SuperQodeSUPERQODE
Menu
Be a Partner
← Back to the Hub

RLM Code

rlm-code

Optional

RLM Code recursive analysis harness with bounded REPL execution, context isolation, and trajectory evidence.

Pythonrlm-codeOpen sourceNeeds setupFresh session sessions
Repository SuperagenticAI/rlm-code ↗Documentation docs.superqode.dev ↗Harness Hub guide

RLM Code executes generated Python inside its configured sandbox. Docker is the safe default; unsafe exec is never enabled by this preset.

Specification

CategoryOptional integrations
LanguagePython
How we knowSuperagenticAI/rlm-code carries pyproject.toml and publishes a Python package.
Runtimerlm-code
InterfaceTUI and CLI
Sourceoptional:rlm-code
LicenceApache-2.0
ContinuityFresh session
SupportNeeds setup
Based onrlm-code

Setup and support

RLM Code is not installed; run uv tool install "superqode[rlm-code]"

Runtime behaviour

Capabilities

single workflowStructured run events

Tools

python

Policies and ownership

  • +Sandbox: docker
  • +Approvals: deny
  • +Shell: blocked
  • +Network: blocked
  • +Checks: not required

Get started

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

Install and authenticate

  1. 1

    Install the RLM Code integration

    In the TUI, select Set up to install, verify, and continue without restarting.

    uv tool install "superqode[rlm-code]"

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 OPTIONAL INTEGRATIONS

Tau (Hugging Face)tauUHP harnessuhpDeepSeek Harnessdeepseek-harnessDeepAgentsdeepagents
Browse all 79 harnesses