| Name | kaygraph JSON |
| Version |
0.0.2
JSON |
| download |
| home_page | None |
| Summary | A context-graph framework for building production-ready AI applications. |
| upload_time | 2025-07-31 00:17:06 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.11 |
| license | MIT |
| keywords |
agentic
ai
context
graphs
llm
workflow
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# KayGraph
An opinionated framework for building context-aware AI applications with production-ready graphs.
[](https://pypi.org/project/kaygraph/)
[](https://www.python.org/downloads/)
## What is KayGraph?
KayGraph provides powerful abstractions for orchestrating complex AI workflows through **Context Graphs** - a pattern that seamlessly integrates operations, LLM calls, and state management into production-ready applications.
### Core Philosophy
- **Context-Aware Graphs**: Build sophisticated AI systems where every node has access to shared context
- **Opinionated Patterns**: Production-tested patterns for common AI workflows
- **Zero Dependencies**: Pure Python implementation with no external dependencies
- **Bring Your Own Tools**: Integrate any LLM, database, or service you prefer
## Installation
### Using uv (Recommended)
[uv](https://github.com/astral-sh/uv) is a fast Python package manager that provides better dependency resolution and faster installations:
```bash
# Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh
# Install KayGraph
uv pip install kaygraph
# Or install from source with development dependencies
git clone https://github.com/KayOS-AI/KayGraph.git
cd KayGraph/kaygraph-library
uv pip install -e ".[dev]"
```
### Using pip
```bash
pip install kaygraph
```
Or install from source:
```bash
git clone https://github.com/KayOS-AI/KayGraph.git
cd KayGraph/kaygraph-library
pip install -e .
```
## Quick Start
```python
from kaygraph import Node, Graph
# Define a simple node
class AnalyzeNode(Node):
def prep(self, shared):
# Read from shared context
return shared.get("input_text")
def exec(self, text):
# Process data (e.g., LLM call)
return analyze_sentiment(text)
def post(self, shared, prep_res, exec_res):
# Write to shared context
shared["sentiment"] = exec_res
return "complete" # Next action
# Create and run a graph
graph = Graph()
analyze = AnalyzeNode("analyzer")
graph.add_node(analyze)
shared = {"input_text": "KayGraph makes AI development intuitive!"}
graph.run(shared)
print(shared["sentiment"]) # Output: "positive"
```
## Key Features
### 🏗️ Core Abstractions
- **Node**: Atomic unit of work with 3-phase lifecycle (prep → exec → post)
- **Graph**: Orchestrates node execution through labeled actions
- **Shared Store**: Context-aware state management across nodes
### 🎯 Production Patterns
- **Agent**: Autonomous decision-making systems
- **RAG**: Retrieval-augmented generation pipelines
- **Workflows**: Multi-step task orchestration
- **Batch Processing**: Efficient data processing at scale
- **Async Operations**: Non-blocking I/O operations
### 🚀 Enterprise Features
- **ValidatedNode**: Input/output validation
- **MetricsNode**: Performance monitoring
- **Comprehensive Logging**: Built-in debugging support
- **Error Handling**: Graceful failure recovery
- **Resource Management**: Context managers for cleanup
## Documentation
### Core Concepts
- [Node Design](docs/fundamentals/node.md) - Understanding the 3-phase lifecycle
- [Graph Orchestration](docs/fundamentals/graph.md) - Connecting nodes with actions
- [Shared Store](docs/fundamentals/communication.md) - Managing shared context
### Common Patterns
- [Building Agents](docs/patterns/agent.md)
- [RAG Pipelines](docs/patterns/rag.md)
- [Workflows](docs/patterns/graph.md)
- [Map-Reduce](docs/patterns/mapreduce.md)
### Advanced Topics
- [Async Operations](docs/fundamentals/async.md)
- [Batch Processing](docs/fundamentals/batch.md)
- [Parallel Execution](docs/fundamentals/parallel.md)
- [Production Best Practices](docs/production/)
## Development with AI Assistants
KayGraph is designed for **Agentic Coding** - where humans design and AI agents implement.
### Generate Cursor Rules
```bash
# Generate AI coding assistant rules from documentation
python utils/update_kaygraph_mdc.py
```
This creates `.cursor/rules/` with context-aware guidance for AI assistants.
