# JayGoga-Orchestra 🎼 - Advanced AI Agent Orchestration Framework
**JayGoga-Orchestra** is a powerful AI agent orchestration framework for intelligent automation. It provides seamless coordination of AI agents for complex workflows and enterprise-grade automation solutions.
## 🌟 Features
- **🎭 Dual Architecture**: Choose between Classical (v1) and Modern (v2) orchestration patterns
- **🔮 Intelligent Orchestration**: Advanced agent coordination and workflow management
- **⚡ High Performance**: Optimized for speed and scalability
- **🛡️ Enterprise Ready**: Built for production environments
- **🎨 Flexible Design**: Adapt to any AI workflow requirement
- **📚 Rich Documentation**: Comprehensive guides and examples
- **🔄 Seamless Integration**: Easy integration with existing systems
## 🚀 Installation
```bash
pip install jaygoga-orchestra
```
## 🎯 Quick Start
### 🏛️ Classical Orchestration (v1) - Structured & Reliable
Perfect for **structured workflows**, **enterprise environments**, and **predictable processes**.
```python
from jaygoga_orchestra.v1 import Agent, Task, Squad, Process
# Create specialized agents
analyst = Agent(
role="Senior Data Analyst",
goal="Extract meaningful insights from complex datasets",
backstory="You are a seasoned analyst with 10+ years of experience in data science and business intelligence."
)
researcher = Agent(
role="Market Researcher",
goal="Gather comprehensive market intelligence",
backstory="You specialize in market analysis and competitive intelligence gathering."
)
# Define specific tasks
analysis_task = Task(
description="Analyze Q4 sales data and identify key trends, patterns, and anomalies",
agent=analyst,
expected_output="Detailed analysis report with visualizations and recommendations"
)
research_task = Task(
description="Research market conditions and competitor performance in Q4",
agent=researcher,
expected_output="Market intelligence report with competitor analysis"
)
# Create coordinated squad
intelligence_squad = Squad(
agents=[analyst, researcher],
tasks=[analysis_task, research_task],
process=Process.sequential,
verbose=True
)
# Execute the orchestrated workflow
results = intelligence_squad.execute()
print(f"Analysis Complete: {results}")
```
### 🚀 Modern Orchestration (v2) - Dynamic & Intelligent
Ideal for **adaptive workflows**, **AI-driven decisions**, and **dynamic environments**.
```python
from jaygoga_orchestra.v2 import Agent, Team, Workflow
# Create intelligent agents with advanced capabilities
data_agent = Agent(
name="JayGoga_DataSage",
description="Advanced AI agent specialized in data analysis with deep learning capabilities",
instructions="You are an expert data scientist with the ability to adapt your analysis approach based on data characteristics",
model="gpt-4",
tools=["python_interpreter", "data_visualization", "statistical_analysis"]
)
insight_agent = Agent(
name="JayGoga_InsightMaster",
description="Strategic insight generator with business acumen",
instructions="Transform data findings into actionable business strategies and recommendations",
model="claude-3-sonnet",
tools=["business_analysis", "report_generation", "strategic_planning"]
)
# Create dynamic team with shared context
intelligence_team = Team(
agents=[data_agent, insight_agent],
name="Strategic Intelligence Unit",
description="Elite team for comprehensive business intelligence",
shared_memory=True,
collaboration_mode="adaptive"
)
# Execute with dynamic adaptation
results = intelligence_team.run(
task="Analyze our Q4 performance data and provide strategic recommendations for Q1",
context={"data_source": "sales_db", "priority": "high", "deadline": "2024-01-15"}
)
print(f"Strategic Analysis: {results.summary}")
print(f"Key Insights: {results.insights}")
print(f"Recommendations: {results.recommendations}")
```
## 🏗️ Architecture Comparison
| Feature | Classical v1 | Modern v2 | Best For |
|---------|-------------|-----------|----------|
| **Structure** | Hierarchical, Role-based | Dynamic, Capability-based | v1: Enterprise, v2: Startups |
| **Execution** | Sequential/Parallel | Adaptive Intelligence | v1: Predictable, v2: Creative |
| **Memory** | Task-scoped | Shared Context | v1: Privacy, v2: Collaboration |
