Home

Awesome

AIOS: AI Agent Operating System

<a href='https://arxiv.org/abs/2403.16971'><img src='https://img.shields.io/badge/Paper-PDF-red'></a> <a href='https://arxiv.org/abs/2312.03815'><img src='https://img.shields.io/badge/Paper-PDF-blue'></a> <a href='https://docs.aios.foundation/'><img src='https://img.shields.io/badge/Documentation-AIOS-green'></a> Code License <a href='https://discord.gg/B2HFxEgTJX'><img src='https://img.shields.io/badge/Community-Discord-8A2BE2'></a> Gurubase

<a href="https://trendshift.io/repositories/8908" target="_blank"><img src="https://trendshift.io/api/badge/repositories/8908" alt="agiresearch%2FAIOS | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>

AIOS is the AI Agent Operating System, which embeds large language model (LLM) into the operating system and facilitates the development and deployment of LLM-based AI Agents. AIOS is designed to address problems (e.g., scheduling, context switch, memory management, storage management, tool management, Agent SDK management, etc.) during the development and deployment of LLM-based agents, towards a better AIOS-Agent ecosystem for agent developers and agent users. AIOS includes the AIOS Kernel (this AIOS repository) and the AIOS SDK (the Cerebrum repository). AIOS supports both Web UI and Terminal UI.

🏠 Architecture of AIOS

Overview

<p align="center"> <img src="docs/assets/aios-figs/architecture.jpg"> </p>

The AIOS system is comprised of two key components: the AIOS kernel and the AIOS SDK. The AIOS kernel acts as an abstraction layer over the operating system kernel, managing various resources that agents require, such as LLM, memory, storage and tool. The AIOS SDK is designed for agent users and developers, enabling them to build and run agent applications by interacting with the AIOS kernel. AIOS kernel is the current repository and AIOS SDK can be found at here

Modules and Connections

Below shows how agents utilize AIOS SDK to interact with AIOS kernel and how AIOS kernel receives agent queries and leverage the chain of syscalls that are scheduled and dispatched to run in different modules.

<p align="center"> <img src="docs/assets/aios-figs/details.png"> </p>

📰 News

Different deployment modes of AIOS

Here are some key notations that are required to know before introducing the different modes of AIOS.

The following parts introduce different modes of deploying AIOS. Currently, AIOS already supports Mode 1 and Mode 2, other modes with new features are still ongoing.

Mode 1 (Local Kernel Mode)

<p align="center"> <img src="docs/assets/aios-figs/stage1.png" width=300> </p>

Mode 2 (Remote Kernel Mode)

<p align="center"> <img src="docs/assets/aios-figs/stage2.png" width=300> </p>

Mode 2.5 (Remote Kernel Dev Mode)

<p align="center"> <img src="docs/assets/aios-figs/stage2.5.png" width=300> </p>

Mode 3 (Personal Remote Kernel Mode)

<p align="center"> <img src="docs/assets/aios-figs/stage3.png" width=800> </p>

Mode 4 (Personal Remote Virtual Kernel Mode)

<p align="center"> <img src="docs/assets/aios-figs/stage4.png" width=800> </p>

✈️ Getting Started

Please see our ongoing documentation for more information.

Installation

Requirements

Python

Environment Variables Configuration

AIOS supports several API integrations that require configuration. You can use the following commands:

When no environment variables are set, the following API keys will be shown:

To obtain these API keys:

  1. OpenAI API: Visit https://platform.openai.com/api-keys
  2. Google Gemini API: Visit https://makersuite.google.com/app/apikey
  3. Groq API: Visit https://console.groq.com/keys
  4. HuggingFace Token: Visit https://huggingface.co/settings/tokens

Installation from source

Git clone AIOS kernel

git clone https://github.com/agiresearch/AIOS.git
cd AIOS && git checkout v0.2.0.beta

Create venv environment (recommended)

python3.x -m venv venv # Only support for Python 3.10 and 3.11
source venv/bin/activate

or create conda environment

conda create -n venv python=3.x  # Only support for Python 3.10 and 3.11
conda activate venv

If you have GPU environments, you can install the dependencies using

pip install -r requirements-cuda.txt

or else you can install the dependencies using

pip install -r requirements.txt

Note: The machine where the AIOS kernel (AIOS) is installed must also have the AIOS SDK (Cerebrum) installed. Installing AIOS kernel will install the AIOS SDK automatically by default. If you are using the Local Kernel mode, i.e., you are running AIOS and agents on the same machine, then simply install both AIOS and Cerebrum on that machine. If you are using Remote Kernel mode, i.e., running AIOS on Machine 1 and running agents on Machine 2 and the agents remotely interact with the kernel, then you need to install both AIOS kernel and AIOS SDK on Machine 1, and install the AIOS SDK alone on Machine 2. Please follow the guidelines at Cerebrum regarding how to install the SDK.

Quickstart

<!-- > [!TIP] -->

For the config of LLM endpoints, multiple API keys may be required to set up. Here we provide the .env.example to for easier configuration of these API keys, you can just copy .env.example as .env and set up the required keys based on your needs.

<!-- Note: Please use `launch.py` for the WebUI, or `agent_repl.py` for the TUI. -->

Configurations

Use with OpenAI API

You need to get your OpenAI API key from https://platform.openai.com/api-keys. Then set up your OpenAI API key as an environment variable

export OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>
Use with Anthropic API

You need to get your Anthropic API key from https://console.anthropic.com/settings/keys. Then set up your Anthropic API key as an environment variable

export ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>
Use with Gemini API

You need to get your Gemini API key from https://ai.google.dev/gemini-api

export GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>

If you want to use open-sourced models provided by huggingface, here we provide three options:

Use with ollama

You need to download ollama from from https://ollama.com/.