## Project Structure
```
kaygraph-library/
├── kaygraph/ # Core framework
│ └── __init__.py # All abstractions in one file
├── docs/ # Comprehensive documentation
├── tests/ # Unit tests
├── utils/ # Helper scripts
└── .cursor/rules/ # AI assistant guidance
```
## Contributing
We welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.
## License
MIT License - see [LICENSE](LICENSE) for details.
---
Built with ❤️ by the KayOS Team
Raw data
{
"_id": null,
"home_page": null,
"name": "kaygraph",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": "agentic, ai, context, graphs, llm, workflow",
"author": null,
"author_email": "KayOS Team <team@kayos.ai>",
"download_url": "https://files.pythonhosted.org/packages/f3/2f/ddcd5030d01d5b41962423a00b5ade084859fdfe184025c0ceebe8d76d18/kaygraph-0.0.2.tar.gz",
"platform": null,
"description": "# KayGraph\n\nAn opinionated framework for building context-aware AI applications with production-ready graphs.\n\n[](https://pypi.org/project/kaygraph/)\n\n[](https://www.python.org/downloads/)\n\n## What is KayGraph?\n\nKayGraph provides powerful abstractions for orchestrating complex AI workflows through **Context Graphs** - a pattern that seamlessly integrates operations, LLM calls, and state management into production-ready applications.\n\n### Core Philosophy\n\n- **Context-Aware Graphs**: Build sophisticated AI systems where every node has access to shared context\n- **Opinionated Patterns**: Production-tested patterns for common AI workflows\n- **Zero Dependencies**: Pure Python implementation with no external dependencies\n- **Bring Your Own Tools**: Integrate any LLM, database, or service you prefer\n\n## Installation\n\n### Using uv (Recommended)\n\n[uv](https://github.com/astral-sh/uv) is a fast Python package manager that provides better dependency resolution and faster installations:\n\n```bash\n# Install uv\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n\n# Install KayGraph\nuv pip install kaygraph\n\n# Or install from source with development dependencies\ngit clone https://github.com/KayOS-AI/KayGraph.git\ncd KayGraph/kaygraph-library\nuv pip install -e \".[dev]\"\n```\n\n### Using pip\n\n```bash\npip install kaygraph\n```\n\nOr install from source:\n\n```bash\ngit clone https://github.com/KayOS-AI/KayGraph.git\ncd KayGraph/kaygraph-library\npip install -e .\n```\n\n## Quick Start\n\n```python\nfrom kaygraph import Node, Graph\n\n# Define a simple node\nclass AnalyzeNode(Node):\n def prep(self, shared):\n # Read from shared context\n return shared.get(\"input_text\")\n\n def exec(self, text):\n # Process data (e.g., LLM call)\n return analyze_sentiment(text)\n\n def post(self, shared, prep_res, exec_res):\n # Write to shared context\n shared[\"sentiment\"] = exec_res\n return \"complete\" # Next action\n\n# Create and run a graph\ngraph = Graph()\nanalyze = AnalyzeNode(\"analyzer\")\ngraph.add_node(analyze)\n\nshared = {\"input_text\": \"KayGraph makes AI development intuitive!\"}\ngraph.run(shared)\nprint(shared[\"sentiment\"]) # Output: \"positive\"\n```\n\n## Key Features\n\n### \ud83c\udfd7\ufe0f Core Abstractions\n\n- **Node**: Atomic unit of work with 3-phase lifecycle (prep \u2192 exec \u2192 post)\n- **Graph**: Orchestrates node execution through labeled actions\n- **Shared Store**: Context-aware state management across nodes\n\n### \ud83c\udfaf Production Patterns\n\n- **Agent**: Autonomous decision-making systems\n- **RAG**: Retrieval-augmented generation pipelines\n- **Workflows**: Multi-step task orchestration\n- **Batch Processing**: Efficient data processing at scale\n- **Async Operations**: Non-blocking I/O operations\n\n### \ud83d\ude80 Enterprise Features\n\n- **ValidatedNode**: Input/output validation\n- **MetricsNode**: