cognitrix


Namecognitrix JSON
Version 0.2.5 PyPI version JSON
download
home_pagehttps://github.com/theonlyamos/cognitrix
SummaryPackage for creating AI Agents using llms
upload_time2024-06-14 17:32:58
maintainerNone
docs_urlNone
authortheonlyamos
requires_python<4.0,>=3.12
licenseApache2
keywords cognitrix ai agents ai agents ai-agents llms autonomous agents
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            # Cognitrix

Cognitrix is an open-source autonomous AI agents orchestrator built in Python. It allows you to create and manage AI agents with ease and integrates seamlessly with large language models (LLMs) from various providers. 

## Features

- **Agent Creation and Management:** Create, list, and load AI agents with customizable names, tasks, and configurations.
- **LLM Integration:** Integrates with multiple LLM providers, including Anthropic (Claude), Cohere, Groq, Google, OpenAI, and Together.
- **Modular Architecture:** Easily extensible, allowing the addition of new tools, agents, and LLM integrations.
- **Conversational Interface:** Interact with AI agents through a command-line interface, providing queries and receiving responses.
- **Tool Integration:** Agents can utilize a variety of tools, including calculators, web searches, file system browsers, and more.
- **Autonomous Agent Mode:** Agents can operate autonomously, visually perceiving the screen, interacting with UI elements, and performing tasks.
- **Multimodal Support:** Handles both text and image inputs/outputs, enabling multimodal interactions.

## Architecture

Cognitrix's architecture is designed to be highly modular and extensible:

- **Agents:** The base `Agent` class and specialized classes like `AIAssistant` for creating and managing AI agents.
- **LLMs:** A collection of classes for integrating with various LLM providers (Cohere, OpenAI, Claude, etc.).
- **Tools:** A set of tools that agents can utilize. Each tool has a `category` attribute for grouping and management.
- **Templates:** Customizable prompt templates guide the behavior and output formats of LLMs.

More tools can be added by creating new classes that inherit from the `Tool` base class and specifying a unique `category`.

## Installation

```bash
pip install cognitrix
```

Alternatively, you can install directly from GitHub:

```bash
pip install https://github.com/theonlyamos/cognitrix/archive/main.zip
```

## Usage

To run Cognitrix with default settings:

```bash
cognitrix
```

To list supported LLM providers:

```bash
cognitrix --providers
```

To list created agents:

```bash
cognitrix agents
```

To list available tools:

```bash
cognitrix --tools
```

To run Cognitrix with a specific provider:

```bash
cognitrix --provider <provider_name>
```

To run Cognitrix with a specific agent:

```bash
cognitrix --agent <agent_name>
```

To run Cognitrix with a category of tools:

```bash
cognitrix --load-tools "web"
```

To run Cognitrix with categories of tools:

```bash
cognitrix --load-tools "web,general"
```

To create a new agent:

```bash
cognitrix agents --new
```

For more options and usage details, use the help command:

```bash
cognitrix --help
```

## Contributing

Cognitrix is open source and contributions are welcome! Please refer to [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on how to contribute.

## License

This project is licensed under the MIT license. See [LICENSE.md](LICENSE.md) for more information.

## Acknowledgments

Cognitrix was created by [Amos Amissah](https://github.com/theonlyamos) and is inspired by projects like AutoGPT and GPT Engineer. Special thanks to the open-source community and AI companies providing LLM APIs.