| **Scalability** | Linear | Exponential | v1: Controlled, v2: Rapid growth |
| **Learning** | Rule-based | AI-driven | v1: Compliance, v2: Innovation |
| **Complexity** | Structured | Self-organizing | v1: Governance, v2: Agility |
### 🎭 When to Choose Which Version
**Choose Classical v1 when:**
- 🏢 Enterprise environment with strict governance
- 📋 Well-defined, repeatable processes
- 🔒 Compliance and audit requirements
- 👥 Large teams with clear role definitions
- 📊 Predictable workflows and outcomes
**Choose Modern v2 when:**
- 🚀 Startup or innovation-focused environment
- 🧠 AI-driven decision making required
- 🔄 Dynamic, adaptive workflows needed
- 🌐 Collaborative, context-sharing scenarios
- 🎯 Creative problem-solving and exploration
## 📁 Project Structure
```
jaygoga_orchestra/
├── __init__.py # Main orchestration entry point
├── v1/ # Classical Orchestration (Structured)
│ ├── __init__.py # Agent, Task, Squad, Process
│ ├── agent.py # Role-based agents
│ ├── team.py # Structured squads
│ ├── task.py # Defined tasks
│ ├── process.py # Execution processes
│ ├── cli/ # Command-line tools
│ ├── tools/ # Agent tools and utilities
│ └── ...
├── v2/ # Modern Orchestration (Intelligent)
│ ├── __init__.py # Agent, Team, Workflow
│ ├── agent/ # Intelligent agents
│ ├── team/ # Collaborative teams
│ ├── workflow/ # Dynamic workflows
│ ├── memory/ # Shared context
│ ├── reasoning/ # AI reasoning
│ └── ...
└── legacy/ # 🧪 Beta Features (Experimental)
├── README_BETA.md # Beta documentation
└── experimental/ # Cutting-edge features
```
## 🧪 Beta Features (Legacy/Experimental)
Our **legacy** directory contains experimental and beta features that showcase the future of AI orchestration:
```python
# 🚧 Beta Features - Available Soon!
from jaygoga_orchestra.legacy import ExperimentalAgent, AdvancedWorkflow
# Cutting-edge features in development
beta_agent = ExperimentalAgent(
name="Krishna_BetaAgent",
capabilities=["quantum_reasoning", "multi_dimensional_analysis"],
status="beta"
)
# Advanced experimental workflows
experimental_flow = AdvancedWorkflow(
name="Future_Intelligence",
description="Next-generation AI orchestration patterns",
beta_features=["auto_optimization", "self_healing", "predictive_scaling"]
)
```
**Beta Features Include:**
- 🔮 **Quantum Reasoning**: Advanced decision-making algorithms
- 🌊 **Self-Healing Workflows**: Automatic error recovery and optimization
- 🎯 **Predictive Scaling**: AI-driven resource management
- 🧠 **Neural Orchestration**: Brain-inspired coordination patterns
- ⚡ **Lightning Execution**: Ultra-fast processing capabilities
*These features are experimental and will be integrated into v3 in future releases.*
## 🔄 Migration & Integration
### 🎯 Getting Started with Govinda
```python
# Start with Classical v1 for structured workflows
from jaygoga_orchestra.v1 import Agent, Task, Squad, Process
# Upgrade to Modern v2 for intelligent orchestration
from jaygoga_orchestra.v2 import Agent, Team, Workflow
# Mix and match as needed
from jaygoga_orchestra.v1 import Task
from jaygoga_orchestra.v2 import Agent, Workflow
```
### 🚀 Advanced Usage Examples
**Multi-Agent Research Pipeline (v1):**
```python
from jaygoga_orchestra.v1 import Agent, Task, Squad, Process
# Create research squad
researcher = Agent(role="Research Specialist", goal="Gather comprehensive data")
analyst = Agent(role="Data Analyst", goal="Analyze and synthesize findings")
writer = Agent(role="Technical Writer", goal="Create detailed reports")
# Define research pipeline
tasks = [
Task(description="Research AI trends in 2024", agent=researcher),
Task(description="Analyze research findings", agent=analyst),
Task(description="Write comprehensive report", agent=writer)
]
research_squad = Squad(agents=[researcher, analyst, writer], tasks=tasks)
report = research_squad.execute()
```
**Intelligent Content Creation (v2):**
```python
from jaygoga_orchestra.v2 import Agent, Team, Workflow
# Create intelligent content team
content_team = Team([
Agent(name="ContentStrategist", model="gpt-4"),
Agent(name="CreativeWriter", model="claude-3"),
Agent(name="SEOOptimizer", model="gpt-3.5-turbo")
])
result = content_team.run("Create a viral blog post about AI trends")
