Fleet 1.13:Teams are now shipping 5x more PRs with autonomous pipelines.See what's new →
FleetFleet
Glossary

Agent Fabric

Agent fabric is a shared communication and coordination layer for a fleet of AI agents, providing event publishing, subscriptions, task claims, inbox messaging, and a persistent audit trail across all agents in the system.

The term 'fabric' suggests the woven interconnect between agents — a substrate that carries messages, events, and state without any single agent needing to coordinate with others directly. Unlike a simple event bus (which handles publish/subscribe), a fabric typically includes additional coordination primitives: inbox messages (direct agent-to-agent communication), work-claiming (exclusive reservation of a task by one agent), and persistent storage of all events for audit and replay.

A fabric makes the coordination topology of a multi-agent system observable: you can query which events have been published, which agents have claimed which tasks, and which messages are waiting in which agent inboxes. This observability is critical for debugging coordination failures and for auditing agent decisions.

Fabrics can be centralized (all agents share one fabric instance) or federated (separate fabric instances per team or project, with cross-fabric routing for events that span organizational boundaries). The tradeoff is consistency versus isolation: a centralized fabric provides a single source of truth but is a single point of failure.

How this relates to Fleet

Fleet's fabric is implemented in SQLite with an optional Unix socket server. Agents publish events using a simple fleet fabric publish CLI command. The fabric stores all events persistently, matches them to subscriptions, delivers them to agent inboxes, and exposes them for audit via the fleet log command. The fabric is the backbone of Fleet's reactive coordination model.

Frequently asked questions

Does every multi-agent system need a fabric?

A fabric is most valuable when agents need to coordinate asynchronously across time and when auditability matters. For a simple two-agent sequential workflow where agent B always follows agent A, a direct handoff may suffice. Fabric becomes necessary when: more than two agents coordinate, agents may not be running simultaneously, or you need a persistent record of all inter-agent communication.

What is the difference between an agent fabric and an agent framework like LangGraph?

LangGraph and similar frameworks provide programming abstractions for building multi-agent applications — graphs, nodes, edges, state management. A fabric is operational infrastructure for running already-built agents — event storage, routing, claiming, and audit. They operate at different levels of the stack and are not mutually exclusive.

Run your first agent fleet

One binary. Five minutes. See every agent, coordinate every handoff, and keep a full audit trail of what your fleet did.