Skip to main content

A batteries-included framework for DIY AI agents

Project description

arkaine

Empower your summoned AI agents. arkaine is a batteries-included framework built for DIY builders, individuals, and small scale solutions.

License: MIT Python 3.8+

Join our Discord!

Overview

arkaine is built to allow individuals with a little python knowledge to easily create deployable AI agents enhanced with tools. While other frameworks are focused on scalable web-scale solutions, arkaine is focused on the smaller scale projects - the prototype, the small cron job, the weekend project. arkaine attempts to be batteries included - multiple features and tools built in to allow you to go from idea to execution rapidly.

📖 Documentation 👩‍🏫

Documentation can be found at arkaine.dev.

WARNING

This is a very early work in progress. Expect breaking changes, bugs, and rapidly expanding features.

Features

  • 🔧 Easy tool creation and programmatic tool prompting for models
  • 🤖 Agents can be "composed" by simply combining these tools and agents together
  • 🔀 Thread safe async routing built in
  • 🔄 Multiple backend implementations for different LLM interfaces
    • OpenAI (GPT-3.5, GPT-4)
    • Anthropic Claude
    • Groq
    • Ollama (local models)
    • More coming soon...
  • 🧰 Built-in common tools (web search, file operations, etc.)

Key Concepts

  • 🔧 Tools - Tools are functions (with some extra niceties) that can be called and do something. That's it!
  • 🤖 Agents - Agents are tools that use LLMS. Different kinds of agents can call other tools, which might be agents themselves!
    • IterativeAgents - IterativeAgents are multi-shot agents that can repeatedly call an LLM to try and perform its task, where the agent can identify when it is complete with its task.
    • 🧰 BackendAgents - BackendAgents are agents that utilize a Backend to perform its task.
    • 💬 Chats - Chats are agents that interact with a user over a prolonged interaction in some way, and can be pair with tools, backends, and other agents.
  • Backends - Backends are systems that empower an LLM to utilize tools and detect when it is finished with its task. You probably won't need to worry about them!
  • 📦 Connectors - Connectors are systems that can trigger your agents in a configurable manner. Want a web server for your agents? Or want your agent firing off every hour? arkaine has you covered.
  • Context - Context provides thread-safe state across tools. No matter how complicated your workflow gets by plugging agents into agents, contexts will keep track of everything.

Installation

To install arkaine, ensure you have Python 3.8 or higher installed. Then, you can install the package using pip:

bash
pip install arkaine

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

arkaine-0.0.23.tar.gz (206.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

arkaine-0.0.23-py3-none-any.whl (260.0 kB view details)

Uploaded Python 3

File details

Details for the file arkaine-0.0.23.tar.gz.

File metadata

  • Download URL: arkaine-0.0.23.tar.gz
  • Upload date:
  • Size: 206.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.1

File hashes

Hashes for arkaine-0.0.23.tar.gz
Algorithm Hash digest
SHA256 45824744b79f33a7f46ec84df6e349bde855203095ea0bfbf4edc4609c027af1
MD5 a49932e0de4ed95ce9b7164985867c5f
BLAKE2b-256 34ab67c8ed5a54bc06fb6bf0bc1060be4ce384890acae2603864e4d243123ff9

See more details on using hashes here.

File details

Details for the file arkaine-0.0.23-py3-none-any.whl.

File metadata

  • Download URL: arkaine-0.0.23-py3-none-any.whl
  • Upload date:
  • Size: 260.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.1

File hashes

Hashes for arkaine-0.0.23-py3-none-any.whl
Algorithm Hash digest
SHA256 803e9e9d327ca179996ac5c4fabcd9640ec3de05b9a3600c05772ee00ca772cf
MD5 ec70bbcd1b02aac725068b22116f8ef7
BLAKE2b-256 74a1fd298e14d9b7ef0ca7b5dc68bb4a1b552f019f6c8852cbc983aded8774d9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page