# GPT Computer Agent
Hi, this is an alternative work for providing ChatGPT MacOS app to Windows and Linux. In this way this is a fresh and stable work. You can easily install as Python library for this time but we will prepare a pipeline for providing native install scripts (.exe).
Powered by <a href="https://github.com/Upsonic/Tiger"><strong>Upsonic Tiger 🐅</strong></a> A function hub for llm agents.
## Installation and Run
Needed >= Python 3.9
```console
pip3 install 'gpt-computer-agent[base]'
```
```console
computeragent
```
### Wake Word | NEW
<details>
We have added Pvporcupine integration. To use it, you need to install an additional library:
```console
pip3 install 'gpt-computer-agent[wakeword]'
```
After that, please enter your [Pvporcupine](https://picovoice.ai/) API key and enable the wake word feature.
</details>
<p align="center">
<br>
<br>
<br>
</p>
### Agent Infrastructure
With this way you can create `crewai` agents and using it into gpt-computer-agent gui and tools.
```console
pip3 install 'gpt-computer-agent[base]'
pip3 install 'gpt-computer-agent[agentic]'
```
```python
from gpt_computer_agent import Agent, start
manager = Agent(
role='Project Manager',
goal='understands project needs and assist coder',
backstory="""You're a manager at a large company.""",
)
coder = Agent(
role='Senior Python Coder',
goal='writing python scripts and copying to clipboard',
backstory="""You're a python developer at a large company.""",
)
start()
```
### Adding Custom Tools
Now you are able to add custom tools that run in the agentic infra and agent processes.
```python
from gpt_computer_agent import Tool, start
@Tool
def sum_tool(first_number: int, second_number: int) -> str:
"""Useful for when you need to sum two numbers together."""
return first_number + second_number
start()
```
### API | NEW
Now you can use your GPT Computer Agent remotely! GUI still active, for this there is few steps:
```console
pip3 install 'gpt-computer-agent[base]'
pip3 install 'gpt-computer-agent[api]'
```
```console
computeragent --api
```
```python
from gpt_computer_agent.remote import remote
output = remote.input("Hi, how are you today?", screen=False, talk=False)
print(output)
remote.just_screenshot()
remote.talk("TTS test")
# Other Functionalities
remote.reset_memory()
remote.profile("default")
remote.enable_predefined_agents()
remote.disable_predefined_agents()
remote.enable_online_tools()
remote.disable_online_tools()
```
<p align="center">
<br>
<br>
<br>
<br>
<br>
</p>
## Roadmap
| Feature | Status | Target Release |
|---------------------------------|--------------|----------------|
| Clear Chat History | Completed | Q2 2024 |
| Long Audios Support (Split 20mb) | Completed | Q2 2024 |
| Text Inputs | Completed | Q2 2024 |
| Just Text Mode (Mute Speech) | Completed | Q2 2024 |
| Added profiles (Different Chats) | Completed | Q2 2024 |
| More Feedback About Agent Status | Completed | Q2 2024 |
| Local Model Vision and Text (With Ollama, and vision models) | Completed | Q2 2024 |
| **Our Customizable Agent Infrastructure** | Completed | Q2 2024 |
| Supporting Groq Models | Completed | Q2 2024 |
| **Adding Custom Tools** | Completed | Q2 2024 |
| Click on something on the screen (text and icon) | Completed | Q2 2024 |
| New UI | Completed | Q2 2024 |
| Native Applications, exe, dmg | Failed (Agentic Infra libraries not supported for now) | Q2 2024 |
| **Collaborated Speaking Different Voice Models on long responses.** | Completed | Q2 2024 |
| **Auto Stop Recording, when you complate talking** | Completed | Q2 2024 |
| **Wakeup Word** | Completed | Q2 2024 |
| **Continuously Conversations** | Completed | Q2 2024 |
| **Adding more capability on device** | Planned | Q2 2024 |
| DeepFace Integration (Facial Recognition) | Planned | Q2 2024 |
## Capabilities
At this time we have many infrastructure elements. We just aim to provide whole things that already in ChatGPT app.
