longvy24/ai-workflow-studio — explained in plain English
Analysis updated 2026-05-18
Design an AI pipeline as a node diagram and see its projected monthly cost before building it.
Compare two workflow designs side by side to find a cheaper model configuration.
Generate a starting workflow diagram by describing it in plain English to an AI chat tool.
Import a workflow JSON file from another tool or from an AI generated response.
| longvy24/ai-workflow-studio | 100/rutgers-pbl-dining-2015 | a15n/a15n_old | |
|---|---|---|---|
| Stars | 0 | — | — |
| Language | HTML | HTML | HTML |
| Last pushed | — | 2015-12-01 | 2016-06-18 |
| Maintenance | — | Dormant | Dormant |
| Setup difficulty | easy | easy | easy |
| Complexity | 2/5 | 1/5 | 1/5 |
| Audience | vibe coder | general | general |
Figures from each repo's GitHub metadata at analysis time.
Can be run with zero install by opening index.html directly in a browser.
AI Workflow Studio is a visual desktop app for designing AI pipelines as diagrams made of connected boxes, similar to tools like n8n, but with one extra feature: it shows you what your design will cost to run before you build it. As you connect nodes representing different AI models and steps, the app calculates a live estimate of cost per run, per day, and per month, and warns you if a design goes over a budget you set. The app ships with 14 ready made example diagrams covering common AI patterns, such as retrieval based question answering, agents that reason and act in loops, systems made of multiple cooperating agents, and workflows that route requests to cheaper or more expensive models depending on need. It uses real, current pricing for Anthropic's Claude models, and that pricing is fully editable if you have a different negotiated rate. You can also paste in your own real usage numbers or import a usage file to replace the estimates with measured figures from your actual traffic. Building a workflow involves dragging pre-built blocks onto a canvas, connecting them, and using an automatic layout button to tidy the diagram. A simulate button animates a run through the pipeline while the cost estimate ticks up, which helps show where money is being spent. Finished diagrams can be exported as a PNG image or as a JSON file that can be imported again later, and there is no cloud account or telemetry involved, everything is stored locally on your computer. One interesting feature lets you describe a pipeline in plain English, copy a prompt into any AI chat tool, and paste the JSON response back into the app to instantly generate a working diagram, without needing an API key of your own. The app runs on Mac, Windows, and Linux, either as a downloadable installer or by opening a single HTML file directly in a browser with no installation at all, or by running it from source with Node.js.
An offline desktop editor for designing AI workflows as diagrams, with live cost estimates per run, day, and month.
Mainly HTML. The stack also includes Electron, HTML, Node.js.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly vibe coder.
This repo across BitVibe Labs
double-check against the repo, no cap.