What you can do with Cadence

3 use cases

• Run a continuing brain that learns from live rewards

  Compose a System 1 brain and feed it observations and measured rewards in one ongoing stream.

  • Cadence
  • Research
  • Intermediate
  View prompt

  Using the Python package cadence-net (repo muellerberndt/cadence), write a loop that drives Brain.compose(inputs=4, actions=2, arousal=True) through live() calls on the toy environment at <environment file>. Expected output: a printed log of actions, rewards and last_settlement values for 200 steps. Verify that each call after the first passes the reward of the previous action.

  Share Save

• Preview a brain's responses without altering live memory

  Use imagination to inspect possible responses while the live trace and pending feedback stay unchanged.

  • Cadence
  • Research
  • Intermediate
  View prompt

  Using the Python package cadence-net (repo muellerberndt/cadence), compose a brain with inputs=4 and actions=2, run live() for 50 steps, then call imagine() on <observation sequence> and print each phase's qualified flag. Expected output: the qualified flags and the live action taken afterward. Verify that the live action sequence matches a control run that skips imagine().

  Share Save

• Test whether System 2 observers help a task

  Build a System 1 brain and a recursive brain with observers, then compare them on the same task.

  • Cadence
  • Research
  • Advanced
  View prompt

  Using the Python package cadence-net (repo muellerberndt/cadence), run Brain.compose with and without observers=(8,) on the environment at <task file> using live() for 500 steps each. Expected output: two reward-by-step series and a summary of their averages. Verify that both brains receive identical observations and rewards at each step.

  Share Save

How to use Cadence

1. Check you have what it needs: Python 3.11 or newer; NumPy installed through pip; A toy environment or task that can supply an observation and a measured reward after each action.
2. Open muellerberndt/cadence on GitHub and read the README and license.
3. python -m pip install cadence-net==0.84.3
4. Create a Python file that runs brain = Brain.compose(inputs=4, actions=2, arousal=True) from cadence.
5. Call action = brain.live(observation) with one observation row, execute the action in your environment, and measure the reward.
6. Call action = brain.live(next_observation, reward=reward) for each following step, passing the reward of the preceding action.

These steps come from our top use case, Run a continuing brain that learns from live rewards, which also has a copy-paste agent prompt.

Cadence alternatives · Best AI repos for Research

About this repo

• Who it is forResearchers and Python developers who want a continuing learning agent to test acquisition, retention and recovery over a long run of experience.
• Why it is hot
• LanguagePython
• Sourcegithub.com/muellerberndt/cadence · Back to Hot repos

Requirements

• Python 3.11 or newer
• NumPy installed through pip
• A toy environment or task that can supply an observation and a measured reward after each action

Related repos

• #5 this week Scientific Agent Skills A library of 177 Agent Skills that give AI agents documented, validated guidance for scientific packages, databases, and research workflows.
• Trended earlier Speaker Mem R1 SpeakerMem-R1 is a Python research repo with a speaker-centered memory package, benchmark runners, writer-training recipes, and evaluation outputs for multi-party dialogue.
• Trended earlier DSH Council A DSH Council plugin that asks several AI models to answer a question independently, review each other's answers anonymously, and produce one inspectable final recommendation inside DeepSeek Harness.