| Name | crewaimaster JSON |
| Version |
0.1.1
JSON |
| download |
| home_page | None |
| Summary | A Python package for building intelligent multi-agent systems using CrewAI |
| upload_time | 2025-07-30 10:34:22 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10 |
| license | MIT |
| keywords |
ai
multi-agent
crewai
automation
agents
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# CrewAIMaster
**A Python package for building intelligent multi-agent systems using CrewAI**
CrewAIMaster is an advanced framework that automatically generates, manages, and executes multi-agent crews based on natural language task descriptions. It provides a CLI interface and comprehensive backend system for creating intelligent AI agents with memory, tools, and safety guardrails.
## 📦 Installation
```bash
# install from PyPI (when available)
pip install crewaimaster
# Or Install from source (recommended for development)
git clone https://github.com/VishApp/crewaimaster
cd crewaimaster
python -m venv venv
source venv/bin/activate
pip install -e .
```
## 🏃 Quick Start
### Prerequisites
```bash
# Install Python 3.10+
python --version
# Configure your LLM provider (see supported providers)
crewaimaster providers
# Quick setup with OpenAI (most common)
crewaimaster providers --configure openai --api-key "your-openai-key" --model "gpt-4"
```
### 1. Create Your First Crew with AI Orchestration
```bash
# Create an intelligent crew using AI analysis
crewaimaster create "Write a comprehensive market analysis report for electric vehicles in 2024" --name electric_vehicles_market_analysis_crew
```
### 2. Execute the Crew
```bash
# Run the crew (requires configured LLM provider)
crewaimaster run electric_vehicles_market_analysis_crew
# With additional context:
crewaimaster run electric_vehicles_market_analysis_crew --input "Focus on Tesla, BMW, and Volkswagen specifically"
```
### 3. Alternative Execution (Direct Script)
Generated crews can also be executed directly using environment variables:
```bash
# Navigate to the generated crew directory
cd crews/electric_vehicles_market_analysis_crew
# Run using standard environment variables
export OPENAI_API_KEY="your-openai-key"
./run.sh "your input"
# Or run using CrewAIMaster-specific environment variables
export CREWAIMASTER_LLM_PROVIDER="openai"
export CREWAIMASTER_LLM_MODEL="gpt-4"
export CREWAIMASTER_LLM_API_KEY="your-openai-key"
export CREWAIMASTER_LLM_BASE_URL="https://api.openai.com/v1"
```
## 🔄 Development Workflow
### Typical CrewAIMaster Workflow
```mermaid
flowchart LR
A["`**1. Task Definition**
Natural Language Task`"] --> B["`**2. AI Analysis**
🤖 Task Complexity
🎯 Agent Requirements
🛠️ Tool Selection`"]
B --> C["`**3. Crew Creation**
👥 Agent Design
🔧 Tool Assignment
📋 Task Orchestration`"]
C --> D["`**4. Execution**
🏃 Multi-Agent Coordination
🔄 Real-time Processing
📊 Progress Monitoring`"]
D --> E["`**5. Results & Analytics**
📄 Output Generation
📈 Performance Metrics
💾 Persistent Storage`"]
E --> F["`**6. Optimization**
🔧 Crew Modification
⚡ Performance Tuning
📤 Export/Backup`"]
F --> G["`**7. Reuse & Scale**
🔄 Crew Reusability
📚 Knowledge Building
🚀 Production Deployment`"]
classDef stepStyle fill:#f9f9f9,stroke:#333,stroke-width:2px,color:#333
class A,B,C,D,E,F,G stepStyle
```
## 🏗️ Architecture
CrewAIMaster follows a clean, layered architecture designed for intelligent multi-agent system creation and execution:
```mermaid
flowchart TD
%% User Entry Point
User[👤 User Input<br/>Natural Language Task] --> CLI[🖥️ CLI Interface<br/>crewaimaster create/run/providers]
%% Configuration Layer
