HKUDS /
CLI-Anything
Generates command-line wrappers so AI agents can drive desktop and web software
- 56.3k stars
- 4.9k stars since 3 Oct
- Python
- Updated 31 days ago
- Some experience
- Coding agents & dev tools
Most software is built for people clicking through windows. AI agents work best with text commands and structured output. CLI-Anything fills that gap by creating a command-line harness around an application, so an agent can call it the way a person calls git or ls.
The generated CLIs are Python tools built on Click. They give both human-readable and JSON output, and each comes with a SKILL.md file that tells an agent how to use it. A HARNESS.md guide describes the method for building a new harness for a given piece of software.
CLI-Hub is the companion registry. You install it with pip, then use it to browse, install, update and remove CLIs. The README lists many community harnesses, including Blender, FreeCAD, Krita, Obsidian, QGIS, n8n and Godot. Contributors add new ones by pull request.
What it does
Harness generation
Follows a HARNESS.md methodology to turn an application into a CLI an agent can call, with unit and end-to-end tests.
CLI-Hub package manager
The cli-anything-hub pip package lets you search, install, update and uninstall CLIs. It supports pip, npm, brew and bundled tools as install sources.
Agent-readable skills
Each CLI has a SKILL.md file. Skills can be installed from one top-level skills directory with npx skills add.
Dual output
Commands print JSON for agents and readable text for people.
Wide community registry
The news log lists harnesses for creative tools, CAD, GIS, note-taking, workflow automation and more.
What you could build
- Let a coding agent edit a Blender scene or FreeCAD model through shell commands.
- Install a community CLI for Obsidian, Zotero or Calibre and have an agent manage your notes or library.
- Generate a new CLI harness for an application you use, then share it with a pull request.
- Automate n8n or Dify workflows from an agent without touching the GUI.
- Browse CLI-Hub to find which tools already have agent-ready commands.
Get started
Install the CLI-Hub package with pip, then install the CLI you want by name. The README also points to a Quick Start section and to npx skills for installing the matching agent skill.
pip install cli-anything-hubcli-hub install <name>Commands are copied from the project's README. Read it on GitHub for the full setup.
More in Coding agents & dev tools
rea
MCP server that lets AI agents reverse engineer apps, binaries and websites locally