```
## 🎨 Why JayGoga-Orchestra?
**JayGoga-Orchestra** represents the perfect harmony of AI agents working together like a well-conducted orchestra. Each agent plays its part while contributing to a greater symphony of intelligent automation.
**Core Principles:**
- 🎭 **Master Orchestration**: Seamlessly coordinates multiple agents
- 🧠 **Intelligent Coordination**: Smart decision-making and adaptation
- ⚡ **High Performance**: Efficient execution with elegant simplicity
- 🌟 **Universal Compatibility**: Works across all domains and use cases
- 🛡️ **Enterprise Reliability**: Robust error handling and fault tolerance
## 🤝 Community & Support
<!-- - 📚 **Documentation**: [docs.jaygoga.ai](https://docs.jaygoga.ai)
- 💬 **Discord**: [Join our community](https://discord.gg/jaygoga-orchestra) -->
- 🐛 **Issues**: [GitHub Issues](https://github.com/AIMLDev726/jaygoga_orchestra/issues)
- 📧 **Email**: aistudentlearn4@gmail.com
## 📜 License
MIT License - see LICENSE file for details.
## 🙏 Contributing
We welcome contributions from the community! Please read our contributing guidelines before submitting PRs.
---
**"Orchestrating AI agents in perfect harmony for intelligent automation."** 🎼
Raw data
{
"_id": null,
"home_page": "https://github.com/AIMLDev726/jaygoga_orchestra",
"name": "jaygoga-orchestra",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "ai, agents, workflow, automation, llm, orchestration, jaygoga",
"author": "AIMLDev726",
"author_email": "AIMLDev726 <aistudentlearn4@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/09/0b/267b86229f827e3909526221e62c484ec71a9a27c9c0330bdaa50bbbff1b/jaygoga_orchestra-1.0.2.tar.gz",
"platform": null,
"description": "# JayGoga-Orchestra \ud83c\udfbc - Advanced AI Agent Orchestration Framework\r\n\r\n**JayGoga-Orchestra** is a powerful AI agent orchestration framework for intelligent automation. It provides seamless coordination of AI agents for complex workflows and enterprise-grade automation solutions.\r\n\r\n## \ud83c\udf1f Features\r\n\r\n- **\ud83c\udfad Dual Architecture**: Choose between Classical (v1) and Modern (v2) orchestration patterns\r\n- **\ud83d\udd2e Intelligent Orchestration**: Advanced agent coordination and workflow management\r\n- **\u26a1 High Performance**: Optimized for speed and scalability\r\n- **\ud83d\udee1\ufe0f Enterprise Ready**: Built for production environments\r\n- **\ud83c\udfa8 Flexible Design**: Adapt to any AI workflow requirement\r\n- **\ud83d\udcda Rich Documentation**: Comprehensive guides and examples\r\n- **\ud83d\udd04 Seamless Integration**: Easy integration with existing systems\r\n\r\n## \ud83d\ude80 Installation\r\n\r\n```bash\r\npip install jaygoga-orchestra\r\n```\r\n\r\n## \ud83c\udfaf Quick Start\r\n\r\n### \ud83c\udfdb\ufe0f Classical Orchestration (v1) - Structured & Reliable\r\n\r\nPerfect for **structured workflows**, **enterprise environments**, and **predictable processes**.