Skip to main content

Unified CLI wizard for Loop Engineering — scaffold, audit, estimate, and monitor AI agent loops

Project description

Loop Wizard 🪐

The unified command-line tool for Loop Engineering. Scaffold, audit, estimate, and monitor autonomous AI agent loops in your projects.


What is a Loop?

A loop is a repeating cycle in which an AI agent takes an action, receives feedback from its environment (such as test runs, git status, lint errors), uses that feedback to decide the next move, and continues until a defined termination condition is met.

Instead of prompting an AI agent dozens of times a day, you design a loop once and let it run autonomously (e.g. overnight in CI/CD) and review its status file once a day.


Features & Commands

loop-wizard acts as a single control plane for all your loop engineering needs:

1. Scaffold a Loop

Initialize a pre-designed loop pattern into your project with a step-by-step interactive setup wizard.

loop-wizard init .

Or run non-interactively for automation:

loop-wizard init . --pattern ci-sweeper --tool claude-code --yes

2. Audit Production Readiness

Score a loop's configuration from 0 to 100 based on safety guardrails, budget limits, file scoping, and termination triggers.

loop-wizard audit . --suggest

3. Estimate Run Costs

Project token consumption and monthly dollar costs based on model selections, cadence presets, and token caps.

loop-wizard cost --pattern ci-sweeper --cadence daily

4. Monitor Loop Execution

Check the current state, recent runs, files changed, and budget usage of a running or completed loop.

loop-wizard status ci-sweeper

Add the --watch flag for a live terminal dashboard that auto-refreshes every 30 seconds:

loop-wizard status ci-sweeper --watch

5. Aggregate Health Dashboard

Generate an overview report summarizing active loops, accumulated costs, git commits made, and runs waiting for human approval.

loop-wizard dashboard .

Installation

Install the package directly from PyPI:

pip install loop-wizard

For local development or custom modifications, clone the repository and run:

pip install -e tools/loop-wizard

Supported AI Agent Tools

The wizard supports generating configurations and CI/CD pipelines for:

  • Claude Code (claude-code, claude)
  • Gemini CLI (gemini-cli)
  • Antigravity (antigravity — by Google DeepMind)
  • Cursor (cursor)
  • OpenCode (opencode)
  • Codex (codex)

License

MIT — use freely, contribute back.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

loop_wizard-0.1.1.tar.gz (27.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

loop_wizard-0.1.1-py3-none-any.whl (29.8 kB view details)

Uploaded Python 3

File details

Details for the file loop_wizard-0.1.1.tar.gz.

File metadata

  • Download URL: loop_wizard-0.1.1.tar.gz
  • Upload date:
  • Size: 27.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for loop_wizard-0.1.1.tar.gz
Algorithm Hash digest
SHA256 ebe90a199cb14a56b503e5f5465467f3cdd9e8226b3d51b7840a40eb456e2b60
MD5 fffd2d869f96c0dd427a01e81a163b9b
BLAKE2b-256 50e669080c2e6df066e0578e10e85472fce4f942d9aa7124fe7adc0ec6a4530a

See more details on using hashes here.

Provenance

The following attestation bundles were made for loop_wizard-0.1.1.tar.gz:

Publisher: publish-pypi.yml on kaiju-no-9/loop_Engg

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file loop_wizard-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: loop_wizard-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 29.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for loop_wizard-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 f698f8ad1c23d39c405a28191adf4fb0bc33ffa1aedd88d907791d718c08733b
MD5 d6b73b13ca2a9977d32957151913398e
BLAKE2b-256 07ffa891150c26ababa145f8d059e58edef9e1b4bfeec57b134cbf23ef6f4112

See more details on using hashes here.

Provenance

The following attestation bundles were made for loop_wizard-0.1.1-py3-none-any.whl:

Publisher: publish-pypi.yml on kaiju-no-9/loop_Engg

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page