DEDUPED Hot AI repos, turned into use cases Get the Monday 5
182 stars · Python

How to use FlowX: what you can do with it

FlowX is an open-source MCP server and Python SDK that turns plain-language process descriptions into stored, runnable AI agent workflows.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

3 use cases

  • Build a support ticket workflow from a chat request

    Describe a process in plain language and get a stored, runnable FastAPI workflow.

    View prompt
    Use the FlowX MCP server in the repo at <repo-path> to build a workflow that accepts a support ticket, classifies its category, assigns a priority, and drafts a reply. Report the workflow ID and the paths of the generated workflow.json and node files. Verify that the files exist under the FLOWX_DEFAULT_WORKSPACE folder.

  • Refine an existing workflow with a follow-up change

    Apply a targeted change to one node or the whole workflow without rebuilding everything.

    View prompt
    Using the FlowX Python SDK in the repo at <repo-path>, open the workflow <workflow-id>, list its nodes, and apply the change: Validate empty input. to the node <step-id>. Report the list of nodes before and after, and confirm that run_service starts the workflow.

  • Delegate workflow generation to another agent over A2A

    Let a separate agent send a text request and receive generated workflow artifact paths.

    View prompt
    Use the FlowX A2A endpoint at http://127.0.0.1:8001/a2a to send a text message describing <process-description> with message/send. Poll tasks/get until the task finishes. Report the task status and the generated artifact paths, and verify that the task is completed only if every stage succeeded.

Quick start with FlowX

  1. Check you have what it needs: Python 3.10 or later; An LLM provider, model, and API key for FLOWX_LLM_PROVIDER, FLOWX_LLM_MODEL, and FLOWX_LLM_API_KEY; A local MCP-capable agent client, or the Python SDK in your own script.
  2. Open AIpRoBuilder/FlowX on GitHub and read the README and license.
  3. Run python3.10 -m venv .venv && source .venv/bin/activate in the FlowX folder.
  4. Run python -m pip install -e .
  5. Copy the example settings with cp .env.example .env, then set FLOWX_LLM_PROVIDER, FLOWX_LLM_MODEL, FLOWX_LLM_API_KEY, and FLOWX_DEFAULT_WORKSPACE.
  6. Register flowx-mcp in your MCP client using the config example in the README, with the absolute path to the executable.

These steps come from our top use case, Build a support ticket workflow from a chat request, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for AIpRoBuilder/FlowX

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

FlowX alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and agent builders who want an AI agent to create, run, and refine repeatable workflows on their own machine.
  • Why it is hot182 stars, launched 80 days ago
  • LanguagePython
  • Sourcegithub.com/AIpRoBuilder/FlowX · Back to Hot repos

Requirements

  • Python 3.10 or later
  • An LLM provider, model, and API key for FLOWX_LLM_PROVIDER, FLOWX_LLM_MODEL, and FLOWX_LLM_API_KEY
  • A local MCP-capable agent client, or the Python SDK in your own script
  • A writable folder for FLOWX_DEFAULT_WORKSPACE

Add this badge to your README

Maintain FlowX? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/AIpRoBuilder/FlowX.svg)](https://dedupedai.com/use-cases/aiprobuilder-flowx/?utm_source=github&utm_medium=badge&utm_campaign=AIpRoBuilder-FlowX)

HTML 

<a href="https://dedupedai.com/use-cases/aiprobuilder-flowx/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=AIpRoBuilder-FlowX"><img src="https://dedupedai.com/badge/AIpRoBuilder/FlowX.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about FlowX

What is FlowX?

FlowX is an open-source MCP server and Python SDK that turns plain-language process descriptions into stored, runnable AI agent workflows. It is an open-source project on GitHub: https://github.com/AIpRoBuilder/FlowX.

Who is FlowX for?

Developers and agent builders who want an AI agent to create, run, and refine repeatable workflows on their own machine.

What can I do with FlowX?

3 use cases so far, for example: Build a support ticket workflow from a chat request; Refine an existing workflow with a follow-up change; Delegate workflow generation to another agent over A2A. Each has steps and a copy-paste agent prompt.

What do I need to run FlowX?

Python 3.10 or later; An LLM provider, model, and API key for FLOWX_LLM_PROVIDER, FLOWX_LLM_MODEL, and FLOWX_LLM_API_KEY; A local MCP-capable agent client, or the Python SDK in your own script; A writable folder for FLOWX_DEFAULT_WORKSPACE.

What are alternatives to FlowX?

Other hot AI repos in Software and DevOps: Codex LB Enhanced, Reuse Before Build, Aibuildai LLM Posttrain Agent, Codex Guard, Kyb.

Is FlowX safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.