CLI --> Config[⚙️ Configuration<br/>config.yaml<br/>LLM Providers]
%% AI Orchestration Core
CLI --> MasterAgent[🧠 Master Agent<br/>Intelligent Orchestrator]
%% AI Analysis Pipeline
MasterAgent --> TaskAnalyzer[📋 Task Analyzer<br/>• Complexity Assessment<br/>• Requirements Extraction<br/>• Agent Planning]
TaskAnalyzer --> AgentDesigner[👥 Agent Designer<br/>• Role Definition<br/>• Tool Selection<br/>• Capability Mapping]
AgentDesigner --> CrewOrchestrator[🎭 Crew Orchestrator<br/>• Team Assembly<br/>• Process Selection<br/>• Workflow Design]
%% Core Generation Engine
CrewOrchestrator --> CrewDesigner[🔧 Crew Designer<br/>File-Based Generator]
Config --> CrewDesigner
CrewDesigner --> FileGen[📁 File Generator<br/>• Project Structure<br/>• Python Modules<br/>• YAML Configs]
%% Output Generation
FileGen --> GeneratedFiles{📄 Generated Crew Project}
%% Generated Project Structure
GeneratedFiles --> AgentYAML[agents.yaml<br/>Agent Definitions]
GeneratedFiles --> TaskYAML[tasks.yaml<br/>Task Specifications]
GeneratedFiles --> CrewPY[crew.py<br/>CrewAI Implementation]
GeneratedFiles --> MainPY[main.py<br/>Execution Entry Point]
%% Execution Runtime
MainPY --> CrewAI[🚀 CrewAI Runtime<br/>Multi-Agent Execution]
CrewAI --> AgentA[🤖 Agent A<br/>Specialized Role]
CrewAI --> AgentB[🤖 Agent B<br/>Specialized Role]
CrewAI --> AgentC[🤖 Agent C<br/>Specialized Role]
%% Tool Integration
AgentA --> Tools[🛠️ Tool Registry<br/>• Web Search<br/>• File Operations<br/>• Code Execution<br/>• Custom Tools]
AgentB --> Tools
AgentC --> Tools
%% LLM Integration
Config --> LLMProvider[🔗 LLM Provider<br/>• OpenAI<br/>• Anthropic<br/>• Google<br/>• Custom APIs]
LLMProvider --> AgentA
LLMProvider --> AgentB
LLMProvider --> AgentC
LLMProvider --> MasterAgent
%% Memory & Knowledge
CrewAI --> Memory[🧠 Memory System<br/>• Agent Memory<br/>• Shared Context<br/>• Knowledge Base]
%% Safety & Guardrails
Tools --> Guardrails[🛡️ Guardrails<br/>• Safety Checks<br/>• Content Filtering<br/>• Validation]
%% Final Output
CrewAI --> Results[📊 Results<br/>Task Completion<br/>Generated Content]
%% Styling
classDef userLayer fill:#e8f5e8,stroke:#1b5e20,stroke-width:3px,color:#000
classDef cliLayer fill:#e1f5fe,stroke:#01579b,stroke-width:2px,color:#000
classDef aiLayer fill:#f3e5f5,stroke:#4a148c,stroke-width:2px,color:#000
classDef coreLayer fill:#fff8e1,stroke:#ff8f00,stroke-width:2px,color:#000
classDef fileLayer fill:#fce4ec,stroke:#880e4f,stroke-width:2px,color:#000
classDef runtimeLayer fill:#fff3e0,stroke:#e65100,stroke-width:2px,color:#000
classDef toolLayer fill:#f1f8e9,stroke:#33691e,stroke-width:2px,color:#000
class User userLayer
class CLI,Config cliLayer
class MasterAgent,TaskAnalyzer,AgentDesigner,CrewOrchestrator aiLayer
class CrewDesigner,FileGen,LLMProvider coreLayer
class GeneratedFiles,AgentYAML,TaskYAML,CrewPY,MainPY fileLayer
class CrewAI,AgentA,AgentB,AgentC,Memory,Results runtimeLayer
class Tools,Guardrails toolLayer
```
### 🔄 Data Flow Explanation
1. **User Input**: Natural language task description via CLI
2. **AI Analysis**: Master Agent analyzes complexity and requirements
3. **Intelligent Design**: AI agents design optimal crew composition
4. **Code Generation**: Automated creation of CrewAI project files
5. **Execution**: Generated crew runs with real-time coordination
6. **Results**: Task completion with generated content and insights
### 🏛️ Architecture Overview
CrewAIMaster's architecture is designed for scalability, modularity, and intelligent automation:
#### 🎯 **User Interface Layer**
- **CLI Interface**: Rich terminal experience with typer and rich libraries
