Ploinky

Secure AI Agent Deployment & Development Platform

Deploy AI agents in isolated Linux containers. Perfect for running untrusted code safely.

Quick Start Demos

ploinky@workspace
🔒

Isolated Containers

Each agent runs in its own container with restricted access to ensure complete isolation.

📦

Repository System

Organize agents in repositories. Enable/disable repos as needed.

🌐

Web Interfaces

Transform any CLI tool into a modern web interface with WebConsole, WebChat, and Dashboard.

🔧

Easy Configuration

Simple manifest.json defines container image, dependencies, and commands.

🚀

Development Workflow

Seamless development with hot-reload support and integrated debugging tools.

🔄

Production Ready

Deploy the same containerized agents to production with built-in health checks.

Introduction to Agents

In Ploinky, an "agent" is a tool that you can use and modify. It's an abstract concept and doesn't necessarily refer to a Large Language Model (LLM). Agents can be anything from a simple script to a complex application.

Agents are organized in repositories, which can contain multiple agents. You can easily add new repositories, and modify existing agents to fit your needs.

Using Agents

You can interact with agents in two main ways:

  1. Individually: You can run an agent's command-line interface directly using the cli command. For example: cli my-agent --input "some data". Agents can be designed to accept various input formats, such as JSON, natural language, or any other convention.
  2. Integrated with Ploinky: By enabling an agent, it becomes part of the Ploinky workspace. The Ploinky server will expose the agent on a local port, which allows you to build applications that interact with your agents through a simple API on localhost. When you open the web interface, you will need to provide a token, which can be found in /.ploinky/.secrets.

Getting Started

Prerequisites

Ploinky uses containers to run agents in isolated environments. Therefore, you need to have a container runtime installed on your system. Ploinky supports both Docker and Podman.

Docker

On Debian-based Linux distributions (like Ubuntu), you can install Docker with:

sudo apt-get update && sudo apt-get install docker-ce docker-ce-cli containerd.io

For other operating systems or more detailed instructions, please refer to the official Docker documentation.

Podman

On Debian-based Linux distributions (like Ubuntu), you can install Podman with:

sudo apt-get update && sudo apt-get install podman

For other operating systems or more detailed instructions, please refer to the official Podman documentation.

Installation

$ git clone https://github.com/ploinkyRepos/ploinky.git
$ cd ploinky
$ npm install
View CLI Reference Learn Architecture

Usage

From within the project directory

When you are in the project directory, you can use the ploinky command directly. Here are the first steps to get you started:

  1. Run ploinky to initialize your workspace
  2. Enable the demo repository: enable repo demo
  3. Start demo agent: start demo

Globally from any directory

To use ploinky from anywhere, you need to add its location to your shell's configuration file (e.g., .bashrc, .zshrc).

Add the following line to your ~/.bashrc or ~/.zshrc file, replacing ~/path/to/ploinky with the actual path to your ploinky directory:

export PATH="$PATH:~/path/to/ploinky/bin"

After adding the line, restart your shell or run source ~/.bashrc (or source ~/.zshrc). You can then use p-cli or ploinky from any directory. For example:

ploinky list agents