Task queue, live
TaskRelay
Assign the work. Agents deliver it.
TaskRelay is a prioritised work queue designed for AI agents. Each ticket carries its priority, project and working directory. Agents claim work in order, execute it in your codebase and close each ticket with a written account of what was done, pausing at usage limits and resuming afterwards.
Why it matters.
Agents are most valuable when they work through a backlog rather than waiting for prompts. TaskRelay provides the queue, the context and the audit trail that make unattended work reviewable.
Prioritised queue
Critical, high, normal and low priorities across projects.
Autonomous pickup
Agents claim the next ticket without manual hand-off.
Usage-aware
Work pauses at provider limits and resumes when capacity returns.
Completion reports
Every ticket closes with notes describing the change.
Where teams use TaskRelay.
Overnight backlog
Queue maintenance work in the evening; review results in the morning.
Multi-project teams
One board for every repository an agent works on.
Traceability
A clear record linking each change to its request.
How TaskRelay connects.
TaskRelay relies on the shared foundations of the layer and works alongside the services below. See the full architecture.
Takes part in: an agent completes a ticket.
Let's build it together.
Whether you want to run your own agents on the layer, discuss one of our products, or need a partner for an AI, Java or enterprise project, we respond within one working day.