CLI tools

A CLI is a command-line utility that helps you work with agents: it installs and runs skills, gathers context and automates routine work. This section collects tools with real commands from their docs, a clear purpose and a risk level.

Match with Foxx AI

Describe the task or paste package.json, and Foxx AI will pick matching skills, MCP servers and CLI tools.

Found: 30

A self-hosted gateway for multiple LLM keys and providers: rotation, failover, request logs and usage accounting

7KRepository stars

A CLI, skill and MCP server for driving Chrome with short Puppeteer scripts, with tabs that keep state between calls

6.6KRepository stars

An Open WebUI proxy that exposes any MCP server as an HTTP API with an OpenAPI schema

4.4KRepository stars

A real browser inside the terminal with a CLI for the agent: a coding agent opens sites and interacts with them in the same tab

3.5KRepository stars

A CLI agent for authorized pentesting: from a natural-language brief it runs recon, finds and verifies vulnerabilities and prepares a report

3.5KRepository stars

A CLI that loops Claude Code, Codex, OpenCode and other agents over a task list or PRD until everything is done

3KRepository stars

A CLI that turns any MCP server, OpenAPI spec or GraphQL endpoint into commands at runtime, with no codegen

2.4KRepository stars

A portable .agent folder with memory, skills and protocols that plugs into many coding agents and keeps its knowledge when you switch tools

2.3KRepository stars

A terminal coding agent tuned for the deepseek-v4 model: deep thinking, reasoning effort control, Agent Skills and MCP

2.3KRepository stars

A CLI to run several coding agents: one config, a session console, local memory and a set of engineering skills

1.6KRepository stars

Lets an agent call MCP and UTCP tools by running code: discover tools, get typed code and run chains instead of dozens of separate calls

1.6KRepository stars

A local dashboard for many Claude Code sessions: each job gets its own context and todo, agents spawn child agents and message each other

1.4KRepository stars

A multi-agent harness that verifies results by artifacts: stop hooks, an independent judge and an event log for Claude Code, Codex, Cursor and more

1.3KRepository stars

A universal MCP CLI client from Apify: persistent sessions, OAuth, JSON output for scripts and shell access to any MCP server for agents

936Repository stars

Postgres Professional utility for PostgreSQL backup and recovery with incremental backups and PITR

799Repository stars
Russian stack

Ready-made methods for Telegram, Bitrix24, VK, CDEK, Yandex Disk, databases and other APIs in 1C, OneScript and the oint CLI

676Repository stars

A CLI that lets agents in different terminals message, watch and spawn each other

525Repository stars
Official

Official CLI and simple SDK for managing Timeweb Cloud resources from the terminal

69Repository stars
Russian stack

A Python CLI for Kaiten with an agent command registry, shell completion and three bonus skills

12Repository stars
Russian stack

A Yandex Tracker CLI built for LLM agents: issues, comments, worklogs, checklists and bulk operations, with an agent skill

11Repository stars
Russian stack

A Swift Kaiten CLI that prints compact JSON for jq, ships Claude and Cursor plugins, and keeps a reference file for agents

8Repository stars

selvpc (Selectel VPC)

python-selvpcclient

Official

Python client and selvpc CLI for the Selectel cloud platform API

8Repository stars
Russian stack

Command-line client and MCP server for the Kaiten tracker: cards, comments, checklists and files from the terminal or an agent

5Repository stars
Russian stack

A Yandex 360 toolkit: Tracker, Wiki and Forms via a CLI, an MCP server, a Python SDK and a Claude Code plugin

3Repository stars

Frequently asked questions

What is a CLI tool for an agent?

A command-line utility that helps an agent or a developer: runs tasks, processes files, manages the project. Installed via npm, pip, brew and similar.

How do I install a CLI tool?

The entry has a real install command from the README, usually one line through a package manager.