| Capability | Status |
|------------------------------------|----------------------------------|
| **Screen Read** | OK |
| **Click to and Text or Icon in the screen** | OK |
| **Move to and Text or Icon in the screen** | OK |
| **Typing Something** | OK |
| **Pressing to Any Key** | OK |
| **Scrolling** | OK |
| **Microphone** | OK |
| **System Audio** | OK |
| **Memory** | OK |
| **Open and Close App** | OK |
| **Open a URL** | OK |
| **Clipboard** | OK |
| **Search Engines** | OK |
| **Writing and running Python** | OK |
| **Writing and running SH** | OK |
| **Using your Telegram Account** | OK |
| **Knowledge Management** | OK |
| **[Add more tool](https://github.com/khulnasoft/gpt-computer-agent/blob/master/gpt_computer_agent/standard_tools.py)** | ? |
### Predefined Agents
If you enable it your agent will work with these teams:
| Team Name | Status |
|------------------------------------|----------------------------------|
| **search_on_internet_and_report_team** | OK |
| **generate_code_with_aim_team_** | OK |
| **[Add your own one](https://github.com/khulnasoft/gpt-computer-agent/blob/master/gpt_computer_agent/teams.py)** | ? |
## Contributors
<a href="https://github.com/khulnasoft/gpt-computer-agent/graphs/contributors">
<img src="https://contrib.rocks/image?repo=khulnasoft/gpt-computer-agent" />
</a>
Raw data
{
"_id": null,
"home_page": "https://github.com/khulnasoft/gpt-computer-agent",
"name": "gpt-computer-agent",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": null,
"author": "KhulnaSoft DevOps",
"author_email": "info@khulnasoft.com",
"download_url": "https://files.pythonhosted.org/packages/d4/76/09284a5b878e63bcba6561736f672340db8dba8c94dc6fc2e11ae571b2f8/gpt_computer_agent-1.0.2.tar.gz",
"platform": null,
"description": "# GPT Computer Agent\nHi, this is an alternative work for providing ChatGPT MacOS app to Windows and Linux. In this way this is a fresh and stable work. You can easily install as Python library for this time but we will prepare a pipeline for providing native install scripts (.exe).\n\nPowered by <a href=\"https://github.com/Upsonic/Tiger\"><strong>Upsonic Tiger \ud83d\udc05</strong></a> A function hub for llm agents.\n\n\n\n\n## Installation and Run\nNeeded >= Python 3.9\n```console\npip3 install 'gpt-computer-agent[base]'\n```\n\n```console\ncomputeragent\n```\n\n### Wake Word | NEW\n<details>\n\n\nWe have added Pvporcupine integration. To use it, you need to install an additional library:\n\n```console\npip3 install 'gpt-computer-agent[wakeword]'\n```\n\nAfter that, please enter your [Pvporcupine](https://picovoice.ai/) API key and enable the wake word feature.\n</details>\n\n<p align=\"center\">\n<br>\n <br>\n <br>\n\n</p>\n\n\n### Agent Infrastructure\n\nWith this way you can create `crewai` agents and using it into gpt-computer-agent gui and tools.\n\n\n```console\npip3 install 'gpt-computer-agent[base]'\npip3 install 'gpt-computer-agent[agentic]'\n```\n\n```python\nfrom gpt_computer_agent import Agent, start\n\nmanager = Agent(\n role='Project Manager',\n goal='understands project needs and assist coder',\n backstory=\"\"\"You're a manager at a large company.\"\"\",\n)\n\ncoder = Agent(\n role='Senior Python Coder',\n goal='writing python scripts and copying to clipboard',\n backstory=\"\"\"You're a python developer at a large company.\"\"\",\n)\n\n\nstart()\n```\n\n\n\n### Adding Custom Tools\n\nNow you are able to add custom tools that run in the agentic infra and agent processes. \n\n\n```python\nfrom gpt_computer_agent import Tool, start\n\n@Tool\ndef sum_tool(first_number: int, second_number: int) -> str:\n \"\"\"Useful for when you need to sum two numbers together.\"\"\"\n return first_number + second_number\n\nstart()\n```\n\n\n\n\n\n\n### API | NEW\n\nNow you can use your GPT Computer Agent remotely! GUI still active, for this there is few steps:\n\n```console\npip3 install 'gpt-computer-agent[base]'\npip3 install 'gpt-computer-agent[api]'\n```\n\n```console\ncomputeragent --api\n```\n\n\n```python\nfrom gpt_computer_agent.remote import remote\n\noutput = remote.input(\"Hi, how are you today?