- **Command Processing**: Handles user commands and provides interactive feedback
- **Input Validation**: Ensures commands are properly formatted and validated
#### 🤖 **AI Orchestration Layer** (Core Innovation)
- **MasterAgentCrew**: Main orchestrator using AI agents for intelligent decision-making
- **TaskAnalyzerAgent**: Advanced NLP analysis of user tasks and requirements
- **AgentDesignerAgent**: Intelligent design of agents based on task requirements
- **CrewOrchestratorAgent**: Optimizes crew composition and execution strategies
#### ⚙️ **Core Processing Layer**
- **CrewDesigner**: Handles CrewAI integration and agent instantiation
- **TaskAnalyzer**: Legacy fallback for task analysis with pattern matching
#### 🛠️ **Tool Ecosystem**
- **Tool Registry**: Centralized management of all available tools
- **Available Tools**: Comprehensive library of built-in and custom tools
- **Guardrails**: Safety and validation systems for secure operation
#### 🔄 **Execution Engine**
- **CrewAI Engine**: Core execution engine for running multi-agent crews
- **Agent Memory**: Sophisticated memory management for agent learning and context
### 🔄 Data Flow
1. **User Input** → CLI processes commands and validates input
2. **AI Analysis** → MasterAgentCrew analyzes task using specialized AI agents
3. **Crew Creation** → CrewDesigner instantiates agents with appropriate tools
4. **Execution** → CrewAI Engine runs the crew with real-time monitoring
## 🛠️ Configuration
### LLM Provider Setup
CrewAIMaster uses a `.crewaimaster/config.yaml` configuration file for all settings. Environment variables are **no longer supported** - all configuration must be done via CLI commands or direct config file editing.
#### 📋 **View Available Providers**
```bash
# See all supported providers and configuration examples
crewaimaster providers
```
#### 🚀 **CLI Configuration (All Providers)**
Configure any supported provider using the CLI:
**OpenAI:**
```bash
crewaimaster providers --configure openai --api-key "your-openai-key" --model "gpt-4"
# Automatically sets base_url to https://api.openai.com/v1
```
**Anthropic:**
```bash
crewaimaster providers --configure anthropic --api-key "your-anthropic-key" --model "claude-3-sonnet-20240229"
# Automatically sets base_url to https://api.anthropic.com/v1
```
**Google:**
```bash
crewaimaster providers --configure google --api-key "your-google-key" --model "gemini-pro"
# Automatically sets base_url to https://generativelanguage.googleapis.com/v1beta
```
**DeepSeek:**
```bash
crewaimaster providers --configure deepseek --api-key "your-deepseek-key" --model "deepseek-chat"
# Automatically sets base_url to https://api.deepseek.com/v1
```
**Custom Provider:**
```bash
crewaimaster providers --configure custom --api-key "your-key" --base-url "https://api.example.com/v1" --model "gpt-4o-mini"
# Requires explicit base_url for custom endpoints
```
## 🤝 Contributing
We welcome contributions! Here's how to get started:
1. Fork the repository
2. Create a feature branch: `git checkout -b feature/amazing-feature`
3. Make your changes and add tests
4. Run tests: `pytest tests/`
5. Commit changes: `git commit -m 'Add amazing feature'`
6. Push to branch: `git push origin feature/amazing-feature`
7. Open a Pull Request
### Development Setup
```bash
# Clone and setup development environment
git clone https://github.com/VishApp/crewaimaster
cd crewaimaster
# Install development dependencies
pip install -e .
```
## 📄 License
CrewAIMaster is released under the MIT License. See [LICENSE](LICENSE) for details.
