# AgentOS
[](https://opensource.org/licenses/MIT)
[](https://www.python.org/downloads/)
[](https://github.com/psf/black)
A minimal, production-ready implementation of Andrej Karpathy's Agent Operating System architecture, developed by Swarms.ai and partners.
## Overview
AgentOS is a lightweight, single-file implementation that provides a robust foundation for building autonomous AI agents. It implements the core concepts outlined in Karpathy's Agent OS architecture while maintaining simplicity and extensibility. Developed by [Swarms.ai](https://swarms.ai) and its partners, AgentOS is a production-ready implementation of autonomous AI agents that follows the architectural principles outlined by Andrej Karpathy.
## Features
- **Unified Model Interface**: Seamless integration with multiple LLM providers through LiteLLM
- Support for Anthropic Claude models (Opus, Sonnet, Haiku)
- Integration with OpenAI GPT models
- Access to optimized variants (GPT-4o, GPT-4o-mini)
- **Browser Automation**: Built-in browser agent capabilities for web interaction using browser-use
- **Multi-Modal Support**:
- Text processing and generation
- Video analysis through Google's Gemini models
- Audio processing and speech synthesis
- Image handling capabilities
- **Resource Management**:
- Efficient handling of computational resources
- Dynamic model selection based on task requirements
- Automatic GPU/CPU optimization
- **HuggingFace Integration**:
- Direct access to open-source models
- Support for text generation and multiple NLP tasks
- Automatic model quantization and optimization
- **Extensible Architecture**: Easy to add new capabilities and tools
## Core Components
- **Model Management**: Dynamic selection and utilization of language models
- **Browser Automation**: Autonomous web-based task execution
- **Resource Orchestration**: Efficient management of computational resources
- **Context Management**: Maintains system state and task dependencies
## Installation
```bash
pip3 install -U agentos-sdk
```
## Usage
```python
from agentos import AgentOS
# Initialize AgentOS
agent_os = AgentOS()
# Run a task
result = agent_os.run(
task="Your task description",
img="optional_image.jpg",
video="optional_video.mp4",
audio="optional_audio.mp3"
)
```
## Available Tools
AgentOS comes with a powerful set of built-in tools that enable various capabilities. Here's a comprehensive list of all available tools:
| Tool Name | Description | Use Case Examples |
|-----------|-------------|------------------|
| Browser Agent | Autonomous web browser automation tool that can navigate websites, extract information, and perform web-based tasks | - Web scraping<br>- Form filling<br>- Data extraction<br>- Website testing |
| Hugging Face Model | Interface for using various Hugging Face models for text generation and other NLP tasks | - Text generation<br>- Language translation<br>- Text classification<br>- Custom model inference |
| LiteLLM Model | Unified interface for multiple LLM providers including OpenAI, Anthropic, and others | - Text generation<br>- Chat completion<br>- Content creation<br>- Advanced reasoning |
| Safe Calculator | Secure mathematical expression evaluator with built-in safety checks | - Mathematical calculations<br>- Formula evaluation<br>- Secure computation<br>- Numeric processing |
| Terminal Developer Agent | Advanced agent for performing terminal operations and development tasks | - File operations<br>- Code execution<br>- System commands<br>- Development tasks |
| Generate Speech | Text-to-speech conversion tool supporting multiple voices and models | - Audio content creation<br>- Voice synthesis<br>- Accessibility features<br>- Audio narration |
| Generate Video | AI-powered video generation tool using Google's Veo 3.0 model | - Video content creation<br>- Visual storytelling<br>- Animation generation<br>- Creative content |
## Community
Join our community of agent engineers and researchers for technical support, cutting-edge updates, and exclusive access to world-class agent engineering insights!
| Platform | Description | Link |
|----------|-------------|------|
| 📚 Documentation | Official documentation and guides | [docs.swarms.world](https://docs.swarms.world) |
| 📝 Blog | Latest updates and technical articles | [Medium](https://medium.com/@kyeg) |
| 💬 Discord | Live chat and community support | [Join Discord](https://discord.gg/jM3Z6M9uMq) |
| 🐦 Twitter | Latest news and announcements | [@kyegomez](https://twitter.com/swarms_corp) |
| 👥 LinkedIn | Professional network and updates | [The Swarm Corporation](https://www.linkedin.com/company/the-swarm-corporation) |
| 📺 YouTube | Tutorials and demos | [Swarms Channel](https://www.youtube.com/channel/UC9yXyitkbU_WSy7bd_41SqQ) |
| 🎫 Events | Join our community events | [Sign up here](https://lu.ma/5p2jnc2v) |
| 🚀 Onboarding Session | Get onboarded with Kye Gomez, creator and lead maintainer of Swarms | [Book Session](https://cal.com/swarms/swarms-onboarding-session) |
## Contributing
We welcome contributions from the community. Please see our contributing guidelines for more information.
## License
This project is under the MIT License.
