Powered by OpenAirymax
The seminal fourth "Operating System Philosophy" in human computing history.
English | 简体中文
| User Type | Product | Version | Download |
|---|---|---|---|
| Pro Users | Docker | v0.0.4 |
📦 Get Docker |
| Personal Users | Desktop | v0.0.4 |
🖥️ Get Desktop |
AgentOS is an intelligent agent operating system that provides comprehensive OS-level support for orchestrating agent teams.
Personal Client Preview
⚡️
Foundational Multibody Cybernetic Intelligent System
- Pure Kernel: Only atomic mechanisms, ensuring purity and efficiency.
- Cognitive Loop: Perception, Planning, Action.
- Memory Stratification: L1 Raw → L2 Features → L3 Structures → L4 Patterns.
- Inherent Security: 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.
Drive Teams
- Precisely coordinates multi-Agent collaboration
- Efficiently completes complex task orchestration and resource scheduling
Autonomous Evolution:
- Possesses self-evolution capability
- Dynamically adjusts strategies
- Continuously optimizes execution effectiveness
✨
Brand New 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 → Real-time 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/module
- Operating System: 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
| Language | Usage Method |
|:-----|:---------|
| C/C++ | Develop via `syscalls.h` system call interface |
| Python | Install via `pip install agentos` then directly import |
| Go | Use `import "github.com/spharx/agentos/toolkit/go"` |
| Rust | Use `use agentos_toolkit::prelude::*;` |
| TypeScript | Install via `npm install @spharx/agentos-toolkit` then directly import |
| Document | Core Content |
|---|---|
| 📘 Architectural Principles | Five-dimensional orthogonal system, 24 core principles |
| 🚀 Quick Start | 5-minute getting-started guide |
| ⚙️ Build Guide | Detailed build steps and options |
| 🧪 Testing Guide | Unit/Integration/Contract testing |
| 🐳 Deployment Guide | Docker/Kubernetes deployment |
👉 Q1: What is the difference between AgentOS and traditional AI Agent frameworks?
AgentOS is an operating system-level product, not a single framework:
| Dimension | AgentOS | Traditional Frameworks |
|---|---|---|
| Positioning | Multi-agent collaboration OS | Single agent |
| Architecture | Microkernel + strict layering | Loosely coupled modules |
| Security | Four-layer inherent security | Application-level protection |
| Memory | Four-layer stratification system | Vector database |
| Token Efficiency | Saves ~500% | No optimization |
👉 Q2: Which application scenarios is it suitable for?
✅ Especially suitable
- 🎯 Complex multi-step task orchestration
- 🧠 Long-term memory and knowledge accumulation needs
- 🔒 High-security enterprise applications
- 💾 Resource-constrained embedded scenarios (atomslite)
- 🌐 Multi-language development teams
❌ Not suitable
- 🚫 Simple single-call tasks (using a sledgehammer to crack a nut)
👉 Q3: How is security guaranteed?
Security built-in design, four-layer protection
| Protection Layer | Implementation Method |
|---|---|
| Virtual Workspace | Process/Container/WASM sandbox isolation |
| Permission Arbitration | RBAC + YAML rule engine |
| Input Sanitization | Regex filtering + Type checking |
| Audit Trail | Full-chain tamper-proof logging |
👉 Q4: What prerequisite knowledge is needed for learning?
| Role | Prerequisite Knowledge | Time to Get Started |
|---|---|---|
| Application Developer | Python/Go basics | 1-2 days |
| System Developer | C/C++, OS fundamentals | 1-2 weeks |
| Architect | Microkernel, distributed systems | 1 month |
Recommended Path: Quick Start → Architectural Principles → CoreLoopThree
We are walking into the future: "Intelligence emergence, and nothing less, is the ultimate sublimation of AI".
☀️
This is not humanity's sunset, but the dawn of a new world
Believe
The spirit of open source can maximize the wisdom of the group;
Collaboration will propel humanity to new heights.
Witness
Every day of our work is part of history;
It will surely be engraved on the monument of human civilization's development.
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 create history
🔥
A faint light cannot illuminate the entire path, yet it guides our direction forward
Fork Project → Create Branch → Develop & Test → Submit PR → Code Review → Merge to MainMain Platforms: AtomGit (Recommended) · Gitee · GitHub
See AUTHORS.md for the list of contributors.
This project is licensed under the Apache License 2.0. See LICENSE file for details.
"From data intelligence emerges."
AtomGit · Gitee · GitHub · Official Website
© 2026 SPHARX Ltd. All Rights Reserved.