AIOS

Active
GitHub Python NOASSERTION

Description

AIOS: AI Agent Operating System - a foundational runtime for large-scale deployment and management of LLM agents with scheduling, memory management, and tool registration.

Key Features

  • AIOS Kernel — LLM-embedded OS kernel managing agent scheduling, context switching, memory, storage, and tools
  • AIOS SDK (Cerebrum) — platform for agent development, deployment, distribution, and discovery
  • Multi-framework support — compatible with ReAct, Reflexion, AutoGen, Open Interpreter, MetaGPT and more
  • Computer-Use specialized architecture — sandboxed computer interaction with VM controller and MCP Server
  • Multiple deployment modes — Web UI, Terminal UI, remote kernel, containerized deployments
  • Agent marketplace ecosystem — publish, download, and share agents via Agent Hub

Use Cases

💡 Large-scale agent deployment and management — unified scheduling of multiple LLM agents at the OS level
💡 Cross-framework agent development — develop and onboard AI agents using a unified SDK
💡 Computer-use agents — safely execute desktop operations through sandboxed environments
💡 Academic research and prototyping — quickly build agent system prototypes with AIOS Kernel and SDK
💡 Agent distribution and sharing — publish and commercialize agents via the Agent Hub mechanism

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (6.2k stars)
  • Established track record (2 years in production)
  • Responsive to issues, low backlog

⚠️ Limitations

  • No clear open-source license

Quick Start

git clone https://github.com/agiresearch/AIOS.git
cd AIOS
pip install -r requirements.txt

# Launch AIOS Web UI
python -m aios.web

# Or run via Terminal UI
python -m aios.terminal

# Install Cerebrum SDK
pip install cerebrum

# See documentation
# https://docs.aios.foundation/

Related Projects

Atomic Agents

6.2k · Python
Active A+

Atomic Agents is a modular AI agent building framework with an atomic design philosophy, providing composable components including tools, pipelines, and memory management for constructing agent systems.

frameworkpythonagent +2
  • · Atomic design philosophy with single-purpose, reusable, composable components
  • · Built on Instructor and Pydantic for type-safe, predictable agent behavior
  • · Multi-provider support including OpenAI, Anthropic, Groq, Gemini, and more

AutoChain

1.9k · Python
Stale C

AutoChain is a lightweight, extensible, and testable LLM Agent framework by Forethought, providing clean abstractions for agent building with automatic tool selection, conversation history management, and automated testing workflows.

frameworkagentpython +3
  • · Lightweight and extensible generative agent pipeline with minimal abstraction layers
  • · Support for custom tools and OpenAI function calling with automatic spec conversion
  • · Simple memory tracking for conversation history and tool outputs with BufferMemory

LlamaFactory

74.1k · Python
Active A+

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs. Supports LoRA, QLoRA, RLHF and more for building custom agent models.

pythonllmagent +2
  • · 100+ model support - covers LLaMA, Qwen3, DeepSeek, Gemma, GLM, Mistral, Phi and over 100 large language models
  • · Full training pipeline - supports pre-training, SFT, RLHF, DPO, KTO, ORPO, PPO and complete training workflows
  • · Efficient fine-tuning - supports 16-bit full tuning, LoRA, QLoRA (2-8 bit) plus GaLore, BAdam, APOLLO and other advanced algorithms