Skip to main content
ModuleX is an AI workflow orchestration platform. You describe a process in plain English or lay it out on a visual canvas, connect the tools you already use, and run it from chat, the API, or an SDK. This page covers what sets ModuleX apart. For a step-by-step picture of how the pieces fit together, read How ModuleX works.

​
What makes ModuleX different

Two ways to build

Describe the workflow to the AI Composer in plain English, or build it node by node on the visual canvas. Both produce the same editable workflow graph.

Realtime collaboration

Your team works on the same canvas at once, with live cursors, presence, and node locks so two people never overwrite each other.

Bring your own keys

Connect your own model and provider accounts. Providers bill you directly, with no ModuleX markup, or use ModuleX-managed models and pay in credits.

Your own knowledge

Ground answers in your company’s documents. ModuleX retrieves the relevant context automatically inside chats and workflows.

175 integrations

Call the services you already use from any workflow or agent. The integration registry is open source, so you can read and extend it.

Developer-grade SDKs

Official JavaScript and Python SDKs put every workflow, run, and stream behind a typed client you can embed in your own product.

​
The problem ModuleX solves

If you have built with AI before, you have probably stitched together model APIs, vendor SDKs, and automation tools by hand, then written your own glue to make them run in order, retry on failure, and stream results. No-code automation tools remove the glue, but they tend to lock you into fixed templates, a single model, and no escape hatch when you need real code. ModuleX sits between the two. You get a visual canvas and natural-language building for the parts that should be fast, plus an API, SDKs, and a code-capable node set for the parts that need control.

​
Build the way that suits the task

You do not have to pick one building style for everything.
1

Describe it

Tell the AI Composer what you want in plain English. It lays out the steps, tools, and logic as an editable workflow graph.
2

Refine it on the canvas

Open the workflow builder and adjust any node directly. Composer edits and manual edits change the same graph.
3

Run it anywhere

Run the finished workflow from chat, the REST API, or an SDK, and stream the result live.
There is also an Assistant: an agentic chat that uses your connected tools step by step to get work done, with no workflow to set up first.

​
Work together, live

Workflows are rarely a solo effort. In ModuleX, several people can edit the same canvas at the same time.

Live presence

See who else is on the canvas and where their cursor is, in realtime.

Node locks

When a teammate is editing a node, it locks so your changes never collide.

Shared history

Edits are versioned, so the team can see what changed and roll back when needed.
For how the canvas stays in sync across collaborators, see the realtime and collaboration model.

​
Your models, your keys

ModuleX works with every major AI provider, including Anthropic, OpenAI, Google, and xAI. You choose how usage is billed.

Bring your own keys (BYOK)

Connect your own provider accounts. The provider bills you directly with no ModuleX markup, so you keep full cost transparency.

ModuleX-managed models

Skip the setup and use ModuleX-provisioned providers. Managed usage is metered in credits.

​
Answers grounded in your knowledge

Connect your company’s documents as knowledge bases, and ModuleX retrieves the relevant context for you, inside both chats and workflows. You can use ModuleX-managed vector storage, billed in credits, or bring your own vector store.

Managed knowledge

Let ModuleX host the vector storage and retrieval. Ingest and retrieval are billed in credits.

Bring your own store

Point ModuleX at your own Qdrant, Pinecone, MongoDB Atlas, or Weaviate.
Read more in Knowledge & RAG.

​
Connect the tools you already use

ModuleX ships with 175 integrations you can call from any workflow or agent. The integration registry is open source, so you can read how each connector works and add your own.

Browse the integration catalog

See all 175 integrations grouped by category, from source control and messaging to CRMs and databases.

​
Pay only for managed usage

ModuleX meters managed usage in credits. When you bring your own keys, that usage is not credited, so your provider bill stays your provider bill.
Running a workflow or an agent turn, ingesting and retrieving from a ModuleX-managed knowledge base, and calling ModuleX-managed models all consume credits. BYOK model usage is billed by your provider, not by ModuleX. See Credits & metering for the full breakdown.
Each plan includes a monthly credit allowance. Paid plans can spend beyond it from a prepaid wallet only if you turn on overage. If you bring your own keys, model usage runs on your provider account at provider rates. See Billing & credits overview.

​
Built for teams and enterprises

As your team grows, ModuleX adds the controls larger organizations need: organization roles, access control, and audit-ready usage tracking.

ModuleX for enterprise

Single sign-on, role-based permissions, and the security posture larger teams require.

​
Where to go next

How ModuleX works

The end-to-end mental model, from a prompt or canvas to a running, observable workflow.

Quickstart

Create an account, get an API key, and make your first authenticated call.

Run your first workflow

Build a workflow in the canvas or with the Composer, then run it from the app.

Core concepts at a glance

The handful of ideas you need: workflows, runs, nodes, Composer, Assistant, knowledge, and credits.