| Name | demiurg JSON |
| Version |
0.1.1
JSON |
| download |
| home_page | None |
| Summary | AI Agent Framework for building intelligent agents with multiple LLM providers |
| upload_time | 2025-07-14 18:45:04 |
| maintainer | None |
| docs_url | None |
| author | Demiurg AI |
| requires_python | <4.0,>=3.9 |
| license | Proprietary |
| keywords |
ai
agents
llm
openai
chatbot
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Demiurg
A flexible AI agent framework for building intelligent agents with support for multiple LLM providers.
## Features
- 🚀 Simple, minimal API for quick agent creation
- 🔌 Support for multiple LLM providers (OpenAI, Anthropic, Google, etc.)
- 📬 Built-in messaging system with conversation history
- 📁 File handling capabilities (images, audio, text)
- 🔧 Extensible tool system with Composio integration
- 🏗️ Production-ready with built-in queue management
- 🐳 Designed for both cloud and local container deployment
## Installation
```bash
pip install demiurg
```
## Quick Start
```python
from demiurg import Agent
# Create an agent with default configuration
agent = Agent()
# Or customize your agent
agent = Agent(
name="My Custom Agent",
model="gpt-4",
temperature=0.7,
provider="openai"
)
```
## Basic Usage
### Sending Messages
```python
from demiurg import send_text, send_file
# Send a text message
await send_text(conversation_id, "Hello from my agent!")
# Send a file
await send_file(conversation_id, "/path/to/file.png", caption="Check this out!")
```
### Getting Conversation History
```python
from demiurg import get_conversation_history
# Get formatted conversation history
messages = await get_conversation_history(
conversation_id,
limit=50,
provider="openai" # Format for specific LLM provider
)
```
### Custom Agent Implementation
```python
from demiurg import Agent
class MyAgent(Agent):
def __init__(self):
super().__init__(
name="Helpful Assistant",
model="gpt-4",
system_prompt="You are a helpful AI assistant."
)
async def process_message(self, message, provider="openai"):
# Add custom logic here
response = await super().process_message(message, provider)
return response
agent = MyAgent()
```
## Environment Variables
The framework uses environment variables for configuration:
- `DEMIURG_BACKEND_URL`: Backend API URL (default: `http://backend:3000`)
- `DEMIURG_AGENT_TOKEN`: Authentication token
- `DEMIURG_AGENT_ID`: Unique agent identifier
- `OPENAI_API_KEY`: OpenAI API key (for OpenAI provider)
- `COMPOSIO_API_KEY`: Composio API key (for tool integration)
## Provider Support
Currently supported:
- ✅ OpenAI (GPT-3.5, GPT-4, etc.)
Coming soon:
- 🚧 Anthropic (Claude)
- 🚧 Google (Gemini)
- 🚧 Cohere
- 🚧 Local models
## Development
For development access and contribution guidelines, please contact support@demiurg.ai.
## License
Copyright © 2024 Demiurg AI. All rights reserved.
This is proprietary software. See LICENSE file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "demiurg",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "ai, agents, llm, openai, chatbot",
"author": "Demiurg AI",
"author_email": "support@demiurg.ai",
"download_url": "https://files.pythonhosted.org/packages/ce/e0/cfb8f776ffb6fa605fdca62758d5bc3eb91314f427b9155ffaf5f7cfaf15/demiurg-0.1.1.tar.gz",
"platform": null,
"description": "# Demiurg\n\nA flexible AI agent framework for building intelligent agents with support for multiple LLM providers.\n\n## Features\n\n- \ud83d\ude80 Simple, minimal API for quick agent creation\n- \ud83d\udd0c Support for multiple LLM providers (OpenAI, Anthropic, Google, etc.)