## 🙏 Acknowledgments
- [CrewAI](https://github.com/joaomdmoura/crewAI) - Core multi-agent framework
- [LangChain](https://github.com/langchain-ai/langchain) - LLM integration tools
- [Sentence Transformers](https://github.com/UKPLab/sentence-transformers) - Text embeddings
- [FAISS](https://github.com/facebookresearch/faiss) - Vector similarity search
## 🔗 Links
- [GitHub Repository](https://github.com/VishApp/crewaimaster)
- [PyPI Package](https://pypi.org/project/crewaimaster)
---
**Built with ❤️ for the AI community**
Raw data
{
"_id": null,
"home_page": null,
"name": "crewaimaster",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "ai, multi-agent, crewai, automation, agents",
"author": null,
"author_email": "Vishnu Prasad <vishnuprasadapp@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/20/fb/42d09ee2e5a35320bc005c791811f109c240ca02d14eb7f89c90fe69576a/crewaimaster-0.1.1.tar.gz",
"platform": null,
"description": "# CrewAIMaster\n\n**A Python package for building intelligent multi-agent systems using CrewAI**\n\nCrewAIMaster is an advanced framework that automatically generates, manages, and executes multi-agent crews based on natural language task descriptions. It provides a CLI interface and comprehensive backend system for creating intelligent AI agents with memory, tools, and safety guardrails.\n\n## \ud83d\udce6 Installation\n\n```bash\n# install from PyPI (when available)\npip install crewaimaster\n\n# Or Install from source (recommended for development)\ngit clone https://github.com/VishApp/crewaimaster\ncd crewaimaster\npython -m venv venv\nsource venv/bin/activate\npip install -e .\n```\n\n## \ud83c\udfc3 Quick Start\n\n### Prerequisites\n```bash\n# Install Python 3.10+\npython --version\n\n# Configure your LLM provider (see supported providers)\ncrewaimaster providers\n\n# Quick setup with OpenAI (most common)\ncrewaimaster providers --configure openai --api-key \"your-openai-key\" --model \"gpt-4\"\n```\n\n### 1. Create Your First Crew with AI Orchestration\n\n```bash\n# Create an intelligent crew using AI analysis\ncrewaimaster create \"Write a comprehensive market analysis report for electric vehicles in 2024\" --name electric_vehicles_market_analysis_crew\n```\n\n### 2. Execute the Crew\n\n```bash\n# Run the crew (requires configured LLM provider)\ncrewaimaster run electric_vehicles_market_analysis_crew\n\n# With additional context:\ncrewaimaster run electric_vehicles_market_analysis_crew --input \"Focus on Tesla, BMW, and Volkswagen specifically\"\n```\n\n### 3. Alternative Execution (Direct Script)\n\nGenerated crews can also be executed directly using environment variables:\n\n```bash\n# Navigate to the generated crew directory\ncd crews/electric_vehicles_market_analysis_crew\n\n# Run using standard environment variables\nexport OPENAI_API_KEY=\"your-openai-key\"\n./run.sh \"your input\"\n\n# Or run using CrewAIMaster-specific environment variables\nexport CREWAIMASTER_LLM_PROVIDER=\"openai\"\nexport CREWAIMASTER_LLM_MODEL=\"gpt-4\"\nexport CREWAIMASTER_LLM_API_KEY=\"your-openai-key\"\nexport CREWAIMASTER_LLM_BASE_URL=\"https://api.openai.com/v1\"\n```\n\n## \ud83d\udd04 Development Workflow\n\n### Typical CrewAIMaster Workflow\n\n```mermaid\nflowchart LR\n A[\"`**1. Task Definition**\n Natural Language Task`\"] --> B[\"`**2. AI Analysis**\n \ud83e\udd16 Task Complexity\n \ud83c\udfaf Agent Requirements\n \ud83d\udee0\ufe0f Tool Selection`\"]\n \n B --> C[\"`**3. Crew Creation**\n \ud83d\udc65 Agent Design\n \ud83d\udd27 Tool Assignment\n \ud83d\udccb Task Orchestration`\"]\n \n C --> D[\"`**4. Execution**\n \ud83c\udfc3 Multi-Agent Coordination\n \ud83d\udd04 Real-time Processing\n \ud83d\udcca Progress Monitoring`\"]\n \n D --> E[\"`**5. Results & Analytics**\n \ud83d\udcc4 Output Generation\n \ud83d\udcc8 Performance