\", screen=False, talk=False)\nprint(output)\n\nremote.just_screenshot()\n\nremote.talk(\"TTS test\")\n\n# Other Functionalities\nremote.reset_memory()\nremote.profile(\"default\")\n\nremote.enable_predefined_agents()\nremote.disable_predefined_agents()\n\nremote.enable_online_tools()\nremote.disable_online_tools()\n```\n\n\n\n\n\n\n<p align=\"center\">\n<br>\n <br>\n <br>\n <br>\n <br>\n</p>\n\n## Roadmap\n| Feature | Status | Target Release |\n|---------------------------------|--------------|----------------|\n| Clear Chat History | Completed | Q2 2024 |\n| Long Audios Support (Split 20mb) | Completed | Q2 2024 |\n| Text Inputs | Completed | Q2 2024 |\n| Just Text Mode (Mute Speech) | Completed | Q2 2024 |\n| Added profiles (Different Chats) | Completed | Q2 2024 |\n| More Feedback About Agent Status | Completed | Q2 2024 |\n| Local Model Vision and Text (With Ollama, and vision models) | Completed | Q2 2024 |\n| **Our Customizable Agent Infrastructure** | Completed | Q2 2024 |\n| Supporting Groq Models | Completed | Q2 2024 |\n| **Adding Custom Tools** | Completed | Q2 2024 |\n| Click on something on the screen (text and icon) | Completed | Q2 2024 |\n| New UI | Completed | Q2 2024 |\n| Native Applications, exe, dmg | Failed (Agentic Infra libraries not supported for now) | Q2 2024 |\n| **Collaborated Speaking Different Voice Models on long responses.** | Completed | Q2 2024 |\n| **Auto Stop Recording, when you complate talking** | Completed | Q2 2024 |\n| **Wakeup Word** | Completed | Q2 2024 |\n| **Continuously Conversations** | Completed | Q2 2024 |\n| **Adding more capability on device** | Planned | Q2 2024 |\n| DeepFace Integration (Facial Recognition) | Planned | Q2 2024 |\n\n\n\n\n\n\n\n## Capabilities\nAt this time we have many infrastructure elements. We just aim to provide whole things that already in ChatGPT app.\n\n| Capability | Status |\n|------------------------------------|----------------------------------|\n| **Screen Read** | OK |\n| **Click to and Text or Icon in the screen** | OK |\n| **Move to and Text or Icon in the screen** | OK |\n| **Typing Something** | OK |\n| **Pressing to Any Key** | OK |\n| **Scrolling** | OK |\n| **Microphone** | OK |\n| **System Audio** | OK |\n| **Memory** | OK |\n| **Open and Close App** | OK |\n| **Open a URL** | OK |\n| **Clipboard** | OK |\n| **Search Engines** | OK |\n| **Writing and running Python** | OK |\n| **Writing and running SH** | OK |\n| **Using your Telegram Account** | OK |\n| **Knowledge Management** | OK |\n| **[Add more tool](https://github.com/khulnasoft/gpt-computer-agent/blob/master/gpt_computer_agent/standard_tools.py)** | ? |\n\n### Predefined Agents\nIf you enable it your agent will work with these teams:\n\n| Team Name | Status |\n|------------------------------------|----------------------------------|\n| **search_on_internet_and_report_team** | OK |\n| **generate_code_with_aim_team_** | OK |\n| **[Add your own one](https://github.com/khulnasoft/gpt-computer-agent/blob/master/gpt_computer_agent/teams.py)** | ? |\n\n\n## Contributors\n\n<a href=\"https://github.com/khulnasoft/gpt-computer-agent/graphs/contributors\">\n <img src=\"https://contrib.rocks/image?repo=khulnasoft/gpt-computer-agent\" />\n</a>",
"bugtrack_url": null,
"license": "MIT",
"summary": "GPT",
"version": "1.0.2",
"project_urls": {
"Homepage": "https://github.com/khulnasoft/gpt-computer-agent"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "d47609284a5b878e63bcba6561736f672340db8dba8c94dc6fc2e11ae571b2f8",
"md5": "d2885a6bf77ef1dd4a413d696c69c3d6",
"sha256": "9461921f7931845c57530b0c70636af34183e6fd79ab2884a044db936154891e"
},
"downloads": -1,
"filename": "gpt_computer_agent-1.0.2.tar.gz",
"has_sig": false,
"md5_digest": "d2885a6bf77ef1dd4a413d696c69c3d6",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 1674875,
"upload_time": "2024-07-28T06:33:49",
"upload_time_iso_8601": "2024-07-28T06:33:49.063354Z",
"url": "https://files.pythonhosted.org/packages/d4/76/09284a5b878e63bcba6561736f672340db8dba8c94dc6fc2e11ae571b2f8/gpt_computer_agent-1.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-07-28 06:33:49",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "khulnasoft",
"github_project": "gpt-computer-agent",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "gpt-computer-agent"
}
JSON
