# ðĶ Dinnovos Agent
**Agile AI Agents with Multi-LLM Support**
Dinnovos Agent is a lightweight Python framework for building AI agents that can seamlessly switch between different Large Language Models (OpenAI, Anthropic, Google).
## Features
- ð **Multi-LLM Support**: OpenAI (GPT), Anthropic (Claude), Google (Gemini)
- ðŊ **Simple API**: Intuitive interface for building conversational agents
- ðū **Context Memory**: Automatic conversation history management
- ð **Extensible**: Easy to add new LLM providers
- ðŠķ **Lightweight**: Minimal dependencies, maximum flexibility
## Installation
### Basic Installation
```bash
pip install dinnovos-agent
```
### With specific LLM support
```bash
# For OpenAI only
pip install dinnovos-agent[openai]
# For Anthropic only
pip install dinnovos-agent[anthropic]
# For Google only
pip install dinnovos-agent[google]
# For all LLMs
pip install dinnovos-agent[all]
```
### For development
```bash
pip install dinnovos-agent[dev]
```
## Quick Start
```python
from dinnovos import Agent, OpenAILLM
# Create an LLM interface
llm = OpenAILLM(api_key="your-api-key", model="gpt-4")
# Create an Agent
agent = Agent(
llm=llm,
system_prompt="You are a helpful assistant."
)
# Chat with your agent
response = agent.chat("Hello! What can you do?")
print(response)
```
## Examples
### Using Different LLMs
```python
from dinnovos import Agent, OpenAILLM, AnthropicLLM, GoogleLLM
# OpenAI
openai_llm = OpenAILLM(api_key="sk-...", model="gpt-4")
agent_gpt = Agent(llm=openai_llm)
# Anthropic Claude
anthropic_llm = AnthropicLLM(api_key="sk-ant-...", model="claude-sonnet-4-5-20250929")
agent_claude = Agent(llm=anthropic_llm)
# Google Gemini
google_llm = GoogleLLM(api_key="...", model="gemini-1.5-pro")
agent_gemini = Agent(llm=google_llm)
```
### Custom System Prompt
```python
agent = Agent(
llm=llm,
system_prompt="You are an expert Python programmer.",
max_history=20 # Keep last 20 messages
)
response = agent.chat("Explain decorators in Python")
```
### Managing Conversation
```python
# Get conversation history
history = agent.get_history()
# Reset conversation
agent.reset()
# Change system prompt
agent.set_system_prompt("You are now a math tutor.")
```
## API Reference
### Agent Class
```python
Agent(llm: BaseLLM, system_prompt: str = None, max_history: int = 10)
```
**Methods:**
- `chat(message: str, temperature: float = 0.7) -> str`: Send a message and get response
- `reset()`: Clear conversation history
- `get_history() -> List[Dict]`: Get conversation history
- `set_system_prompt(prompt: str)`: Change system prompt and reset
### LLM Interfaces
```python
OpenAILLM(api_key: str, model: str = "gpt-4")
AnthropicLLM(api_key: str, model: str = "claude-sonnet-4-5-20250929")
GoogleLLM(api_key: str, model: str = "gemini-1.5-pro")
```
## Requirements
- Python 3.8+
- Optional: `openai`, `anthropic`, `google-generativeai` (based on which LLMs you use)
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
## License
MIT License - see LICENSE file for details
## Links
- [Documentation](https://github.com/yourusername/dinnovos-agent/docs)
- [Issue Tracker](https://github.com/yourusername/dinnovos-agent/issues)
- [Source Code](https://github.com/yourusername/dinnovos-agent)
## Support
If you encounter any issues or have questions, please file an issue on GitHub.
