useclis.
Saved CLIs

Submit your CLI

Free to list

Put your command-line tool in the hands of agents.

Link to the public repository where your CLI lives.

A CLI that agents can use.

Include a working command, public documentation, and a clear task an agent can accomplish with your tool.

2. The essentials

A concrete use case helps people find the right tool.

Directory listing

A CLI profile with your repository, documentation, and command. Submissions are reviewed before appearing in the directory.

Free

Submissions are public GitHub issues.

Sign in to GitHub, then review and create your issue.

EVA

evaAgents & modelsBy ARCANGEL0 ↗

GitHub repository: Within freshness window. Last successful check . Freshness policy ↗

EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing structured attack guidance, contextual analysis, and multi-backend AI integration.

For your agent

Invoke eva from a shell for the documented use case: EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing structured attack guidance, contextual analysis, and multi-backend AI integration.

Agent capability details have not yet been reviewed. Check the official documentation ↗

Example command

eva --config

Run after following the project’s setup instructions. Local files, credentials, or a connected service may be required.

What it does

  • Command-line interface

GitHub activity: Within freshness window. Last successful check . Freshness policy ↗

Repository activity

Commits per week · GitHub snapshot

49 commits across 5 weeks
01121Sep 27, 2026Oct 27, 2026

Tap, hover, or use the arrow keys to inspect weekly commits. Weekly totals can extend beyond the selected dates; the latest week may be incomplete. All time includes up to 52 recorded weeks. Hourly data is unavailable.

Commands and capabilities are described from the project documentation. Repository statistics cover ARCANGEL0/EVA, which may contain more than the CLI. Listing a tool does not mean every command has been tested with every agent.