\r\n\r\n```python\r\nfrom jaygoga_orchestra.v1 import Agent, Task, Squad, Process\r\n\r\n# Create specialized agents\r\nanalyst = Agent(\r\n role=\"Senior Data Analyst\",\r\n goal=\"Extract meaningful insights from complex datasets\",\r\n backstory=\"You are a seasoned analyst with 10+ years of experience in data science and business intelligence.\"\r\n)\r\n\r\nresearcher = Agent(\r\n role=\"Market Researcher\",\r\n goal=\"Gather comprehensive market intelligence\",\r\n backstory=\"You specialize in market analysis and competitive intelligence gathering.\"\r\n)\r\n\r\n# Define specific tasks\r\nanalysis_task = Task(\r\n description=\"Analyze Q4 sales data and identify key trends, patterns, and anomalies\",\r\n agent=analyst,\r\n expected_output=\"Detailed analysis report with visualizations and recommendations\"\r\n)\r\n\r\nresearch_task = Task(\r\n description=\"Research market conditions and competitor performance in Q4\",\r\n agent=researcher,\r\n expected_output=\"Market intelligence report with competitor analysis\"\r\n)\r\n\r\n# Create coordinated squad\r\nintelligence_squad = Squad(\r\n agents=[analyst, researcher],\r\n tasks=[analysis_task, research_task],\r\n process=Process.sequential,\r\n verbose=True\r\n)\r\n\r\n# Execute the orchestrated workflow\r\nresults = intelligence_squad.execute()\r\nprint(f\"Analysis Complete: {results}\")\r\n```\r\n\r\n### \ud83d\ude80 Modern Orchestration (v2) - Dynamic & Intelligent\r\n\r\nIdeal for **adaptive workflows**, **AI-driven decisions**, and **dynamic environments**.\r\n\r\n```python\r\nfrom jaygoga_orchestra.v2 import Agent, Team, Workflow\r\n\r\n# Create intelligent agents with advanced capabilities\r\ndata_agent = Agent(\r\n name=\"JayGoga_DataSage\",\r\n description=\"Advanced AI agent specialized in data analysis with deep learning capabilities\",\r\n instructions=\"You are an expert data scientist with the ability to adapt your analysis approach based on data characteristics\",\r\n model=\"gpt-4\",\r\n tools=[\"python_interpreter\", \"data_visualization\", \"statistical_analysis\"]\r\n)\r\n\r\ninsight_agent = Agent(\r\n name=\"JayGoga_InsightMaster\",\r\n description=\"Strategic insight generator with business acumen\",\r\n instructions=\"Transform data findings into actionable business strategies and recommendations\",\r\n model=\"claude-3-sonnet\",\r\n tools=[\"business_analysis\", \"report_generation\", \"strategic_planning\"]\r\n)\r\n\r\n# Create dynamic team with shared context\r\nintelligence_team = Team(\r\n agents=[data_agent, insight_agent],\r\n name=\"Strategic Intelligence Unit\",\r\n description=\"Elite team for comprehensive business intelligence\",\r\n shared_memory=True,\r\n collaboration_mode=\"adaptive\"\r\n)\r\n\r\n\r\n# Execute with dynamic adaptation\r\nresults = intelligence_team.run(\r\n task=\"Analyze our Q4 performance data and provide strategic recommendations for Q1\",\r\n context={\"data_source\": \"sales_db\", \"priority\": \"high\", \"deadline\": \"2024-01-15\"}\r\n)\r\n\r\nprint(f\"Strategic Analysis: {results.summary}\")\r\nprint(f\"Key Insights: {results.insights}\")\r\nprint(f\"Recommendations: {results.recommendations}\")\r\n```\r\n\r\n## \ud83c\udfd7\ufe0f Architecture Comparison\r\n\r\n| Feature | Classical v1 | Modern v2 | Best For |\r\n|---------|-------------|-----------|----------|\r\n| **Structure** | Hierarchical, Role-based | Dynamic, Capability-based | v1: Enterprise, v2: Startups |\r\n| **Execution** | Sequential/Parallel | Adaptive Intelligence | v1: Predictable, v2: Creative |\r\n| **Memory** | Task-scoped | Shared Context | v1: Privacy, v2: Collaboration |\r\n| **Scalability** | Linear | Exponential | v1: Controlled, v2: Rapid growth |\r\n| **Learning** | Rule-based | AI-driven | v1: Compliance, v2: Innovation |\r\n| **Complexity** | Structured | Self-organizing | v1: Governance, v2: Agility |\r\n\r\n### \ud83c\udfad When to Choose Which Version\r\n\r\n**Choose Classical v1 when:**\r\n- \ud83c\udfe2 Enterprise environment with strict governance\r\n- \ud83d\udccb Well-defined, repeatable processes\r\n- \ud83d\udd12 Compliance and audit requirements\r\n- \ud83d\udc65 Large teams with clear role definitions\r\n- \ud83d\udcca Predictable workflows and outcomes\r\n\r\n**Choose Modern v2 when:**\r\n- \ud83d\ude80 Startup or innovation-focused environment\r\n- \ud83e\udde0 AI-driven decision making required\r\n- \ud83d\udd04 Dynamic, adaptive workflows needed\r\n- \ud83c\udf10 Collaborative, context-sharing scenarios\r\n- \ud83c\udfaf Creative problem-solving and exploration\r\n\r\n## \ud83d\udcc1 Project Structure\r\n\r\n```\r\njaygoga_orchestra/\r\n\u251c\u2500\u2500 __init__.py # Main orchestration entry point\r\n\u251c\u2500\u2500 v1/ # Classical Orchestration (Structured)\r\n\u2502 \u251c\u2500\u2500 __init__.py # Agent, Task, Squad, Process\r\n\u2502 \u251c\u2500\u2500 agent.py # Role-based agents\r\n\u2502 \u251c\u2500\u2500 team.py # Structured squads\r\n\u2502 \u251c\u2500\u2500 task.py # Defined tasks\r\n\u2502 \u251c\u2500\u2500 process.py # Execution processes\r\n\u2502 \u251c\u2500\u2500 cli/ # Command-line tools\r\n\u2502 \u251c\u2500\u2500 tools/ # Agent tools and utilities\r\n\u2502 \u2514\u2500\u2500 ...\r\n\u251c\u2500\u2500 v2/ # Modern Orchestration (Intelligent)\r\n\u2502 \u251c\u2500\u2500 __init__.py # Agent, Team, Workflow\r\n\u2502 \u251c\u2500\u2500 agent/ # Intelligent agents\r\n\u2502 \u251c\u2500\u2500 team/ # Collaborative teams\r\n\u2502 \u251c\u2500\u2500 workflow/ # Dynamic workflows\r\n\u2502 \u251c\u2500\u2500 memory/ # Shared context\r\n\u2502 \u251c\u2500\u2500 reasoning/ # AI reasoning\r\n\u2502 \u2514\u2500\u2500 ...\r\n\u2514\u2500\u2500 legacy/ # \ud83e\uddea Beta Features (Experimental)\r\n \u251c\u2500\u2500 README_BETA.md # Beta documentation\r\n \u2514\u2500\u2500 experimental/ # Cutting-edge features\r\n```\r\n\r\n## \ud83e\uddea Beta Features (Legacy/Experimental)\r\n\r\nOur **legacy** directory contains experimental and beta features that showcase the future of AI orchestration:\r\n\r\n```python\r\n# \ud83d\udea7 Beta Features - Available Soon!