'''
Raw data
{
"_id": null,
"home_page": "https://github.com/dinnovos/dinnovos-agent",
"name": "dinnovos-agent",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "ai, agents, llm, openai, anthropic, google, gemini, dinnovos",
"author": "Dinnovos",
"author_email": "Dinnovos Agent <development.dinnovos@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/87/04/ceedd4d77eb318989f6159652aede92cc414e1c4c4dee8683e0cdc24904e/dinnovos_agent-0.6.0.tar.gz",
"platform": null,
"description": "# \ud83e\udd96 Dinnovos Agent\r\n\r\n**Agile AI Agents with Multi-LLM Support**\r\n\r\nDinnovos Agent is a lightweight Python framework for building AI agents that can seamlessly switch between different Large Language Models (OpenAI, Anthropic, Google).\r\n\r\n## Features\r\n\r\n- \ud83d\udd04 **Multi-LLM Support**: OpenAI (GPT), Anthropic (Claude), Google (Gemini)\r\n- \ud83c\udfaf **Simple API**: Intuitive interface for building conversational agents\r\n- \ud83d\udcbe **Context Memory**: Automatic conversation history management\r\n- \ud83d\udd0c **Extensible**: Easy to add new LLM providers\r\n- \ud83e\udeb6 **Lightweight**: Minimal dependencies, maximum flexibility\r\n\r\n## Installation\r\n\r\n### Basic Installation\r\n```bash\r\npip install dinnovos-agent\r\n```\r\n\r\n### With specific LLM support\r\n```bash\r\n# For OpenAI only\r\npip install dinnovos-agent[openai]\r\n\r\n# For Anthropic only\r\npip install dinnovos-agent[anthropic]\r\n\r\n# For Google only\r\npip install dinnovos-agent[google]\r\n\r\n# For all LLMs\r\npip install dinnovos-agent[all]\r\n```\r\n\r\n### For development\r\n```bash\r\npip install dinnovos-agent[dev]\r\n```\r\n\r\n## Quick Start\r\n\r\n```python\r\nfrom dinnovos import Agent, OpenAILLM\r\n\r\n# Create an LLM interface\r\nllm = OpenAILLM(api_key=\"your-api-key\", model=\"gpt-4\")\r\n\r\n# Create an Agent\r\nagent = Agent(\r\n llm=llm,\r\n system_prompt=\"You are a helpful assistant.\"\r\n)\r\n\r\n# Chat with your agent\r\nresponse = agent.chat(\"Hello! What can you do?\")\r\nprint(response)\r\n```\r\n\r\n## Examples\r\n\r\n### Using Different LLMs\r\n\r\n```python\r\nfrom dinnovos import Agent, OpenAILLM, AnthropicLLM, GoogleLLM\r\n\r\n# OpenAI\r\nopenai_llm = OpenAILLM(api_key=\"sk-...\", model=\"gpt-4\")\r\nagent_gpt = Agent(llm=openai_llm)\r\n\r\n# Anthropic Claude\r\nanthropic_llm = AnthropicLLM(api_key=\"sk-ant-...\", model=\"claude-sonnet-4-5-20250929\")\r\nagent_claude = Agent(llm=anthropic_llm)\r\n\r\n# Google Gemini\r\ngoogle_llm = GoogleLLM(api_key=\"...\", model=\"gemini-1.5-pro\")\r\nagent_gemini = Agent(llm=google_llm)\r\n```\r\n\r\n### Custom System Prompt\r\n\r\n```python\r\nagent = Agent(\r\n llm=llm,\r\n system_prompt=\"You are an expert Python programmer.\",\r\n max_history=20 # Keep last 20 messages\r\n)\r\n\r\nresponse = agent.chat(\"Explain decorators in Python\")\r\n```\r\n\r\n### Managing Conversation\r\n\r\n```python\r\n# Get conversation history\r\nhistory = agent.get_history()\r\n\r\n# Reset conversation\r\nagent.reset()\r\n\r\n# Change system prompt\r\nagent.set_system_prompt(\"You are now a math tutor.