--- title: "pennylane-cli, a Pennylane CLI for agents" description: "An agent-friendly CLI that exposes the Pennylane API v2 as commands with JSON output, plus an escape hatch for raw requests." url: "https://mc-stud.io/en/open-source/pennylane-cli" lang: "en" updated: "2026-10-12" --- Beta CLI accounting Pennylane agents # pennylane-cli An agent-friendly CLI that exposes the Pennylane API v2 as commands with JSON output, plus an escape hatch for raw requests. Install `git clone https://github.com/ZEDIUM-Off/pennylane-cli && cd pennylane-cli && pip install -e .` Young tools: read the repository README before installing. **2** commits / 12 months **Latest version** v0.1 **stars** 0 **forks** 0 **contributor** 1 **open issues** 0 **Last commit** 11 October 2026 Commits per month. Last 12 months, each repository on its own scale. GitHub figures taken on 12 October 2026. **Source code** [github.com/ZEDIUM-Off/pennylane-cli](https://github.com/ZEDIUM-Off/pennylane-cli) **Licence** MIT licence **Status** Beta ## What it does pennylane-cli exposes the operations of the Pennylane Company API v2 as command-line commands, with JSON output an agent reads without ambiguity. The 160 visible operations of the OpenAPI specification are covered, and a raw request command is the escape hatch for the rest. I built it for my own operations, where agents prepare invoice drafts that I approve before anything is sent. The CLI installs from a local clone of the repository. [Source code](https://github.com/ZEDIUM-Off/pennylane-cli) ## When to reach for it - An agent needs to read or prepare accounting data in Pennylane. - You want predictable commands with JSON output rather than an improvised HTTP call. ## Let’s talk about what AI could change for you A 30-minute discovery call, by video and with no commitment, to talk about your project, your constraints and the best next step. [Book a call](https://calendar.app.google/VQTPrCgNvQSNwdA7A) [contact@mc-stud.io](mailto:contact@mc-stud.io?subject=First%20call)