\r\nfrom jaygoga_orchestra.legacy import ExperimentalAgent, AdvancedWorkflow\r\n\r\n# Cutting-edge features in development\r\nbeta_agent = ExperimentalAgent(\r\n name=\"Krishna_BetaAgent\",\r\n capabilities=[\"quantum_reasoning\", \"multi_dimensional_analysis\"],\r\n status=\"beta\"\r\n)\r\n\r\n# Advanced experimental workflows\r\nexperimental_flow = AdvancedWorkflow(\r\n name=\"Future_Intelligence\",\r\n description=\"Next-generation AI orchestration patterns\",\r\n beta_features=[\"auto_optimization\", \"self_healing\", \"predictive_scaling\"]\r\n)\r\n```\r\n\r\n**Beta Features Include:**\r\n- \ud83d\udd2e **Quantum Reasoning**: Advanced decision-making algorithms\r\n- \ud83c\udf0a **Self-Healing Workflows**: Automatic error recovery and optimization\r\n- \ud83c\udfaf **Predictive Scaling**: AI-driven resource management\r\n- \ud83e\udde0 **Neural Orchestration**: Brain-inspired coordination patterns\r\n- \u26a1 **Lightning Execution**: Ultra-fast processing capabilities\r\n\r\n*These features are experimental and will be integrated into v3 in future releases.*\r\n\r\n## \ud83d\udd04 Migration & Integration\r\n\r\n### \ud83c\udfaf Getting Started with Govinda\r\n\r\n```python\r\n# Start with Classical v1 for structured workflows\r\nfrom jaygoga_orchestra.v1 import Agent, Task, Squad, Process\r\n\r\n# Upgrade to Modern v2 for intelligent orchestration\r\nfrom jaygoga_orchestra.v2 import Agent, Team, Workflow\r\n\r\n# Mix and match as needed\r\nfrom jaygoga_orchestra.v1 import Task\r\nfrom jaygoga_orchestra.v2 import Agent, Workflow\r\n```\r\n\r\n### \ud83d\ude80 Advanced Usage Examples\r\n\r\n**Multi-Agent Research Pipeline (v1):**\r\n```python\r\nfrom jaygoga_orchestra.v1 import Agent, Task, Squad, Process\r\n\r\n# Create research squad\r\nresearcher = Agent(role=\"Research Specialist\", goal=\"Gather comprehensive data\")\r\nanalyst = Agent(role=\"Data Analyst\", goal=\"Analyze and synthesize findings\")\r\nwriter = Agent(role=\"Technical Writer\", goal=\"Create detailed reports\")\r\n\r\n# Define research pipeline\r\ntasks = [\r\n Task(description=\"Research AI trends in 2024\", agent=researcher),\r\n Task(description=\"Analyze research findings\", agent=analyst),\r\n Task(description=\"Write comprehensive report\", agent=writer)\r\n]\r\n\r\nresearch_squad = Squad(agents=[researcher, analyst, writer], tasks=tasks)\r\nreport = research_squad.execute()\r\n```\r\n\r\n**Intelligent Content Creation (v2):**\r\n```python\r\nfrom jaygoga_orchestra.v2 import Agent, Team, Workflow\r\n\r\n# Create intelligent content team\r\ncontent_team = Team([\r\n Agent(name=\"ContentStrategist\", model=\"gpt-4\"),\r\n Agent(name=\"CreativeWriter\", model=\"claude-3\"),\r\n Agent(name=\"SEOOptimizer\", model=\"gpt-3.5-turbo\")\r\n])\r\n\r\nresult = content_team.run(\"Create a viral blog post about AI trends\")\r\n```\r\n\r\n## \ud83c\udfa8 Why JayGoga-Orchestra?\r\n\r\n**JayGoga-Orchestra** represents the perfect harmony of AI agents working together like a well-conducted orchestra. Each agent plays its part while contributing to a greater symphony of intelligent automation.