\n- \ud83d\udcec Built-in messaging system with conversation history\n- \ud83d\udcc1 File handling capabilities (images, audio, text)\n- \ud83d\udd27 Extensible tool system with Composio integration\n- \ud83c\udfd7\ufe0f Production-ready with built-in queue management\n- \ud83d\udc33 Designed for both cloud and local container deployment\n\n## Installation\n\n```bash\npip install demiurg\n```\n\n## Quick Start\n\n```python\nfrom demiurg import Agent\n\n# Create an agent with default configuration\nagent = Agent()\n\n# Or customize your agent\nagent = Agent(\n name=\"My Custom Agent\",\n model=\"gpt-4\",\n temperature=0.7,\n provider=\"openai\"\n)\n```\n\n## Basic Usage\n\n### Sending Messages\n\n```python\nfrom demiurg import send_text, send_file\n\n# Send a text message\nawait send_text(conversation_id, \"Hello from my agent!\")\n\n# Send a file\nawait send_file(conversation_id, \"/path/to/file.png\", caption=\"Check this out!\")\n```\n\n### Getting Conversation History\n\n```python\nfrom demiurg import get_conversation_history\n\n# Get formatted conversation history\nmessages = await get_conversation_history(\n conversation_id,\n limit=50,\n provider=\"openai\" # Format for specific LLM provider\n)\n```\n\n### Custom Agent Implementation\n\n```python\nfrom demiurg import Agent\n\nclass MyAgent(Agent):\n def __init__(self):\n super().__init__(\n name=\"Helpful Assistant\",\n model=\"gpt-4\",\n system_prompt=\"You are a helpful AI assistant.\"\n )\n \n async def process_message(self, message, provider=\"openai\"):\n # Add custom logic here\n response = await super().process_message(message, provider)\n return response\n\nagent = MyAgent()\n```\n\n## Environment Variables\n\nThe framework uses environment variables for configuration:\n\n- `DEMIURG_BACKEND_URL`: Backend API URL (default: `http://backend:3000`)\n- `DEMIURG_AGENT_TOKEN`: Authentication token\n- `DEMIURG_AGENT_ID`: Unique agent identifier\n- `OPENAI_API_KEY`: OpenAI API key (for OpenAI provider)\n- `COMPOSIO_API_KEY`: Composio API key (for tool integration)\n\n## Provider Support\n\nCurrently supported:\n- \u2705 OpenAI (GPT-3.5, GPT-4, etc.)\n\nComing soon:\n- \ud83d\udea7 Anthropic (Claude)\n- \ud83d\udea7 Google (Gemini)\n- \ud83d\udea7 Cohere\n- \ud83d\udea7 Local models\n\n## Development\n\nFor development access and contribution guidelines, please contact support@demiurg.ai.\n\n## License\n\nCopyright \u00a9 2024 Demiurg AI. All rights reserved.\n\nThis is proprietary software. See LICENSE file for details.\n",
"bugtrack_url": null,
"license": "Proprietary",
"summary": "AI Agent Framework for building intelligent agents with multiple LLM providers",
"version": "0.1.1",
"project_urls": {
"Documentation": "https://docs.demiurg.ai",
"Homepage": "https://demiurg.ai"
},
"split_keywords": [
"ai",
" agents",
" llm",
" openai",
" chatbot"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "1e8f635320df6d0d9f39af1d48e1bf9f18eedf1fff88613cdd8d4ed46a212a4c",
"md5": "82c76c464b8f7587bbe42ad97b1be1b8",
"sha256": "5a9491df8a41c88fe31cbed1c8c58654b3159b8eb971e7d36a21d32ee560af4f"
},
"downloads": -1,
"filename": "demiurg-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "82c76c464b8f7587bbe42ad97b1be1b8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 23300,
"upload_time": "2025-07-14T18:45:02",
"upload_time_iso_8601": "2025-07-14T18:45:02.944152Z",
"url": "https://files.pythonhosted.org/packages/1e/8f/635320df6d0d9f39af1d48e1bf9f18eedf1fff88613cdd8d4ed46a212a4c/demiurg-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "cee0cfb8f776ffb6fa605fdca62758d5bc3eb91314f427b9155ffaf5f7cfaf15",
"md5": "7dc6d7d0cf7d94f70704b0d4a909ea7c",
"sha256": "9cba086b08f987d8d6f054be3252178306281d336a49ff3c307670cb24bf5324"
},
"downloads": -1,
"filename": "demiurg-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "7dc6d7d0cf7d94f70704b0d4a909ea7c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 18711,
"upload_time": "2025-07-14T18:45:04",
"upload_time_iso_8601": "2025-07-14T18:45:04.209506Z",
"url": "https://files.pythonhosted.org/packages/ce/e0/cfb8f776ffb6fa605fdca62758d5bc3eb91314f427b9155ffaf5f7cfaf15/demiurg-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-14 18:45:04",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "demiurg"
}
