# oryxflow

> oryxflow is an open-source Python library and Claude Code plugin for trustworthy, reproducible AI data analysis: no result is ever built on stale data, every result records the code and inputs that made it, and because finished steps are never recomputed the trustworthy path is also the fast, cheap one — lineage-tracked pipelines, local-first, no server or account.

oryxflow is a small, self-contained Python library for building data-science workflows: declare Task classes with parameters, dependencies (requires) and a run() that save()s output; the engine runs the DAG in dependency order, skips tasks whose output already exists, and reruns exactly what a parameter, data, or code change affects.

## oryxflow

- [Home](<https://docs.oryxflow.dev/index.md>)
- [Documentation](<https://docs.oryxflow.dev/docs/index.md>)
- [Why oryxflow](<https://docs.oryxflow.dev/docs/why-oryxflow/index.md>)
- [Installation](<https://docs.oryxflow.dev/docs/installation/index.md>)
- [Quickstart](<https://docs.oryxflow.dev/docs/quickstart/index.md>)
- [Transition from scripts](<https://docs.oryxflow.dev/docs/transition/index.md>)
- [Migrate a messy notebook project](<https://docs.oryxflow.dev/docs/migrate-notebook-to-pipeline/index.md>)
- [Writing and managing tasks](<https://docs.oryxflow.dev/docs/tasks/index.md>)
- [Workflows](<https://docs.oryxflow.dev/docs/workflow/index.md>)
- [Running workflows](<https://docs.oryxflow.dev/docs/run/index.md>)
- [Task I/O formats](<https://docs.oryxflow.dev/docs/targets/index.md>)
- [Reports from notebooks](<https://docs.oryxflow.dev/docs/reports/index.md>)
- [Logging](<https://docs.oryxflow.dev/docs/logging/index.md>)
- [Managing complex workflows](<https://docs.oryxflow.dev/docs/managing-workflows/index.md>)
- [Experiment tracking (MLflow, W&amp;B)](<https://docs.oryxflow.dev/docs/experiment-tracking/index.md>)
- [Dynamic workflow generation](<https://docs.oryxflow.dev/docs/advtasksdyn/index.md>)
- [Parameters](<https://docs.oryxflow.dev/docs/advparam/index.md>)
- [Functional API](<https://docs.oryxflow.dev/docs/functional_tasks/index.md>)
- [Example (ML)](<https://docs.oryxflow.dev/docs/example-ml/index.md>)
- [Glossary](<https://docs.oryxflow.dev/docs/glossary/index.md>)
- [Security &amp; supply chain](<https://docs.oryxflow.dev/docs/supply-chain/index.md>)
- [API Reference](<https://docs.oryxflow.dev/docs/reference/index.md>)
- [Changelog](<https://docs.oryxflow.dev/docs/changelog/index.md>)

## Knowledge

- [Collaborate &amp; share flows](<https://docs.oryxflow.dev/docs/collaborate/index.md>)

## oryxeval

- [Quickstart](<https://docs.oryxflow.dev/docs/llm-evals-quickstart/index.md>)
- [Guide](<https://docs.oryxflow.dev/docs/llm-evals/index.md>)
- [Prompt files](<https://docs.oryxflow.dev/docs/llm-evals-prompts/index.md>)
- [Classes and functions](<https://docs.oryxflow.dev/docs/llm-evals-api/index.md>)
- [What a plan must contain](<https://docs.oryxflow.dev/docs/llm-evals-checklist/index.md>)
- [Scaffold with Claude Code](<https://docs.oryxflow.dev/docs/claude-plugin/evals/index.md>)
- [Changelog](<https://docs.oryxflow.dev/docs/llm-evals-changelog/index.md>)

## Claude Code

- [Claude Code for data science](<https://docs.oryxflow.dev/docs/claude-code-for-data-science/index.md>)
- [Built for AI coding agents](<https://docs.oryxflow.dev/docs/ai-ready/index.md>)
- [Build with Claude Code](<https://docs.oryxflow.dev/docs/claude-plugin/index.md>)
- [Trustworthy AI data analysis](<https://docs.oryxflow.dev/docs/claude-plugin/trust/index.md>)
- [Commands](<https://docs.oryxflow.dev/docs/claude-plugin/commands/index.md>)
- [Data-science project structure](<https://docs.oryxflow.dev/docs/claude-plugin/project-structure/index.md>)
- [Stop AI data analysis turning into a mess](<https://docs.oryxflow.dev/docs/claude-plugin/coding-standards/index.md>)
- [Why library + plugin](<https://docs.oryxflow.dev/docs/claude-plugin/why/index.md>)

