AIOS

AIOS: AI Agent Operating System

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

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.

Computer-use Specialized Architecture

For computer-use agent, the architecture extends the AIOS Kernel with significant enhancements focused on computer contextualization. While preserving essential components like LLM Core(s), Context Manager, and Memory Manager, the Tool Manager module has been fundamentally redesigned to incorporate a VM (Virtual Machine) Controller and MCP Server. This redesign creates a sandboxed environment that allows agents to safely interact with computer systems while maintaining a consistent semantic mapping between agent intentions and computer operations.

News

• [2025-07-08] The foundational paper AIOS: LLM Agent Operating System has been accepted by the Conference on Language Modeling (COLM 2025). Congratulations to the team!
• [2025-07-02] AIOS has been selected as the finalist for AgentX – LLM Agents MOOC Competition, hosted by Berkeley RDI in conjunction with the Advanced LLM Agents MOOC. Congratulations to the team!
• [2025-05-24] Check out our paper on computer-use agent: LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS and the corresponding codebase.
• [2025-03-13] Paper Cerebrum (AIOS SDK): A Platform for Agent Development, Deployment, Distribution, and Discovery has been accepted by NAACL 2025! Features has been integrated into Cerebrum.
• [2025-03-12] A major refactor of the codebase packed with powerful new features have been integrated into the main repo. Please check out the AIOS v0.2.2 release.
• [2025-03-10] Check out our paper on agentic memory A-MEM: Agentic Memory for LLM Agents and the corresponding codebase.
• [2025-02-07] Our paper From Commands to Prompts: LLM-based Semantic File System for AIOS has been accepted by ICLR2025! The features of this paper has been integrated into AIOS as the Terminal UI.
• [2025-01-27] Deepseek-r1 (1.5b, 7b, 8b, 14b, 32b, 70b, 671b) has already been supported in AIOS, both open-sourced versions and deepseek apis (deepseek-chat and deepseek-reasoner) are available.
• [2024-11-30] AIOS v0.2: Disentangled AIOS Kernel (this AIOS repository) and AIOS SDK (The Cerebrum repository), Remote Kernel for agent users.
• [2024-09-01] AIOS supports multiple agent creation frameworks (e.g., ReAct, Reflexion, OpenAGI, AutoGen, Open Interpreter, MetaGPT). Agents created by these frameworks can onboard AIOS. Onboarding guidelines can be found at the Doc.
• [2024-07-10] AIOS documentation is up, which can be found at Website.
• [2024-06-20] Function calling for open-sourced LLMs (native huggingface, vLLM, ollama) is supported.
• [2024-05-20] More agents with ChatGPT-based tool calling are added (i.e., MathAgent, RecAgent, TravelAgent, AcademicAgent and CreationAgent), their profiles and workflows can be found in OpenAGI.
• [2024-05-13] ️ Local models (diffusion models) as tools from HuggingFace are integrated.
• [2024-05-01] ️ The agent creation in AIOS is refactored, which can be found in our OpenAGI package.
• [2024-04-05] ️ AIOS currently supports external tool callings (google search, wolframalpha, rapid API, etc).
• [2024-04-02] AIOS Discord Community is up. Welcome to join the community for discussions, brainstorming, development, or just random chats! For how to contribute to AIOS, please see CONTRIBUTE.
• [2024-03-25] ✈️ Our paper AIOS: LLM Agent Operating System is released!
• [2023-12-06] After several months of working, our perspective paper LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem is officially released.

Different deployment modes of AIOS

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

• AHM (Agent Hub Machine): Central server that hosts the agent marketplace/repository where users can publish, download, and share agents. Acts as the distribution center for all agent-related resources.
• AUM (Agent UI Machine): Client machine that provides user interface for interacting with agents. Can be any device from mobile phones to desktops that supports agent visualization and control.
• ADM (Agent Development Machine): Development environment where agent developers write, debug and test their agents. Requires proper development tools and libraries.
• ARM (Agent Running Machine): Execution environment where agents actually run and perform tasks. Needs adequate computational resources for agent operations.

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)

• Features:
  • For agent users: They can download agents from agent hub from Machine B and run agents on Machine A.
  • For agent developers: They can develop and test agents in Machine A and can upload agents to agent hub on Machine B.

Mode 2 (Remote Kernel Mode)

• Features:
  • Remote use of agents: Agent users / developers can use agents on Machine B, which is different from the development and running machine (Machine A).
  • Benefit users who would like to use agents on resource-restricted machine (e.g., mobile device or edge device)

Mode 2.5 (Remote Kernel Dev Mode)

• Features:
  • Remote development of agents: Agent developers can develop their agents on Machine B while running and testing their agents in Machine A. Benefit developers who would like to develop agents on resource-restricted machine (e.g., mobile device or edge device)
• Critical technique:
  • Packaging and agent transmission on different machines for distributed agent development and testing

Mode 3 (Personal Remote Kernel Mode)

• Ongoing Features:

  • Each user/developer can have their personal AIOS with long-term persistent data as long as they have registered account in the AIOS ecosystem
  • Their personal data can be synced to different machines with the same account

• Critical techniques:

  • User account registration and verification mechanism
  • Persistent personal data storage for each user's AIOS
  • Synchronization for different AIOS instances on different devices within the same account
  • Data privacy mechanism

Mode 4 (Personal Remote Virtual Kernel Mode)

• Ongoing Features:
  • Different user/developer's personal AIOS kernels can co-exist in the same physical machine through virtualization
• Critical techniques:
  • Virtualization of different AIOS kernel instances in the same machine
  • Scheduling and resource allocation mechanism for different virtual machines located in the same machine

✈️ Getting Started

Please see our ongoing documentation for more information.

• Installation
• Quickstart
• WebUI Quickstart

Installation

Requirements

Python

• Supported versions: Python 3.10 - 3.11

Installation from source

Step 1: Install AIOS Kernel

Git clone AIOS kernel

git clone https://github.com/agiresearch/AIOS.git

Create venv environment

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

[!TIP] We strongly recommend using uv for faster and more reliable package installation. To install uv: bash pip install uv

For GPU environments:

uv pip install -r requirements-cuda.txt

For CPU-only environments:

uv pip install -r requirements.txt

Alternatively, if you prefer using pip:

For GPU environments:

pip install -r requirements-cuda.txt

For CPU-only environments:

pip install -r requirements.txt

Step 2: Install AIOS SDK (Cerebrum)

1. Clone the Cerebrum repository:

   bash复制

   git clone https://github.com/agiresearch/Cerebrum.git

2. Install using uv (recommended):

   bash复制

   cd Cerebrum && uv pip install -e .

   Or using pip:

   bash复制

   cd Cerebrum && pip install -e .

Step 3: Install Virtualized Environment (Optional)

To use the mcp for computer-use agent, we strongly recommend you install a virtualized environment equipped with GUI. Instructions can be found in here.

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 bo