Agent OS

AgentOS is an intelligent agent operating system that provides comprehensive OS-level support for orchestrating agent teams.

Foundational Theory 👉 Multibody Cybernetic Intelligent System

• Pure Kernel: Only atomic mechanisms (IPC/Mem/Task/Time), ensuring purity and efficiency.
• Cognitive Loop: Perception → Planning → Action, with dual-system synergy (System 1 + System 2).
• Memory Stratification: L1 Raw → L2 Features → L3 Structures → L4 Patterns, enabling intelligence emergence.
• Inherent Security: Four-layer protection: Sandbox Isolation, Permission Arbitration, Input Sanitization, Audit Trail.
• Token Efficiency: Saves approximately 500% tokens compared to traditional frameworks.
• Comprehensive SDKs: Native support for Go / Python / Rust / TypeScript.

Team Orchestration

• Precisely coordinates multi‑agent collaboration
• Enables efficient task orchestration and resource scheduling

Autonomous Evolution

• Self‑evolving capability
• Dynamically adjusts strategies
• Continuously optimizes execution effectiveness

✨ Groundbreaking Architecture · Inherent Security · Intelligence Emergence ✨

Architecture Design
Complete architecture from kernel to application:

Application Layer (openlab)
    ⇅
Service Layer (daemon)
    ⇅
Kernel Layer (atoms)
    ⇅
Security Layer (cupolas)
    ⇅
Support Layer (commons)
    ⇅
SDK Layer (toolkit)

Design Principles
Built upon ARCHITECTURAL_PRINCIPLES:

• System Perspective: Feedback loops · Layered decomposition · Holistic design · Emergence management → Response <10ms
• Kernel Perspective: Minimalist kernel · Contractual interfaces · Service isolation · Pluggable strategies → Kernel ~25K LOC
• Cognitive Perspective: Dual‑system synergy · Incremental evolution · Memory stratification · Forgetting mechanism → Token savings 500%
• Engineering Perspective: Security built‑in · Observability · Resource determinism · Cross‑platform consistency → Test coverage >90%
• Design Aesthetics: Simplicity first · Extreme attention to detail · Human‑centric · Perfectionism → API <50 per module

• OS: Ubuntu 22.04+ / macOS 13+ / Windows 11 (WSL2)
• Compiler: GCC 11+ / Clang 14+ (C11/C++17)
• Build Tools: CMake 3.20+, Ninja
• Python: 3.10+ (Required for OpenLab)

# 1. Clone repository
git clone https://atomgit.com/spharx/agentos.git && cd agentos

# 2. Install dependencies (Ubuntu)
sudo apt install -y build-essential cmake gcc g++ libssl-dev libsqlite3-dev ninja-build

# 3. Build kernel
mkdir build && cd build
cmake .. -G Ninja -DCMAKE_BUILD_TYPE=Release -DBUILD_TESTS=ON
cmake --build . --parallel $(nproc)

# 4. Run tests
ctest --output-on-failure

# Build image
docker build -f scripts/deploy/docker/Dockerfile.kernel -t agentos:latest .

# Run container
docker run -d --name agentos -p 8080:8080 -v ./config:/app/config agentos:latest

☀️ This is not humanity's sunset, but the dawn of a new world ☀️

"Intelligence emergence, and nothing less, is the ultimate sublimation of AI."

This is the future we are stepping into.

Believe
The spirit of open source can unleash the collective wisdom of the community, propelling humanity to new heights.

Witness
Every day of our work is part of history, destined to be engraved on the monument of human civilization, witnessing the true emergence of intelligence.

This is not humanity's sunset, but the dawn of a new world.

Whether you are an experienced developer or just starting out:

• 🐛 Find Issues → Report bugs, help us improve quality
• 💡 Share Ideas → Suggest new features, make the project stronger
• 📝 Share Knowledge → Improve documentation, help more people understand AgentOS
• 🔧 Write Code → Submit PRs, jointly build a better intelligent agent OS

See Contributing Guide

Fork Project → Create Branch → Develop & Test → Submit PR → Code Review → Merge to Main

Main Platforms: AtomGit (Recommended) · Gitee · GitHub

🔥 "A faint light cannot illuminate the entire path, yet it guides our direction forward." 🔥

This project is licensed under the Apache License 2.0. See LICENSE file for details.