## Blog

- [Blog](<https://docs.oryxflow.dev/blog/index.md>)
- [4 Reasons why your machine learning code is bad](<https://docs.oryxflow.dev/blog/machine-learning/why-machine-learning-code-is-bad/index.md>)
- [Best practices for AI-assisted data analysis](<https://docs.oryxflow.dev/blog/ai-agents/best-practices-ai-assisted-data-analysis/index.md>)
- [Airflow alternatives for data science: an honest roundup](<https://docs.oryxflow.dev/blog/comparisons/airflow-alternatives-for-data-science/index.md>)
- [The best AI tools for data analysis (and the trust layer most of them miss)](<https://docs.oryxflow.dev/blog/ai-agents/best-ai-tools-for-data-analysis/index.md>)
- [The best Claude Code plugins and tools for data science](<https://docs.oryxflow.dev/blog/ai-agents/best-claude-code-plugins-for-data-science/index.md>)
- [How to cache intermediate DataFrames in Python (without brittle pickle files)](<https://docs.oryxflow.dev/blog/caching/cache-intermediate-dataframes-in-python/index.md>)
- [How to make Claude Code a trustworthy data scientist](<https://docs.oryxflow.dev/blog/ai-agents/caching-dag-for-ai-coding-agents/index.md>)
- [Cheap, durable LLM evals: pydantic-evals + oryxflow](<https://docs.oryxflow.dev/blog/guides/cheap-durable-llm-evals/index.md>)
- [Claude Code skills for data science: what they are, and what they aren't](<https://docs.oryxflow.dev/blog/ai-agents/claude-code-skills-for-data-science/index.md>)
- [Your eval platform deletes your results in 14 days](<https://docs.oryxflow.dev/blog/ai-agents/llm-eval-results-deleted-retention/index.md>)
- [LLM evals are a parameter sweep — use a parameter sweep tool](<https://docs.oryxflow.dev/blog/ai-agents/llm-evals-are-a-parameter-sweep/index.md>)
- [Migrate from d6tflow to oryxflow](<https://docs.oryxflow.dev/blog/guides/migrate-from-d6tflow-to-oryxflow/index.md>)
- [MLflow alternatives: the trackers worth a look (and the layer underneath them)](<https://docs.oryxflow.dev/blog/comparisons/mlflow-alternatives/index.md>)
- [Do you need MLflow, or do you need a reproducible pipeline?](<https://docs.oryxflow.dev/blog/mlops/mlflow-vs-pipeline-caching/index.md>)
- [How to turn a messy notebook into a reproducible pipeline, one step at a time](<https://docs.oryxflow.dev/blog/reproducibility/notebook-to-reproducible-pipeline/index.md>)
- [oryxflow vs Airflow: research workflows vs production orchestration](<https://docs.oryxflow.dev/blog/comparisons/oryxflow-vs-airflow/index.md>)
- [oryxflow vs Dagster: a lightweight research loop vs an asset platform](<https://docs.oryxflow.dev/blog/comparisons/oryxflow-vs-dagster/index.md>)
- [oryxflow vs DVC: Python task identity vs file-hash data versioning](<https://docs.oryxflow.dev/blog/comparisons/oryxflow-vs-dvc/index.md>)
- [oryxflow vs Prefect: research-loop caching vs Python-native orchestration](<https://docs.oryxflow.dev/blog/comparisons/oryxflow-vs-prefect/index.md>)
- [oryxflow vs. the field: pipeline frameworks for AI data analysis](<https://docs.oryxflow.dev/blog/comparisons/oryxflow-vs-pipeline-frameworks/index.md>)
- [Parameter sweeps in Python without rerunning upstream steps](<https://docs.oryxflow.dev/blog/caching/parameter-sweeps-without-rerunning/index.md>)
- [Reproducible data science workflows in Python](<https://docs.oryxflow.dev/blog/reproducibility/reproducible-data-science-workflows-in-python/index.md>)
- [Stop rerunning your whole pipeline when one step changes](<https://docs.oryxflow.dev/blog/caching/stop-rerunning-your-pipeline/index.md>)
- [When not to use oryxflow](<https://docs.oryxflow.dev/blog/guides/when-not-to-use-oryxflow/index.md>)