Then you need to start the ollama server either from ollama app

or using the following command in the terminal

ollama serve

To use models provided by ollama, you need to pull the available models from https://ollama.com/library

ollama pull llama3:8b # use llama3:8b for example

ollama can support both CPU-only and GPU environment, details of how to use ollama can be found at here

Use with native huggingface llm models

Some of the huggingface models require authentification, if you want to use all of the models you need to set up your authentification token in https://huggingface.co/settings/tokens and set up it as an environment variable using the following command

By default, huggingface will download the models in the ~/.cache directory. If you want to designate the download directory, you can set up it using the following command

export HF_HOME=<YOUR_HF_HOME>
Use with vLLM

If you want to speed up the inference of huggingface models, you can use vLLM as the backend.

[!NOTE]

It is important to note that vLLM currently only supports linux and GPU-enabled environment. So if you do not have the environment, you need to choose other options.

Considering that vLLM itself does not support passing designated GPU ids, you need to either setup the environment variable,

export CUDA_VISIBLE_DEVICES="0" # replace with your designated gpu ids

or you can pass the CUDA_VISIBLE_DEVICES as the prefix

Launch AIOS

After you setup your keys or environment parameters, then you can follow the instructions below to start.

First, you need to start the AIOS kernel by running the following commands

bash runtime/launch_kernel.sh

Then you can start the client provided by the AIOS SDK either in the terminal or in the WebUI. The instructions can be found at here

Supported Agent Frameworks

Supported LLM Cores

Provider 🏢Model Name 🤖Open Source 🔓Model String ⌨️Backend ⚙️Required API Key
AnthropicClaude 3.5 Sonnet❌claude-3-5-sonnet-20241022anthropicANTHROPIC_API_KEY
AnthropicClaude 3.5 Haiku❌claude-3-5-haiku-20241022anthropicANTHROPIC_API_KEY
AnthropicClaude 3 Opus❌claude-3-opus-20240229anthropicANTHROPIC_API_KEY
AnthropicClaude 3 Sonnet❌claude-3-sonnet-20240229anthropicANTHROPIC_API_KEY
AnthropicClaude 3 Haiku❌claude-3-haiku-20240307anthropicANTHROPIC_API_KEY
OpenAIGPT-4❌gpt-4openaiOPENAI_API_KEY
OpenAIGPT-4 Turbo❌gpt-4-turboopenaiOPENAI_API_KEY
OpenAIGPT-4o❌gpt-4oopenaiOPENAI_API_KEY
OpenAIGPT-4o mini❌gpt-4o-miniopenaiOPENAI_API_KEY
OpenAIGPT-3.5 Turbo❌gpt-3.5-turboopenaiOPENAI_API_KEY
GoogleGemini 1.5 Flash❌gemini-1.5-flashgoogleGEMINI_API_KEY
GoogleGemini 1.5 Flash-8B❌gemini-1.5-flash-8bgoogleGEMINI_API_KEY
GoogleGemini 1.5 Pro❌gemini-1.5-progoogleGEMINI_API_KEY
GoogleGemini 1.0 Pro❌gemini-1.0-progoogleGEMINI_API_KEY
GroqLlama 3.2 90B Vision✅llama-3.2-90b-vision-previewgroqGROQ_API_KEY
GroqLlama 3.2 11B Vision✅llama-3.2-11b-vision-previewgroqGROQ_API_KEY
GroqLlama 3.1 70B✅llama-3.1-70b-versatilegroqGROQ_API_KEY
GroqLlama Guard 3 8B✅llama-guard-3-8bgroqGROQ_API_KEY
GroqLlama 3 70B✅llama3-70b-8192groqGROQ_API_KEY
GroqLlama 3 8B✅llama3-8b-8192groqGROQ_API_KEY
GroqMixtral 8x7B✅mixtral-8x7b-32768groqGROQ_API_KEY
GroqGemma 7B✅gemma-7b-itgroqGROQ_API_KEY
GroqGemma 2B✅gemma2-9b-itgroqGROQ_API_KEY
GroqLlama3 Groq 70B✅llama3-groq-70b-8192-tool-use-previewgroqGROQ_API_KEY
GroqLlama3 Groq 8B✅llama3-groq-8b-8192-tool-use-previewgroqGROQ_API_KEY
ollamaAll Models✅model-nameollama-
vLLMAll Models✅model-namevllm-
HuggingFaceAll Models✅model-namehuggingfaceHF_HOME

🖋️ References

@article{mei2024aios,
  title={AIOS: LLM Agent Operating System},
  author={Mei, Kai and Li, Zelong and Xu, Shuyuan and Ye, Ruosong and Ge, Yingqiang and Zhang, Yongfeng}
  journal={arXiv:2403.16971},
  year={2024}
}
@article{ge2023llm,
  title={LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem},
  author={Ge, Yingqiang and Ren, Yujie and Hua, Wenyue and Xu, Shuyuan and Tan, Juntao and Zhang, Yongfeng},
  journal={arXiv:2312.03815},
  year={2023}
}

🚀 Contributions

For how to contribute, see CONTRIBUTE. If you would like to contribute to the codebase, issues or pull requests are always welcome!

🌍 AIOS Contributors

AIOS contributors

🤝 Discord Channel

If you would like to join the community, ask questions, chat with fellows, learn about or propose new features, and participate in future developments, join our Discord Community!