SuperQodeSUPERQODE
Menu
GitHub
← Back to the Hub

rlm-monty

rlm-monty

Preset

Recursive analysis harness on Pydantic Monty: persistent Python, repository reads, and semantic subcalls only.

rlmOpen sourceReadyContext replay sessions
RepositoryHarness Hub guide

Monty Python: no filesystem, subprocess, network, or third-party imports. Writes, shell and rlm.run refuse. Needs the 'monty' extra.

Specification

CategoryModel and task presets
Runtimerlm
InterfaceTUI and CLI
Sourcebuilt-in-template
LicenceApache-2.0
ContinuityContext replay
SupportReady
Based onrlm-monty

Runtime behaviour

Capabilities

single workflowRecursive child agentsStructured run events

Tools

python

Policies and ownership

  • +Sandbox: monty
  • +Approvals: none
  • +Shell: blocked
  • +Network: blocked
  • +Checks: not required

Get started

Inside SuperQode
$ :harness switch rlm-monty$ :harness show rlm-monty$ :harness status
From your shell
$ superqode harness run rlm-monty "Describe your task"$ superqode harness show rlm-monty

Evaluate and optimize

Measure
$ superqode harness test --spec harness.yaml$ superqode harness eval --spec harness.yaml --tasks eval-tasks.yaml$ superqode harness bench --manifest harnessbench.yaml
Improve
$ 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

ALSO IN MODEL AND TASK PRESETS

benchmark-codingbuiltinrlm-dockerrlmprime-agent-pythonprime-agentgemma4-codingbuiltingemma4-no-toolbuiltinds4-codingbuiltin
Browse all 104 harnesses