## Todo
- [ ] Add deep research agent or sub agent
- [ ] Implement video and audio processing
Raw data
{
"_id": null,
"home_page": "https://github.com/The-Swarm-Corporation/AgentOS",
"name": "agentos-sdk",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": "artificial intelligence, deep learning, optimizers, Prompt Engineering, swarms, agents, llms, transformers, multi-agent, swarms of agents, Enterprise-Grade Agents, Production-Grade Agents, Agents, Multi-Grade-Agents, Swarms, Transformers, LLMs, Prompt Engineering, Agents, Generative Agents, Generative AI, Agent Marketplace, Agent Store, quant, finance, algorithmic trading, portfolio optimization, risk management, financial modeling, machine learning for finance, natural language processing for finance",
"author": "Kye Gomez",
"author_email": "kye@apac.ai",
"download_url": "https://files.pythonhosted.org/packages/ee/43/db9cc4c3eb6d4cea4479abeaa60de3fe73f25dbd3215ab7f41be32f5f07f/agentos_sdk-0.0.2.tar.gz",
"platform": null,
"description": "# AgentOS\n\n[](https://opensource.org/licenses/MIT)\n[](https://www.python.org/downloads/)\n[](https://github.com/psf/black)\n\n\nA minimal, production-ready implementation of Andrej Karpathy's Agent Operating System architecture, developed by Swarms.ai and partners.\n\n\n\n## Overview\n\nAgentOS is a lightweight, single-file implementation that provides a robust foundation for building autonomous AI agents. It implements the core concepts outlined in Karpathy's Agent OS architecture while maintaining simplicity and extensibility. Developed by [Swarms.ai](https://swarms.ai) and its partners, AgentOS is a production-ready implementation of autonomous AI agents that follows the architectural principles outlined by Andrej Karpathy.\n\n\n## Features\n\n- **Unified Model Interface**: Seamless integration with multiple LLM providers through LiteLLM\n - Support for Anthropic Claude models (Opus, Sonnet, Haiku)\n - Integration with OpenAI GPT models\n - Access to optimized variants (GPT-4o, GPT-4o-mini)\n- **Browser Automation**: Built-in browser agent capabilities for web interaction using browser-use\n- **Multi-Modal Support**: \n - Text processing and generation\n - Video analysis through Google's Gemini models\n - Audio processing and speech synthesis\n - Image handling capabilities\n- **Resource Management**: \n - Efficient handling of computational resources\n - Dynamic model selection based on task requirements\n - Automatic GPU/CPU optimization\n- **HuggingFace Integration**: \n - Direct access to open-source models\n - Support for text generation and multiple NLP tasks\n - Automatic model quantization and optimization\n- **Extensible Architecture**: Easy to add new capabilities and tools\n\n## Core Components\n\n- **Model Management**: Dynamic selection and utilization of language models\n- **Browser Automation**: Autonomous web-based task execution\n- **Resource Orchestration**: Efficient management of computational resources\n- **Context Management**: Maintains system state and task dependencies\n\n## Installation\n\n```bash\npip3 install -U agentos-sdk\n```\n\n## Usage\n\n```python\nfrom agentos import AgentOS\n\n# Initialize AgentOS\nagent_os = AgentOS()\n\n# Run a task\nresult = agent_os.run(\n task=\"Your task description\",\n img=\"optional_image.jpg\",\n video=\"optional_video.mp4\",\n audio=\"optional_audio.mp3\"\n)\n```\n\n## Available Tools\n\nAgentOS comes with a powerful set of built-in tools that enable various capabilities. Here's a comprehensive list of all available tools:\n\n| Tool Name | Description | Use Case Examples |\n|-----------|-------------|------------------|\n| Browser Agent | Autonomous web browser automation tool that can navigate websites, extract information, and perform web-based tasks | - Web scraping<br>- Form filling<br>- Data extraction<br>- Website testing |\n| Hugging Face Model | Interface for using various Hugging Face models for text generation and other NLP tasks | - Text generation<br>- Language translation<br>- Text classification<br>- Custom model inference |\n| LiteLLM Model | Unified interface for multiple LLM providers including OpenAI, Anthropic, and others | - Text generation<br>- Chat completion<br>- Content creation<br>- Advanced reasoning |\n| Safe Calculator | Secure mathematical expression evaluator with built-in safety checks | - Mathematical calculations<br>- Formula evaluation<br>- Secure computation<br>- Numeric processing |\n| Terminal Developer Agent | Advanced agent for performing terminal operations and development tasks | - File operations<br>- Code execution<br>- System commands<br>- Development tasks |\n| Generate Speech | Text-to-speech conversion tool supporting multiple voices and models | - Audio content creation<br>- Voice synthesis<br>- Accessibility features<br>- Audio narration |\n| Generate Video | AI-powered video generation tool using Google's Veo 3.0 model | - Video content creation<br>- Visual storytelling<br>- Animation generation<br>- Creative content |\n\n\n## Community \n\nJoin our community of agent engineers and researchers for technical support, cutting-edge updates, and exclusive access to world-class agent engineering insights!