← Back to the Hub
Preset
rlm-docker
rlm-docker
Recursive coding harness with the Python kernel in a Docker container. Writes are allowed, networking is off.
rlmOpen sourceReadyContext replay sessions
Docker Python: the kernel runs inside a container with networking disabled. Requires a running Docker daemon.
Specification
| Category | Model and task presets |
|---|---|
| Runtime | rlm |
| Interface | TUI and CLI |
| Source | built-in-template |
| Licence | Apache-2.0 |
| Continuity | Context replay |
| Support | Ready |
| Based on | rlm-docker |
Runtime behaviour
Capabilities
single workflowRecursive child agentsStructured run events
Tools
pythonPolicies and ownership
- +Sandbox: docker
- +Approvals: none
- +Shell: allowed
- +Network: blocked
- +Checks: not required
Get started
Inside SuperQode
$ :harness switch rlm-docker$ :harness show rlm-docker$ :harness statusFrom your shell
$ superqode harness run rlm-docker "Describe your task"$ superqode harness show rlm-dockerEvaluate and optimize
Measure
$ superqode harness test --spec harness.yaml$ superqode harness eval --spec harness.yaml --tasks eval-tasks.yaml$ superqode harness bench --manifest harnessbench.yamlImprove
$ superqode harness optimize-omni --spec harness.yaml --tasks eval-tasks.yaml$ superqode harness optimize --spec harness.yaml --tasks eval-tasks.yaml$ superqode harness promote stage