Skip to content
Get packs

Guide · Open source

How to use rocketride-server: install, build pipelines and call them

Updated · written with AI from the project's own documentation and checked against our catalogue data

RocketRide is an open source AI Development Environment for building and running AI data pipelines. Pipelines are defined as portable JSON, built visually inside VS Code, and executed by a multithreaded C++ runtime. This guide explains what the rocketride-server repository contains, how to get started, and when it is the right tool.

RocketRiderocketride-org/rocketride-server · ★ 19.6k · MIT

Quick start

  1. 1Clone the repository. Run git clone on the rocketride-org/rocketride-server repository to get the source.
  2. 2Install the VS Code extension. Search for RocketRide in the VS Code extension marketplace and install it.
  3. 3Choose Local. In the extension, pick Local to run pipelines on your own machine.
  4. 4Build a pipeline visually. Drag, connect and configure nodes on the canvas in VS Code.
  5. 5Run and observe. Run the pipeline and use the observability views to check token usage, latency and execution.
  6. 6Call from an app. Use the Python or TypeScript SDK to run the pipeline from your application.

What is rocketride-server?

rocketride-server is the open source repository behind RocketRide. According to its README, RocketRide is an open source data pipeline builder and runtime for AI and ML workloads, with 100+ pipeline nodes covering LLM providers, vector databases, OCR, NER and more. The project is MIT licensed and its primary language is Python.

The engine runs entirely on your own infrastructure. The README also describes it as a development environment and SDKs rather than an end-user chat application.

  • Pipelines are defined as portable JSON and built visually in VS Code.
  • Execution happens in a multithreaded C++ runtime.
  • Nodes are Python-extensible, so you can write and publish your own.

What do you need before you start?

The main prerequisite listed for the extension is VS Code. The README describes a developer-oriented setup, so basic familiarity with IDEs, and for some workflows Docker or the SDKs, is assumed.

  • VS Code, needed for the RocketRide extension.
  • Git, to clone the repository.
  • Docker, if you plan to use the Docker deployment path described in the README.
  • Python or TypeScript, if you want to call pipelines from an application.

Install rocketride-server and the VS Code extension

The README's install step starts by cloning the repository. Then install the extension for your IDE by searching for RocketRide in the extension marketplace. The README also links the VS Code Marketplace and Open VSX Registry listings.

After installing the extension, the README suggests picking Local in the extension to run a pipeline on your own machine.

  • VS Code Marketplace and Open VSX Registry both list the RocketRide extension.
  • The README's quick start says nothing needs to be signed up for to run locally.
git clone https://github.com/rocketride-org/rocketride-server

Build and run your first pipeline

Pipelines are composed on a visual canvas in VS Code. You drag, connect and configure nodes, then run and debug the pipeline from the IDE. The README says the built-in observability tracks token usage, LLM calls, latency and execution.

Because pipelines are plain JSON, you can keep them in version control and share them.

  • Add nodes such as LLM providers, vector databases or OCR from the visual builder.
  • Connect nodes and configure each one.
  • Run and observe the pipeline to check token usage, latency and execution.

Call pipelines from Python or TypeScript

The README describes Python and TypeScript SDKs for dropping pipelines into an application with a few lines of code. Python SDK and TypeScript SDK packages are linked from the README on PyPI and npm.

An MCP server is also listed, which lets you expose pipelines as callable tools for AI assistants.

  • Python SDK: published on PyPI as rocketride.
  • TypeScript SDK: published on npm as rocketride.
  • MCP server: documented at docs.rocketride.org.

Deploy with Docker or on your own infrastructure

The README lists Docker, on-prem and RocketRide Cloud as deployment options. The Docker and on-prem options run on your own infrastructure. RocketRide Cloud is a hosted option that the README describes as operated by the project team.

For a self-hosted setup, check the Docker instructions in the project documentation at docs.rocketride.org, since the README excerpt does not include the exact Docker commands.

  • Docker: listed as a deployment option.
  • On-prem: run the engine on your own machines.
  • RocketRide Cloud: hosted option, not required to use the open source engine.

What people use it for

  • Building an LLM workflow visually inside VS Code and testing it locally.
  • Running AI pipelines on your own infrastructure instead of a hosted service.
  • Calling a pipeline from a Python or TypeScript app.
  • Swapping between different LLM providers and vector databases in one pipeline design.
  • Building multi-agent workflows with CrewAI or LangChain support.

Frequently asked questions

Is rocketride-server free to use?

The README states the engine is MIT licensed and open source, with no enterprise edition and nothing behind a paywall. Check the LICENSE file in the repository for the full terms.

What are the requirements for rocketride-server?

The README lists VS Code as the prerequisite for the extension. Docker, Python or TypeScript may be needed depending on how you deploy or call pipelines.

How do I install rocketride-server?

Start by cloning the repository with git clone from the rocketride-org GitHub account. Then install the RocketRide extension from the VS Code Marketplace or Open VSX Registry.

Is rocketride-server a chat app?

No. The README describes it as a development environment and SDKs for building AI pipelines, not a ready-made end-user chat product.

How does rocketride-server compare to LangChain or LlamaIndex?

The README positions RocketRide as a visual pipeline builder and runtime with a C++ engine, while LangChain and LlamaIndex are typically code-first frameworks. Compare them on whether you want a visual IDE workflow or code-based composition.

Why won't my pipeline run?

The source excerpt does not include troubleshooting steps. Check the documentation at docs.rocketride.org and the project's GitHub issues, or ask in the Discord linked from the README.

New agent skills, repos and AI tools — every week

The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.

Our verdict

rocketride-server suits developers who want to build and debug LLM pipelines visually in VS Code and run them on their own infrastructure. It is less suited to non-technical users, people who only want a chat app, or projects that need a single simple LLM call.

Install options & downloads