\n\n| Platform | Description | Link |\n|----------|-------------|------|\n| \ud83d\udcda Documentation | Official documentation and guides | [docs.swarms.world](https://docs.swarms.world) |\n| \ud83d\udcdd Blog | Latest updates and technical articles | [Medium](https://medium.com/@kyeg) |\n| \ud83d\udcac Discord | Live chat and community support | [Join Discord](https://discord.gg/jM3Z6M9uMq) |\n| \ud83d\udc26 Twitter | Latest news and announcements | [@kyegomez](https://twitter.com/swarms_corp) |\n| \ud83d\udc65 LinkedIn | Professional network and updates | [The Swarm Corporation](https://www.linkedin.com/company/the-swarm-corporation) |\n| \ud83d\udcfa YouTube | Tutorials and demos | [Swarms Channel](https://www.youtube.com/channel/UC9yXyitkbU_WSy7bd_41SqQ) |\n| \ud83c\udfab Events | Join our community events | [Sign up here](https://lu.ma/5p2jnc2v) |\n| \ud83d\ude80 Onboarding Session | Get onboarded with Kye Gomez, creator and lead maintainer of Swarms | [Book Session](https://cal.com/swarms/swarms-onboarding-session) |\n\n## Contributing\n\nWe welcome contributions from the community. Please see our contributing guidelines for more information. \n\n## License\n\nThis project is under the MIT License.\n\n## Todo\n\n- [ ] Add deep research agent or sub agent\n- [ ] Implement video and audio processing",
"bugtrack_url": null,
"license": "MIT",
"summary": "AgentOS - TGSC",
"version": "0.0.2",
"project_urls": {
"Documentation": "https://docs.swarms.world",
"Homepage": "https://github.com/The-Swarm-Corporation/AgentOS",
"Repository": "https://github.com/The-Swarm-Corporation/AgentOS"
},
"split_keywords": [
"artificial intelligence",
" deep learning",
" optimizers",
" prompt engineering",
" swarms",
" agents",
" llms",
" transformers",
" multi-agent",
" swarms of agents",
" enterprise-grade agents",
" production-grade agents",
" agents",
" multi-grade-agents",
" swarms",
" transformers",
" llms",
" prompt engineering",
" agents",
" generative agents",
" generative ai",
" agent marketplace",
" agent store",
" quant",
" finance",
" algorithmic trading",
" portfolio optimization",
" risk management",
" financial modeling",
" machine learning for finance",
" natural language processing for finance"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "a6923d1c0ba05849d1c55d37e3707826822f54cd787b23f4e10ec27bddf80a85",
"md5": "4b8758b6045998eb56aaaa37f5e07898",
"sha256": "a7cabb857c9890301aa563f667be699c49c4d0d93e4f05bcaa3b0eff2bdb373f"
},
"downloads": -1,
"filename": "agentos_sdk-0.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "4b8758b6045998eb56aaaa37f5e07898",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 25122,
"upload_time": "2025-07-10T17:47:56",
"upload_time_iso_8601": "2025-07-10T17:47:56.242496Z",
"url": "https://files.pythonhosted.org/packages/a6/92/3d1c0ba05849d1c55d37e3707826822f54cd787b23f4e10ec27bddf80a85/agentos_sdk-0.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "ee43db9cc4c3eb6d4cea4479abeaa60de3fe73f25dbd3215ab7f41be32f5f07f",
"md5": "53d33920bf162fc500c54a7eca475572",
"sha256": "87ab767a5a7c99ee1327bb06d5a6fb53f26d7a57be33d40c4473bb47c11f42d7"
},
"downloads": -1,
"filename": "agentos_sdk-0.0.2.tar.gz",
"has_sig": false,
"md5_digest": "53d33920bf162fc500c54a7eca475572",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 24709,
"upload_time": "2025-07-10T17:47:57",
"upload_time_iso_8601": "2025-07-10T17:47:57.470779Z",
"url": "https://files.pythonhosted.org/packages/ee/43/db9cc4c3eb6d4cea4479abeaa60de3fe73f25dbd3215ab7f41be32f5f07f/agentos_sdk-0.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-10 17:47:57",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "The-Swarm-Corporation",
"github_project": "AgentOS",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "swarms",
"specs": []
},
{
"name": "litellm",
"specs": []
},
{
"name": "browser-use",
"specs": []
},
{
"name": "transformers",
"specs": []
},
{
"name": "torch",
"specs": []
},
{
"name": "langchain-openai",
"specs": []
},
{
"name": "chromadb",
"specs": []
},
{
"name": "pypdf2",
"specs": []
},
{
"name": "pandas",
"specs": []
},
{
"name": "beautifulsoup4",
"specs": []
},
{
"name": "sentence-transformers",
"specs": []
},
{
"name": "claude-code-sdk",
"specs": []
},
{
"name": "google-cloud-aiplatform",
"specs": []
}
],
"lcname": "agentos-sdk"
}
JSON