            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/theonlyamos/cognitrix",
    "name": "cognitrix",
    "maintainer": null,
    "docs_url": null,
    "requires_python": "<4.0,>=3.12",
    "maintainer_email": null,
    "keywords": "cognitrix, ai, agents, ai agents, ai-agents, llms, autonomous agents",
    "author": "theonlyamos",
    "author_email": "theonlyamos@gmail.com",
    "download_url": "https://files.pythonhosted.org/packages/83/de/75e41a7910f06bf5cec230e423b1830d1f330d67f123dcf29b00ffa201b6/cognitrix-0.2.5.tar.gz",
    "platform": null,
    "description": "# Cognitrix\n\nCognitrix is an open-source autonomous AI agents orchestrator built in Python. It allows you to create and manage AI agents with ease and integrates seamlessly with large language models (LLMs) from various providers. \n\n## Features\n\n- **Agent Creation and Management:** Create, list, and load AI agents with customizable names, tasks, and configurations.\n- **LLM Integration:** Integrates with multiple LLM providers, including Anthropic (Claude), Cohere, Groq, Google, OpenAI, and Together.\n- **Modular Architecture:** Easily extensible, allowing the addition of new tools, agents, and LLM integrations.\n- **Conversational Interface:** Interact with AI agents through a command-line interface, providing queries and receiving responses.\n- **Tool Integration:** Agents can utilize a variety of tools, including calculators, web searches, file system browsers, and more.\n- **Autonomous Agent Mode:** Agents can operate autonomously, visually perceiving the screen, interacting with UI elements, and performing tasks.\n- **Multimodal Support:** Handles both text and image inputs/outputs, enabling multimodal interactions.\n\n## Architecture\n\nCognitrix's architecture is designed to be highly modular and extensible:\n\n- **Agents:** The base `Agent` class and specialized classes like `AIAssistant` for creating and managing AI agents.\n- **LLMs:** A collection of classes for integrating with various LLM providers (Cohere, OpenAI, Claude, etc.).\n- **Tools:** A set of tools that agents can utilize. Each tool has a `category` attribute for grouping and management.\n- **Templates:** Customizable prompt templates guide the behavior and output formats of LLMs.\n\nMore tools can be added by creating new classes that inherit from the `Tool` base class and specifying a unique `category`.\n\n## Installation\n\n```bash\npip install cognitrix\n```\n\nAlternatively, you can install directly from GitHub:\n\n```bash\npip install https://github.com/theonlyamos/cognitrix/archive/main.zip\n```\n\n## Usage\n\nTo run Cognitrix with default settings:\n\n```bash\ncognitrix\n```\n\nTo list supported LLM providers:\n\n```bash\ncognitrix --providers\n```\n\nTo list created agents:\n\n```bash\ncognitrix agents\n```\n\nTo list available tools:\n\n```bash\ncognitrix --tools\n```\n\nTo run Cognitrix with a specific provider:\n\n```bash\ncognitrix --provider <provider_name>\n```\n\nTo run Cognitrix with a specific agent:\n\n```bash\ncognitrix --agent <agent_name>\n```\n\nTo run Cognitrix with a category of tools:\n\n```bash\ncognitrix --load-tools \"web\"\n```\n\nTo run Cognitrix with categories of tools:\n\n```bash\ncognitrix --load-tools \"web,general\"\n```\n\nTo create a new agent:\n\n```bash\ncognitrix agents --new\n```\n\nFor more options and usage details, use the help command:\n\n```bash\ncognitrix --help\n```\n\n## Contributing\n\nCognitrix is open source and contributions are welcome! Please refer to [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on how to contribute.\n\n## License\n\nThis project is licensed under the MIT license. See [LICENSE.md](LICENSE.md) for more information.\n\n## Acknowledgments\n\nCognitrix was created by [Amos Amissah](https://github.com/theonlyamos) and is inspired by projects like AutoGPT and GPT Engineer. Special thanks to the open-source community and AI companies providing LLM APIs.\n",
    "bugtrack_url": null,
    "license": "Apache2",
    "summary": "Package for creating AI Agents using llms",
    "version": "0.2.5",
    "project_urls": {
        "Bug Tracker": "https://github.com/theonlyamos/cognitrix/issues",
        "Homepage": "https://github.com/theonlyamos/cognitrix",
        "Repository": "https://github.com/theonlyamos/cognitrix"
    },
    "split_keywords": [
        "cognitrix",
        " ai",
        " agents",
        " ai agents",
        " ai-agents",
        " llms",
        " autonomous agents"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "c1639570f54fcae0485de75a9533977ba97580d32f18d3d56f9c60c2d34bbb62",
                "md5": "4ec1fdc65b0d02d5dc9fc9bf6b25f33f",
                "sha256": "23fb7d3f35c07a8aa3a0612a2c912005593283d987e9ab0b4c00fc1a5cb8bb15"
            },
            "downloads": -1,
            "filename": "cognitrix-0.2.5-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "4ec1fdc65b0d02d5dc9fc9bf6b25f33f",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": "<4.0,>=3.12",
            "size": 54202,
            "upload_time": "2024-06-14T17:32:57",
            "upload_time_iso_8601": "2024-06-14T17:32:57.795944Z",
            "url": "https://files.pythonhosted.org/packages/c1/63/9570f54fcae0485de75a9533977ba97580d32f18d3d56f9c60c2d34bbb62/cognitrix-0.2.5-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "83de75e41a7910f06bf5cec230e423b1830d1f330d67f123dcf29b00ffa201b6",
                "md5": "cc3c7c7a8431e6d8f027724ab89c4cb9",
                "sha256": "7f8f4988e58dfabb76297578297c8cc765c73284eb8a886e468573a433fdee4b"
            },
            "downloads": -1,
            "filename": "cognitrix-0.2.5.tar.gz",
            "has_sig": false,
            "md5_digest": "cc3c7c7a8431e6d8f027724ab89c4cb9",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": "<4.0,>=3.12",
            "size": 39265,
            "upload_time": "2024-06-14T17:32:58",
            "upload_time_iso_8601": "2024-06-14T17:32:58.865460Z",
            "url": "https://files.pythonhosted.org/packages/83/de/75e41a7910f06bf5cec230e423b1830d1f330d67f123dcf29b00ffa201b6/cognitrix-0.2.5.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-06-14 17:32:58",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "theonlyamos",
    "github_project": "cognitrix",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "lcname": "cognitrix"
}
        
Elapsed time: 0.26672s