\")\r\n```\r\n\r\n## API Reference\r\n\r\n### Agent Class\r\n\r\n```python\r\nAgent(llm: BaseLLM, system_prompt: str = None, max_history: int = 10)\r\n```\r\n\r\n**Methods:**\r\n- `chat(message: str, temperature: float = 0.7) -> str`: Send a message and get response\r\n- `reset()`: Clear conversation history\r\n- `get_history() -> List[Dict]`: Get conversation history\r\n- `set_system_prompt(prompt: str)`: Change system prompt and reset\r\n\r\n### LLM Interfaces\r\n\r\n```python\r\nOpenAILLM(api_key: str, model: str = \"gpt-4\")\r\nAnthropicLLM(api_key: str, model: str = \"claude-sonnet-4-5-20250929\")\r\nGoogleLLM(api_key: str, model: str = \"gemini-1.5-pro\")\r\n```\r\n\r\n## Requirements\r\n\r\n- Python 3.8+\r\n- Optional: `openai`, `anthropic`, `google-generativeai` (based on which LLMs you use)\r\n\r\n## Contributing\r\n\r\nContributions are welcome! Please feel free to submit a Pull Request.\r\n\r\n## License\r\n\r\nMIT License - see LICENSE file for details\r\n\r\n## Links\r\n\r\n- [Documentation](https://github.com/yourusername/dinnovos-agent/docs)\r\n- [Issue Tracker](https://github.com/yourusername/dinnovos-agent/issues)\r\n- [Source Code](https://github.com/yourusername/dinnovos-agent)\r\n\r\n## Support\r\n\r\nIf you encounter any issues or have questions, please file an issue on GitHub.\r\n'''\r\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Dinnovos Agent - Agile AI Agents with multi-LLM support",
"version": "0.6.0",
"project_urls": {
"Bug Tracker": "https://github.com/dinnovos/dinnovos-agent/issues",
"Documentation": "https://github.com/dinnovos/dinnovos-agent/docs",
"Homepage": "https://github.com/dinnovos/dinnovos-agent",
"Repository": "https://github.com/dinnovos/dinnovos-agent"
},
"split_keywords": [
"ai",
" agents",
" llm",
" openai",
" anthropic",
" google",
" gemini",
" dinnovos"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "b3747d836e9410b6fc8d770c76bb8f68119fb787c4bb05c793b4ef9d2455ce78",
"md5": "40381f6ad17f1b31fa279e2c2104d54b",
"sha256": "78f931f649d2cfbdc676cd10f1c2621b41488db8459822af041c3f785e3f9780"
},
"downloads": -1,
"filename": "dinnovos_agent-0.6.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "40381f6ad17f1b31fa279e2c2104d54b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 42932,
"upload_time": "2025-10-30T05:05:47",
"upload_time_iso_8601": "2025-10-30T05:05:47.084769Z",
"url": "https://files.pythonhosted.org/packages/b3/74/7d836e9410b6fc8d770c76bb8f68119fb787c4bb05c793b4ef9d2455ce78/dinnovos_agent-0.6.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "8704ceedd4d77eb318989f6159652aede92cc414e1c4c4dee8683e0cdc24904e",
"md5": "5336e7204260b3d5b0aa3fb47fdf3d70",
"sha256": "270df5216439dbe8082136b8e1c961e74e359e0e6b6218a31b97c8ce8040e2fb"
},
"downloads": -1,
"filename": "dinnovos_agent-0.6.0.tar.gz",
"has_sig": false,
"md5_digest": "5336e7204260b3d5b0aa3fb47fdf3d70",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 39648,
"upload_time": "2025-10-30T05:05:48",
"upload_time_iso_8601": "2025-10-30T05:05:48.265930Z",
"url": "https://files.pythonhosted.org/packages/87/04/ceedd4d77eb318989f6159652aede92cc414e1c4c4dee8683e0cdc24904e/dinnovos_agent-0.6.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-30 05:05:48",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "dinnovos",
"github_project": "dinnovos-agent",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "dinnovos-agent"
}
JSON