Performance monitoring\n- **Comprehensive Logging**: Built-in debugging support\n- **Error Handling**: Graceful failure recovery\n- **Resource Management**: Context managers for cleanup\n\n## Documentation\n\n### Core Concepts\n- [Node Design](docs/fundamentals/node.md) - Understanding the 3-phase lifecycle\n- [Graph Orchestration](docs/fundamentals/graph.md) - Connecting nodes with actions\n- [Shared Store](docs/fundamentals/communication.md) - Managing shared context\n\n### Common Patterns\n- [Building Agents](docs/patterns/agent.md)\n- [RAG Pipelines](docs/patterns/rag.md)\n- [Workflows](docs/patterns/graph.md)\n- [Map-Reduce](docs/patterns/mapreduce.md)\n\n### Advanced Topics\n- [Async Operations](docs/fundamentals/async.md)\n- [Batch Processing](docs/fundamentals/batch.md)\n- [Parallel Execution](docs/fundamentals/parallel.md)\n- [Production Best Practices](docs/production/)\n\n## Development with AI Assistants\n\nKayGraph is designed for **Agentic Coding** - where humans design and AI agents implement.\n\n### Generate Cursor Rules\n\n```bash\n# Generate AI coding assistant rules from documentation\npython utils/update_kaygraph_mdc.py\n```\n\nThis creates `.cursor/rules/` with context-aware guidance for AI assistants.\n\n## Project Structure\n\n```\nkaygraph-library/\n\u251c\u2500\u2500 kaygraph/ # Core framework\n\u2502 \u2514\u2500\u2500 __init__.py # All abstractions in one file\n\u251c\u2500\u2500 docs/ # Comprehensive documentation\n\u251c\u2500\u2500 tests/ # Unit tests\n\u251c\u2500\u2500 utils/ # Helper scripts\n\u2514\u2500\u2500 .cursor/rules/ # AI assistant guidance\n```\n\n## Contributing\n\nWe welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.\n\n## License\n\nMIT License - see [LICENSE](LICENSE) for details.\n\n---\n\nBuilt with \u2764\ufe0f by the KayOS Team\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A context-graph framework for building production-ready AI applications.",
"version": "0.0.2",
"project_urls": {
"Documentation": "https://github.com/KayOS-AI/KayGraph",
"Homepage": "https://github.com/KayOS-AI/KayGraph",
"Issues": "https://github.com/KayOS-AI/KayGraph/issues"
},
"split_keywords": [
"agentic",
" ai",
" context",
" graphs",
" llm",
" workflow"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "a91d914d1d3b6f229aa137438763602ff22814cfddfae40fc8a636f528e422d5",
"md5": "4e71b7ea52cb116f254f41fa9648fbf0",
"sha256": "aa2448e0cfe9aeae4f49a228eb9f0622b09c1023250d74a725e036794c25a4d2"
},
"downloads": -1,
"filename": "kaygraph-0.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "4e71b7ea52cb116f254f41fa9648fbf0",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 9501,
"upload_time": "2025-07-31T00:17:05",
"upload_time_iso_8601": "2025-07-31T00:17:05.447726Z",
"url": "https://files.pythonhosted.org/packages/a9/1d/914d1d3b6f229aa137438763602ff22814cfddfae40fc8a636f528e422d5/kaygraph-0.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "f32fddcd5030d01d5b41962423a00b5ade084859fdfe184025c0ceebe8d76d18",
"md5": "4d907fe33ad5805f5a431a489ac835c1",
"sha256": "f12aa93903c6fe4fd05ad7ab18bcbff310fb3eb36e73bc219de869b4cae30ae6"
},
"downloads": -1,
"filename": "kaygraph-0.0.2.tar.gz",
"has_sig": false,
"md5_digest": "4d907fe33ad5805f5a431a489ac835c1",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 662647,
"upload_time": "2025-07-31T00:17:06",
"upload_time_iso_8601": "2025-07-31T00:17:06.597434Z",
"url": "https://files.pythonhosted.org/packages/f3/2f/ddcd5030d01d5b41962423a00b5ade084859fdfe184025c0ceebe8d76d18/kaygraph-0.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-31 00:17:06",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "KayOS-AI",
"github_project": "KayGraph",
"github_not_found": true,
"lcname": "kaygraph"
}