Metrics\n \ud83d\udcbe Persistent Storage`\"]\n \n E --> F[\"`**6. Optimization**\n \ud83d\udd27 Crew Modification\n \u26a1 Performance Tuning\n \ud83d\udce4 Export/Backup`\"]\n \n F --> G[\"`**7. Reuse & Scale**\n \ud83d\udd04 Crew Reusability\n \ud83d\udcda Knowledge Building\n \ud83d\ude80 Production Deployment`\"]\n\n classDef stepStyle fill:#f9f9f9,stroke:#333,stroke-width:2px,color:#333\n class A,B,C,D,E,F,G stepStyle\n```\n\n## \ud83c\udfd7\ufe0f Architecture\n\nCrewAIMaster follows a clean, layered architecture designed for intelligent multi-agent system creation and execution:\n\n```mermaid\nflowchart TD\n %% User Entry Point\n User[\ud83d\udc64 User Input<br/>Natural Language Task] --> CLI[\ud83d\udda5\ufe0f CLI Interface<br/>crewaimaster create/run/providers]\n \n %% Configuration Layer\n CLI --> Config[\u2699\ufe0f Configuration<br/>config.yaml<br/>LLM Providers]\n \n %% AI Orchestration Core\n CLI --> MasterAgent[\ud83e\udde0 Master Agent<br/>Intelligent Orchestrator]\n \n %% AI Analysis Pipeline\n MasterAgent --> TaskAnalyzer[\ud83d\udccb Task Analyzer<br/>\u2022 Complexity Assessment<br/>\u2022 Requirements Extraction<br/>\u2022 Agent Planning]\n \n TaskAnalyzer --> AgentDesigner[\ud83d\udc65 Agent Designer<br/>\u2022 Role Definition<br/>\u2022 Tool Selection<br/>\u2022 Capability Mapping]\n \n AgentDesigner --> CrewOrchestrator[\ud83c\udfad Crew Orchestrator<br/>\u2022 Team Assembly<br/>\u2022 Process Selection<br/>\u2022 Workflow Design]\n \n %% Core Generation Engine\n CrewOrchestrator --> CrewDesigner[\ud83d\udd27 Crew Designer<br/>File-Based Generator]\n Config --> CrewDesigner\n \n CrewDesigner --> FileGen[\ud83d\udcc1 File Generator<br/>\u2022 Project Structure<br/>\u2022 Python Modules<br/>\u2022 YAML Configs]\n \n %% Output Generation\n FileGen --> GeneratedFiles{\ud83d\udcc4 Generated Crew Project}\n \n %% Generated Project Structure\n GeneratedFiles --> AgentYAML[agents.yaml<br/>Agent Definitions]\n GeneratedFiles --> TaskYAML[tasks.yaml<br/>Task Specifications]\n GeneratedFiles --> CrewPY[crew.py<br/>CrewAI Implementation]\n GeneratedFiles --> MainPY[main.py<br/>Execution Entry Point]\n \n %% Execution Runtime\n MainPY --> CrewAI[\ud83d\ude80 CrewAI Runtime<br/>Multi-Agent Execution]\n \n CrewAI --> AgentA[\ud83e\udd16 Agent A<br/>Specialized Role]\n CrewAI --> AgentB[\ud83e\udd16 Agent B<br/>Specialized Role]\n CrewAI --> AgentC[\ud83e\udd16 Agent C<br/>Specialized Role]\n \n %% Tool Integration\n AgentA --> Tools[\ud83d\udee0\ufe0f Tool Registry<br/>\u2022 Web Search<br/>\u2022 File Operations<br/>\u2022 Code Execution<br/>\u2022 Custom Tools]\n AgentB --> Tools\n AgentC --> Tools\n \n %% LLM Integration\n Config --> LLMProvider[\ud83d\udd17 LLM Provider<br/>\u2022 OpenAI<br/>\u2022 Anthropic<br/>\u2022 Google<br/>\u2022 Custom APIs]\n LLMProvider --> AgentA\n LLMProvider --> AgentB\n LLMProvider --> AgentC\n LLMProvider --> MasterAgent\n \n %% Memory & Knowledge\n CrewAI --> Memory[\ud83e\udde0 Memory System<br/>\u2022 Agent Memory<br/>\u2022 Shared Context<br/>\u2022 Knowledge Base]\n \n %% Safety & Guardrails\n Tools --> Guardrails[\ud83d\udee1\ufe0f Guardrails<br/>\u2022 Safety Checks<br/>\u2022 Content Filtering<br/>\u2022 Validation]\n \n %% Final Output\n CrewAI --> Results[\ud83d\udcca Results<br/>Task Completion<br/>Generated Content]\n \n %% Styling\n classDef userLayer fill:#e8f5e8,stroke:#1b5e20,stroke-width:3px,color:#000\n classDef cliLayer fill:#e1f5fe,stroke:#01579b,stroke-width:2px,color:#000\n classDef aiLayer fill:#f3e5f5,stroke:#4a148c,stroke-width:2px,color:#000\n classDef coreLayer fill:#fff8e1,stroke:#ff8f00,stroke-width:2px,color:#000\n classDef fileLayer fill:#fce4ec,stroke:#880e4f,stroke-width:2px,color:#000\n classDef runtimeLayer fill:#fff3e0,stroke:#e65100,stroke-width:2px,color:#000\n classDef toolLayer