stored and when. The Starknet integration means you can verify memory integrity without trusting the storage layer, which matters for multi-agent systems or scenarios where audit trails are critical. Works over stdio and supports both self-hosted and cloud deployments.
claude mcp add --transport stdio seritalien-brain-protocol -- npx -y @brain-protocol/mcp