Metadata-Version: 2.5
Name: graphon-local
Version: 1.4.0
Summary: Graph execution engine for agentic AI workflows.
Project-URL: source, https://github.com/langgenius/graphon
Project-URL: homepage, https://github.com/langgenius/graphon
Project-URL: issues, https://github.com/langgenius/graphon/issues
License-Expression: Apache-2.0
License-File: LICENSE
Requires-Python: <3.14,>=3.12
Requires-Dist: charset-normalizer>=2.1
Requires-Dist: defusedxml>=0.7
Requires-Dist: httpx>=0.28
Requires-Dist: json-repair>=0.55
Requires-Dist: jsonschema>=4.18
Requires-Dist: odfdo>=3.22.8
Requires-Dist: orjson>=3
Requires-Dist: pandas[excel]>=2.1
Requires-Dist: pydantic-extra-types>=2
Requires-Dist: pydantic>=2.7
Requires-Dist: pypdf>=6.19.0
Requires-Dist: pypdfium2>=5
Requires-Dist: python-docx>=1.2
Requires-Dist: pyyaml>=6
Requires-Dist: tiktoken>=0.12
Requires-Dist: transformers>=4
Requires-Dist: typing-extensions>=4.10.0
Requires-Dist: unstructured[docx,md,ppt,pptx]>=0.21
Requires-Dist: webvtt-py>=0.5
Description-Content-Type: text/markdown

<!-- knowledge
last_checked: "2026-10-15T00:57:04Z"
-->
# Graphon

Graphon is a Python graph execution engine for agentic AI workflows.

The repository is still evolving, but it already contains a working execution
engine, built-in workflow nodes, model runtime abstractions, integration
protocols, and a runnable end-to-end example.

## Highlights

- Queue-based `Engine` orchestration with event-driven execution
- Graph parsing, validation, and fluent graph building
- Shared runtime state, variable pool, and workflow execution state
- Built-in node implementations for common workflow patterns
- DSL import support with Slim-backed LLM nodes
- HTTP, file, tool, and human-input integration protocols
- Extensible engine layers and external command channels

## Get started

Follow [development setup](CONTRIBUTING.md#development-setup), then run the
[Slim LLM example](examples/slim_llm/README.md). It includes both DSL import and
direct Python graph construction.

## Find the implementation

- [Architecture](ARCHITECTURE.md): public entry points, execution flow, and state ownership.
- [Development guide](docs/development.md): change surfaces and host integrations.
- [Repository knowledge](docs/README.md): component guides and maintenance.
- [Contributing](CONTRIBUTING.md): setup, validation, and contribution workflow.

## License

Apache-2.0. See [LICENSE](LICENSE).