fill:#f1f8e9,stroke:#33691e,stroke-width:2px,color:#000\n \n class User userLayer\n class CLI,Config cliLayer\n class MasterAgent,TaskAnalyzer,AgentDesigner,CrewOrchestrator aiLayer\n class CrewDesigner,FileGen,LLMProvider coreLayer\n class GeneratedFiles,AgentYAML,TaskYAML,CrewPY,MainPY fileLayer\n class CrewAI,AgentA,AgentB,AgentC,Memory,Results runtimeLayer\n class Tools,Guardrails toolLayer\n```\n\n### \ud83d\udd04 Data Flow Explanation\n\n1. **User Input**: Natural language task description via CLI\n2. **AI Analysis**: Master Agent analyzes complexity and requirements\n3. **Intelligent Design**: AI agents design optimal crew composition\n4. **Code Generation**: Automated creation of CrewAI project files\n5. **Execution**: Generated crew runs with real-time coordination\n6. **Results**: Task completion with generated content and insights\n\n### \ud83c\udfdb\ufe0f Architecture Overview\n\nCrewAIMaster's architecture is designed for scalability, modularity, and intelligent automation:\n\n#### \ud83c\udfaf **User Interface Layer**\n- **CLI Interface**: Rich terminal experience with typer and rich libraries\n- **Command Processing**: Handles user commands and provides interactive feedback\n- **Input Validation**: Ensures commands are properly formatted and validated\n\n#### \ud83e\udd16 **AI Orchestration Layer** (Core Innovation)\n- **MasterAgentCrew**: Main orchestrator using AI agents for intelligent decision-making\n- **TaskAnalyzerAgent**: Advanced NLP analysis of user tasks and requirements\n- **AgentDesignerAgent**: Intelligent design of agents based on task requirements\n- **CrewOrchestratorAgent**: Optimizes crew composition and execution strategies\n\n#### \u2699\ufe0f **Core Processing Layer**\n- **CrewDesigner**: Handles CrewAI integration and agent instantiation\n- **TaskAnalyzer**: Legacy fallback for task analysis with pattern matching\n\n#### \ud83d\udee0\ufe0f **Tool Ecosystem**\n- **Tool Registry**: Centralized management of all available tools\n- **Available Tools**: Comprehensive library of built-in and custom tools\n- **Guardrails**: Safety and validation systems for secure operation\n\n#### \ud83d\udd04 **Execution Engine**\n- **CrewAI Engine**: Core execution engine for running multi-agent crews\n- **Agent Memory**: Sophisticated memory management for agent learning and context\n\n### \ud83d\udd04 Data Flow\n\n1. **User Input** \u2192 CLI processes commands and validates input\n2. **AI Analysis** \u2192 MasterAgentCrew analyzes task using specialized AI agents\n3. **Crew Creation** \u2192 CrewDesigner instantiates agents with appropriate tools\n4. **Execution** \u2192 CrewAI Engine runs the crew with real-time monitoring\n\n## \ud83d\udee0\ufe0f Configuration\n\n### LLM Provider Setup\n\nCrewAIMaster uses a `.crewaimaster/config.yaml` configuration file for all settings. Environment variables are **no longer supported** - all configuration must be done via CLI commands or direct config file editing.\n\n#### \ud83d\udccb **View Available Providers**\n```bash\n# See all supported providers and configuration examples\ncrewaimaster providers\n```\n\n#### \ud83d\ude80 **CLI Configuration (All Providers)**\n\nConfigure any supported provider using the CLI:\n\n**OpenAI:**\n```bash\ncrewaimaster providers --configure openai --api-key \"your-openai-key\" --model \"gpt-4\"\n# Automatically sets base_url to https://api.openai.com/v1\n```\n\n**Anthropic:**\n```bash\ncrewaimaster providers --configure anthropic --api-key \"your-anthropic-key\" --model \"claude-3-sonnet-20240229\"\n# Automatically sets base_url to https://api.anthropic.com/v1\n```\n\n**Google:**\n```bash\ncrewaimaster providers --configure google --api-key \"your-google-key\" --model \"gemini-pro\"\n# Automatically sets base_url to