\r\n\r\n**Core Principles:**\r\n- \ud83c\udfad **Master Orchestration**: Seamlessly coordinates multiple agents\r\n- \ud83e\udde0 **Intelligent Coordination**: Smart decision-making and adaptation\r\n- \u26a1 **High Performance**: Efficient execution with elegant simplicity\r\n- \ud83c\udf1f **Universal Compatibility**: Works across all domains and use cases\r\n- \ud83d\udee1\ufe0f **Enterprise Reliability**: Robust error handling and fault tolerance\r\n\r\n## \ud83e\udd1d Community & Support\r\n\r\n<!-- - \ud83d\udcda **Documentation**: [docs.jaygoga.ai](https://docs.jaygoga.ai)\r\n- \ud83d\udcac **Discord**: [Join our community](https://discord.gg/jaygoga-orchestra) -->\r\n- \ud83d\udc1b **Issues**: [GitHub Issues](https://github.com/AIMLDev726/jaygoga_orchestra/issues)\r\n- \ud83d\udce7 **Email**: aistudentlearn4@gmail.com\r\n\r\n## \ud83d\udcdc License\r\n\r\nMIT License - see LICENSE file for details.\r\n\r\n## \ud83d\ude4f Contributing\r\n\r\nWe welcome contributions from the community! Please read our contributing guidelines before submitting PRs.\r\n\r\n---\r\n\r\n**\"Orchestrating AI agents in perfect harmony for intelligent automation.\"** \ud83c\udfbc\r\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "JayGoga-Orchestra - Advanced AI Agent Orchestration Framework",
"version": "1.0.2",
"project_urls": {
"Documentation": "https://docs.jaygoga.ai",
"Homepage": "https://github.com/AIMLDev726/jaygoga_orchestra",
"Issues": "https://github.com/AIMLDev726/jaygoga_orchestra/issues",
"Repository": "https://github.com/AIMLDev726/jaygoga_orchestra"
},
"split_keywords": [
"ai",
" agents",
" workflow",
" automation",
" llm",
" orchestration",
" jaygoga"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "2c91ce8dc538e506ac12f510b8f55aeef6abf772fba514415b3d90f3329eddbe",
"md5": "665c48fe5cdcd7f247cc0f8b7de2f6b5",
"sha256": "6bde357c2509fcdb3191bf1c326f11f67f44b018830502ab573be6e2342e7d2e"
},
"downloads": -1,
"filename": "jaygoga_orchestra-1.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "665c48fe5cdcd7f247cc0f8b7de2f6b5",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 1609618,
"upload_time": "2025-08-30T19:35:22",
"upload_time_iso_8601": "2025-08-30T19:35:22.457666Z",
"url": "https://files.pythonhosted.org/packages/2c/91/ce8dc538e506ac12f510b8f55aeef6abf772fba514415b3d90f3329eddbe/jaygoga_orchestra-1.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "090b267b86229f827e3909526221e62c484ec71a9a27c9c0330bdaa50bbbff1b",
"md5": "9a773467508bd26586859ec26ae57648",
"sha256": "faa392ebecbeacdcf1c83e765cd8a8b1dae32b59496439cc146c6d9d38ddf920"
},
"downloads": -1,
"filename": "jaygoga_orchestra-1.0.2.tar.gz",
"has_sig": false,
"md5_digest": "9a773467508bd26586859ec26ae57648",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 1166434,
"upload_time": "2025-08-30T19:35:24",
"upload_time_iso_8601": "2025-08-30T19:35:24.586653Z",
"url": "https://files.pythonhosted.org/packages/09/0b/267b86229f827e3909526221e62c484ec71a9a27c9c0330bdaa50bbbff1b/jaygoga_orchestra-1.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-30 19:35:24",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "AIMLDev726",
"github_project": "jaygoga_orchestra",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "pydantic",
"specs": [
[
">=",
