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.
BRAIN_API_URLCloud mode API URL (e.g., https://brain.api.vauban.tech). When unset, uses local SQLite.
BRAIN_API_KEYsecretAPI key for cloud mode authentication (sent as X-API-Key header)
BRAIN_DB_PATHOverride path for the local SQLite database file
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent