michellacle/agentic-workflow-designer-vsc-extension — explained in plain English
Analysis updated 2026-05-18
Design multi-step AI agent workflows visually instead of writing orchestration code.
Chain planning, implementing, testing, and reviewing agents into one automated pipeline.
Add conditional branches, retry loops, and human approval steps to an agent workflow.
Track and share workflows as version-controlled YAML files.
| michellacle/agentic-workflow-designer-vsc-extension | 0xkinno/neuralvault | 0xmayurrr/ai-contractauditor | |
|---|---|---|---|
| Stars | 1 | 1 | 1 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | moderate | hard | easy |
| Complexity | 3/5 | 4/5 | 2/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires Node.js 18+, VS Code 1.129+, and GitHub Copilot with custom-agent support, must be built and installed manually.
This project is an extension for Visual Studio Code that lets developers build automated workflows by dragging and dropping shapes on a visual canvas, instead of writing code by hand. Each shape, called a node, represents a step in the workflow, such as starting the process, running an AI agent, checking a condition, waiting for a human to approve something, pausing for a set time, or ending the workflow. The workflows are designed to run using GitHub Copilot's custom agent feature. Each agent node in a workflow points to a written instruction file that tells an AI agent what its job is, like planning a task, writing code, testing it, or reviewing it. When you run a workflow, the extension opens Copilot Chat and starts executing each node in order, showing live colored status updates on the canvas so you can see which steps are running, finished, or failed. Workflows can branch based on conditions, retry steps in a loop, and pause for human approval before continuing. All of this is saved as YAML files, a plain text format, which means workflows can be tracked and shared using version control tools like git, the same way code is. To use it, you need Node.js, npm, a recent version of VS Code, and GitHub Copilot with chat and custom agent support turned on. Installing it involves running a few build commands from the project's source code and then installing the resulting extension package into VS Code manually, since it is not yet listed on the extension marketplace. The project includes example agent files for common roles like planning, implementing, testing, and reviewing, along with sample workflow files to help new users understand the format. The README does not state which open source license the project uses.
A VS Code extension for visually designing and running AI agent workflows on a drag-and-drop canvas, powered by GitHub Copilot custom agents.
Mainly TypeScript. The stack also includes TypeScript, VS Code Extension API, YAML.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
double-check against the repo, no cap.