Skip to main content

An AI-powered task automation tool

Project description

OpenCopilot - PikoAi

Your AI-Powered Command-Line Companion!

PikoAi powered by the OpenCopilot framework, transforms your terminal into an intelligent assistant. Seamlessly integrate AI into your daily workflow to automate tasks, conduct research, interact with web services, and much more. Stop switching contexts and let your copilot handle the heavy lifting, right from your command line.

Install it using a single pip command

pip install pikoai

✨ See It In Action!

Watch a glimpse of OpenCopilot's capabilities:

OpenCopilot Demo

This demo showcases how OpenCopilot can understand your requests, interact with web pages, and provide you with the information you need, all within your terminal.


🚀 Core Features

  • LLM-Powered Task Automation: Leverages cutting-edge Large Language Models to understand your natural language prompts and orchestrate complex task execution.
  • Multi-Provider Support: Flexibility to choose and switch between various LLM providers such as Mistral, Groq, OpenAI, Anthropic, and Gemini.
  • Extensible Tool System: Equip your AI agent with a growing library of custom tools to interact with files, system details, web content, and more.
  • Versatile Execution Modes:
    • Conversational Mode: Engage in an interactive dialogue to collaboratively accomplish tasks.
    • One-Shot Task Execution: Directly execute specific tasks with a single, concise command.
  • User-Friendly CLI: An intuitive command-line interface to manage configurations, tools, API keys, and task execution.
  • Web Interaction: Browse websites, extract information, and perform web searches directly through the agent.

🛠️ Getting Started

Prerequisites

  • Python 3.8+
  • Git (if cloning from source)

Installation

You can install OpenCopilot using pip:

pip install pikoai

Alternatively, to install from source:

  1. Clone the repository:
    git clone https://github.com/Piko-AI/OpenCopilot.git
    
  2. Navigate to the project directory:
    cd OpenCopilot
    
  3. Create a virtual environment:
    python -m venv venv
    
    or if you have multiple Python versions:
    python3 -m venv venv
    
  4. Activate the virtual environment:
    • Windows:
      venv\Scripts\activate
      
    • macOS/Linux:
      source venv/bin/activate
      
  5. Install dependencies:
    pip install -r requirements.txt
    

▶️ Running the Application

Once the installation is complete, you can run OpenCopilot from the root directory of the project:

python Src/cli.py

or

python3 Src/cli.py

This will start OpenCopilot in conversational mode. You can also use it for one-shot tasks.


⚡ One-Shot Task Execution

Execute tasks directly without entering the conversational mode:

python Src/cli.py --task "Your task description here"

You can also set the maximum number of iterations for a task:

python Src/cli.py --task "Your task description here" --max-iter 5

🤝 Contributing

We welcome contributions! Please feel free to fork the repository, make your changes, and submit a pull request. For major changes, please open an issue first to discuss what you would like to change.


📄 License

This project is licensed under the terms of the LICENSE file.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pikoai-0.1.30.tar.gz (35.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pikoai-0.1.30-py3-none-any.whl (39.7 kB view details)

Uploaded Python 3

File details

Details for the file pikoai-0.1.30.tar.gz.

File metadata

  • Download URL: pikoai-0.1.30.tar.gz
  • Upload date:
  • Size: 35.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.1

File hashes

Hashes for pikoai-0.1.30.tar.gz
Algorithm Hash digest
SHA256 94e231a4ca73f7620e0b10c9d1ce2aa47027bef4a6d26569c53854aaae4074bc
MD5 3518bc0deec888442dd323f925fee0e4
BLAKE2b-256 75b872700f0d23c8f9c226ef5f89955bb6508d09b3f3978650b3b259891a853b

See more details on using hashes here.

File details

Details for the file pikoai-0.1.30-py3-none-any.whl.

File metadata

  • Download URL: pikoai-0.1.30-py3-none-any.whl
  • Upload date:
  • Size: 39.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.1

File hashes

Hashes for pikoai-0.1.30-py3-none-any.whl
Algorithm Hash digest
SHA256 f9b8e0c4352da1fff7ed27c855db78c430372f41ad7fd2aa99537490685a7f09
MD5 b8ce19fbe766c7695600d82433b53547
BLAKE2b-256 bfefa43b8b31a4d6538204e51aaf7329abd8c54e02222fdde48d2a1592432feb

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page