---
title: "Introducing Daggr: Chain apps programmatically, inspect visually"
description: "Building AI applications that connect multiple models and APIs often results in fragile scripts or requires complex production orchestration tools. To address rapid experimentation needs, Daggr introduces an open-source Python library created by the Gradio team for chaining AI workflows programmatically. Developers define workflows in Python code using components like GradioNode, FnNode, and InferenceNode, which automatically generate an interactive visual canvas served on port 7860. The interface allows users to inspect intermediate outputs, modify inputs, rerun individual pipeline steps without complete re-execution, and maintain persistent state across workspaces called sheets. Currently in beta, Daggr supports local execution with automatic fallback to remote APIs and integrates directly with Hugging Face Spaces."
---

# Introducing Daggr: Chain apps programmatically, inspect visually

[Hugging Face](https://yomu.fyi/company/hugging-face) · merve, yuvraj sharma, Abubakar Abid, hysts, Pedro Cuenca · Jan 29, 2026

**Type:** Announcement

## Summary

Building AI applications that connect multiple models and APIs often results in fragile scripts or requires complex production orchestration tools. To address rapid experimentation needs, Daggr introduces an open-source Python library created by the Gradio team for chaining AI workflows programmatically. Developers define workflows in Python code using components like GradioNode, FnNode, and InferenceNode, which automatically generate an interactive visual canvas served on port 7860. The interface allows users to inspect intermediate outputs, modify inputs, rerun individual pipeline steps without complete re-execution, and maintain persistent state across workspaces called sheets. Currently in beta, Daggr supports local execution with automatic fallback to remote APIs and integrates directly with Hugging Face Spaces.

## Context

Developers building AI pipelines across multiple models often struggle with debugging fragile scripts, re-running entire workflows to trace failed steps, or managing heavyweight production orchestration platforms not suited for rapid experimentation.

## Approach / What changed

Daggr provides a code-first Python library that constructs workflow graphs using GradioNode, FnNode, and InferenceNode, automatically rendering a visual canvas where users can inspect outputs, rerun specific steps, and persist workflow state.

## Takeaways

- Daggr supports three node types: GradioNode for Gradio Space endpoints or local clones, FnNode for custom Python functions, and InferenceNode for Hugging Face Inference Providers.
- Setting run\_locally=True on GradioNode automatically clones a Space into an isolated virtual environment and falls back to remote APIs if local execution fails.
- The automatically generated visual canvas persists state, inputs, and cached results locally, allowing individual workflow steps to be rerun without executing the entire pipeline.

**Tags:** [Developer Experience](https://yomu.fyi/topic/developer-experience), [Machine Learning](https://yomu.fyi/topic/machine-learning), [Open Source](https://yomu.fyi/topic/open-source), [Python](https://yomu.fyi/topic/python)

- Source: [Hugging Face](https://huggingface.co/blog/daggr)
- Source URL: https://huggingface.co/blog/daggr
- Ingested by Yomu: 2026-08-28T04:00:58.445Z

[Read original post](https://huggingface.co/blog/daggr)