"2.4.2"
]
]
},
{
"name": "openai",
"specs": [
[
">=",
"1.13.3"
]
]
},
{
"name": "litellm",
"specs": [
[
"==",
"1.74.9"
]
]
},
{
"name": "instructor",
"specs": [
[
">=",
"1.3.3"
]
]
},
{
"name": "pdfplumber",
"specs": [
[
">=",
"0.11.4"
]
]
},
{
"name": "regex",
"specs": [
[
">=",
"2024.9.11"
]
]
},
{
"name": "opentelemetry-api",
"specs": [
[
">=",
"1.30.0"
]
]
},
{
"name": "opentelemetry-sdk",
"specs": [
[
">=",
"1.30.0"
]
]
},
{
"name": "opentelemetry-exporter-otlp-proto-http",
"specs": [
[
">=",
"1.30.0"
]
]
},
{
"name": "chromadb",
"specs": [
[
">=",
"0.5.23"
]
]
},
{
"name": "tokenizers",
"specs": [
[
">=",
"0.20.3"
]
]
},
{
"name": "onnxruntime",
"specs": [
[
"==",
"1.22.0"
]
]
},
{
"name": "openpyxl",
"specs": [
[
">=",
"3.1.5"
]
]
},
{
"name": "pyvis",
"specs": [
[
">=",
"0.3.2"
]
]
},
{
"name": "python-dotenv",
"specs": [
[
">=",
"1.0.0"
]
]
},
{
"name": "pyjwt",
"specs": [
[
">=",
"2.9.0"
]
]
},
{
"name": "click",
"specs": [
[
">=",
"8.1.7"
]
]
},
{
"name": "appdirs",
"specs": [
[
">=",
"1.4.4"
]
]
},
{
"name": "jsonref",
"specs": [
[
">=",
"1.1.0"
]
]
},
{
"name": "json-repair",
"specs": [
[
"==",
"0.25.2"
]
]
},
{
"name": "uv",
"specs": [
[
">=",
"0.4.25"
]
]
},
{
"name": "tomli-w",
"specs": [
[
">=",
"1.1.0"
]
]
},
{
"name": "tomli",
"specs": [
[
">=",
"2.0.2"
]
]
},
{
"name": "blinker",
"specs": [
[
">=",
"1.9.0"
]
]
},
{
"name": "json5",
"specs": [
[
">=",
"0.10.0"
]
]
},
{
"name": "portalocker",
"specs": [
[
"==",
"2.7.0"
]
]
},
{
"name": "rich",
"specs": [
[
">=",
"13.0.0"
]
]
},
{
"name": "typing-extensions",
"specs": [
[
">=",
"4.0.0"
]
]
},
{
"name": "requests",
"specs": [
[
">=",
"2.25.0"
]
]
},
{
"name": "anthropic",
"specs": [
[
">=",
"0.3.0"
]
]
},
{
"name": "langchain",
"specs": [
[
">=",
"0.1.0"
]
]
},
{
"name": "langchain-community",
"specs": [
[
">=",
"0.0.1"
]
]
},
{
"name": "langchain-openai",
"specs": [
[
">=",
"0.0.1"
]
]
},
{
"name": "tiktoken",
"specs": [
[
">=",
"0.5.0"
]
]
},
{
"name": "tenacity",
"specs": [
[
">=",
"8.0.0"
]
]
},
{
"name": "PyYAML",
"specs": [
[
">=",
"6.0.0"
]
]
},
{
"name": "jsonschema",
"specs": [
[
">=",
"4.0.0"
]
]
},
{
"name": "sqlalchemy",
"specs": [
[
">=",
"2.0.0"
]
]
},
{
"name": "aiofiles",
"specs": [
[
">=",
"23.0.0"
]
]
},
{
"name": "httpx",
"specs": [
[
">=",
"0.24.0"
]
]
},
{
"name": "aiohttp",
"specs": [
[
">=",
"3.8.0"
]
]
},
{
"name": "pandas",
"specs": [
[
">=",
"2.2.3"
]
]
},
{
"name": "numpy",
"specs": [
[
">=",
"1.24.0"
]
]
},
{
"name": "pypdf",
"specs": [
[
">=",
"3.0.0"
]
]
},
{
"name": "python-docx",
"specs": [
[
">=",
"0.8.11"
]
]
},
{
"name": "markdown",
"specs": [
[
">=",
"3.4.0"
]
]
},
{
"name": "pgvector",
"specs": [
[
">=",
"0.2.0"
]
]
},
{
"name": "qdrant-client",
"specs": [
[
">=",
"1.14.3"
]
]
},
{
"name": "pinecone-client",
"specs": [
[
">=",
"2.2.0"
]
]
},
{
"name": "weaviate-client",
"specs": [
[
">=",
"3.15.0"
]
]
},
{
"name": "sentence-transformers",
"specs": [
[
">=",
"2.2.0"
]
]
},
{
"name": "huggingface-hub",
"specs": [
[
">=",
"0.16.0"
]
]
},
{
"name": "asyncio",
"specs": [
[
">=",
"3.4.3"
]
]
}
],
"lcname": "jaygoga-orchestra"
}
