MIT Licensed • Python 3.8+

An AI agents framework for makers, prototypes, and weekend projects

arkaine is the batteries included framework designed to get you from idea to finished project in a weekend

Warning: arkaine is an early work in progress. Expect breaking changes and rapidly expanding features.

Features

arkaine is focused on smaller scale projects - the prototype, the cron job, the weekend project. To speed you up, we've included a whole lotta batteries:

Composable Agents
Build complex behavior with simple building blocks. Plug agents together as you like to create increasingly capable AI agent workflows.
Built-In Tools
Want to send an e-mail, scrape a website, look for a local coffee shop, or perform a web search? arkaine has you covered with ready-to-go tools out of the box.
Plug and Play Compatibility
Support for every major model provider - OpenAI™, Google™, Anthropic™, DeepSeek™, Groq™ - or local models with Ollama, and more coming soon.
Researchers
arkaine has built in deep AI researchers to make building the most informed AI agents a breeze.
Connectors
Want to have an agent that reacts to your e-mails? Trigger whenever your favorite website changes? Fire off every fourth Tuesday at 1pm? How about your custom AI being integrated into your command line? Done and done.
Chat Ready
Want to chat with your summoned AI minions, and inject some personality into your project? arkaine's got you.

Key Concepts

Understanding the core concepts of arkaine will help you get started working with its building blocks.

Tools
Functions with extra niceties that can be called to perform actions

Tools are the fundamental building blocks in arkaine. They're simply functions that do something when called, with added metadata to help LLMs understand how to use them.

Agents
Tools that use LLMs and can call other tools

Agents are special tools that use LLMs. Different types of agents can call other tools, which might be agents themselves, creating powerful compositions.

IterativeAgents: Multi-shot agents that can repeatedly call an LLM
BackendAgents: Agents that utilize tools to perform tasks
Chats: Tool-equipped chatbots that interact with users over prolonged interactions
Backends
Systems that empower LLMs to utilize tools

Backends are systems that connect to LLM providers and enable agents to use tools. Backends are integrated right into model providers where possible, and use research-backed local prompting and parsing solutions for every model.

Connectors
Systems that trigger your agents in configurable ways

Want an API server for your agents? Or for your agent to fire off every hour? Or to react to an incoming e-mail? Connectors are out-of-the-box solutions for hosting and integrating your agents to your needs.

Context
Thread-safe state across tools

No matter how complicated your workflow gets when plugging agents into agents into agents... contexts will keep track of everything. Context provides thread-safe state that persists across tool calls, ensuring your agents have the information they need.

Toolbox
Pre-built tools to make your life easier and your project cooler

The toolbox is a collection of pre-built tools for assumed-common tasks:

  • Web Search: Search the web for information
  • Website + PDF Scraping: consume docs and the web to educate your agents
  • Communication send + receive e-mails and SMS text messages
  • Local Search weather, local business search, and more...

Getting Started

Start building with arkaine in minutes

Diving Right In

Here's a simple example of creating an agent that can search the web:

Quick Start Guide

  1. 1

    Install arkaine

  2. 2

    Set up your API keys

    Configure your LLM provider API keys (OpenAI, Anthropic, etc.) or any other tools you need

  3. 3

    Create tools

    Define a set of tools for your agent, or pull some out of the toolbox

  4. 4

    Build your agent

    Feed your tools to your agent and write its prompt

  5. 5

    Run debug rinse repeat

    Test your agent; happy building!

Guided Walkthrough

Want a guided walkthrough of arkaine's features? Check out our more detailed examples; each walks you through building of a mini project to learn arkaine.


Examples

Documentation

Want to learn more about arkaine? Check out the full documentation:


Documentation