https://generativelanguage.googleapis.com/v1beta\n```\n\n**DeepSeek:**\n```bash\ncrewaimaster providers --configure deepseek --api-key \"your-deepseek-key\" --model \"deepseek-chat\"\n# Automatically sets base_url to https://api.deepseek.com/v1\n```\n\n**Custom Provider:**\n```bash\ncrewaimaster providers --configure custom --api-key \"your-key\" --base-url \"https://api.example.com/v1\" --model \"gpt-4o-mini\"\n# Requires explicit base_url for custom endpoints\n```\n\n## \ud83e\udd1d Contributing\n\nWe welcome contributions! Here's how to get started:\n\n1. Fork the repository\n2. Create a feature branch: `git checkout -b feature/amazing-feature`\n3. Make your changes and add tests\n4. Run tests: `pytest tests/`\n5. Commit changes: `git commit -m 'Add amazing feature'`\n6. Push to branch: `git push origin feature/amazing-feature`\n7. Open a Pull Request\n\n### Development Setup\n\n```bash\n# Clone and setup development environment\ngit clone https://github.com/VishApp/crewaimaster\ncd crewaimaster\n\n# Install development dependencies\npip install -e .\n```\n\n## \ud83d\udcc4 License\n\nCrewAIMaster is released under the MIT License. See [LICENSE](LICENSE) for details.\n\n## \ud83d\ude4f Acknowledgments\n\n- [CrewAI](https://github.com/joaomdmoura/crewAI) - Core multi-agent framework\n- [LangChain](https://github.com/langchain-ai/langchain) - LLM integration tools \n- [Sentence Transformers](https://github.com/UKPLab/sentence-transformers) - Text embeddings\n- [FAISS](https://github.com/facebookresearch/faiss) - Vector similarity search\n\n## \ud83d\udd17 Links\n\n- [GitHub Repository](https://github.com/VishApp/crewaimaster)\n- [PyPI Package](https://pypi.org/project/crewaimaster)\n---\n\n**Built with \u2764\ufe0f for the AI community**\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A Python package for building intelligent multi-agent systems using CrewAI",
"version": "0.1.1",
"project_urls": {
"Changelog": "https://github.com/VishApp/crewaimaster/blob/main/CHANGELOG.md",
"Documentation": "https://github.com/VishApp/crewaimaster#readme",
"Homepage": "https://github.com/VishApp/crewaimaster",
"Issues": "https://github.com/VishApp/crewaimaster/issues",
"Repository": "https://github.com/VishApp/crewaimaster"
},
"split_keywords": [
"ai",
" multi-agent",
" crewai",
" automation",
" agents"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "a73d7c8c977e22d7035f000de4d6f68c84cfcc809b73e814d13984beb58d2f83",
"md5": "7824b3676ed4e5a6742bfd90294e9fa5",
"sha256": "8bc0781a07f050172e29c9d00adbe70790e947d27481647633f39d837ba41216"
},
"downloads": -1,
"filename": "crewaimaster-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "7824b3676ed4e5a6742bfd90294e9fa5",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 122984,
"upload_time": "2025-07-30T10:34:19",
"upload_time_iso_8601": "2025-07-30T10:34:19.750182Z",
"url": "https://files.pythonhosted.org/packages/a7/3d/7c8c977e22d7035f000de4d6f68c84cfcc809b73e814d13984beb58d2f83/crewaimaster-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "20fb42d09ee2e5a35320bc005c791811f109c240ca02d14eb7f89c90fe69576a",
"md5": "c2da278aad3e2174483564097948f9da",
"sha256": "b7a3a8cd09e6013097ed1e2681fb69627b2e616dee9e7cf02bba583b4843fd36"
},
"downloads": -1,
"filename": "crewaimaster-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "c2da278aad3e2174483564097948f9da",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 376032,
"upload_time": "2025-07-30T10:34:22",
"upload_time_iso_8601": "2025-07-30T10:34:22.417948Z",
"url": "https://files.pythonhosted.org/packages/20/fb/42d09ee2e5a35320bc005c791811f109c240ca02d14eb7f89c90fe69576a/crewaimaster-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-30 10:34:22",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "VishApp",
"github_project": "crewaimaster",
"github_not_found": true,
"lcname": "crewaimaster"
}
