| name | runner |
| description | Run and manage AgentUse agents from the CLI. Use when you need to list agents, run an agent, inspect sessions, start or inspect the AgentUse server, work with schedules, or understand runtime command behavior. |
AgentUse Runner
Run .agentuse files, inspect their execution state, and operate the HTTP
server used for webhooks, approvals, channels, and schedules.
Commands
agentuse agents [--verbose|--json]
agentuse run <file>
agentuse run <file> --model <provider:model>
agentuse run <file> --timeout <seconds>
agentuse run <file> --json --no-tty -C /path/to/project
agentuse sessions [-n 20|--json]
agentuse sessions show <session-id> --full
agentuse serve [-p 8080]
agentuse serve ps
agentuse serve agents
agentuse serve schedules
agentuse skills installed
serve agents / serve schedules report live loaded data, not the cached
serve ps counts.
Serve Web UI
/agents, /schedules — what the daemon loaded./sessions — every run; filter with ?agent= / ?trigger=./sessions/<id> — run log, and the approve/reject/continue surface when a
run is suspended on an approval gate./approvals — sessions awaiting review.
Scheduled Agents
A schedule: agent only runs while agentuse serve is running for a watched
project. Before relying on one:
- Confirm the project is in
~/.agentuse/config.json under serve.projects.
- Confirm the daemon is up (
agentuse serve ps).
- Use a process manager for long-running schedules.
YAML schedule: is for recurring jobs; schedule one-off runs outside YAML.
References
