agent-team-os

De la autor

Run a team of AI agents (or one agent in several role sessions) as one governed unit — layered long-term memory, hub-coordinated governance with evidence anchors and human approval gates, an identity-based agent mailbox with receipts, and an event-driven doorbell that wakes seats on new mail without polling. Use when setting up or operating a multi-agent team, when agents must share durable memory and verifiable hand-offs, or when a single agent should work in the same pattern across multiple sessions. Do not use for adversarial or multi-tenant environments, or for any flow where a single message by itself authorizes payment, deployment, or credential release — on the mailbox's CLI path the sender is self-declared.