RocketRide Documentation

RocketRide is an open-source runtime for AI pipelines. Pipelines are portable JSON: version-controlled, shareable, and executed by a multithreaded C++ core that runs the same way on your laptop, your servers, or RocketRide Cloud.

Get StartedCore Concepts

01 · Build

Build your first pipeline

New to RocketRide? Start here: run a working pipeline and pick up the core concepts along the way.

Build in your IDE

Install the VS Code extension, deploy a local runtime, and assemble a pipeline visually in minutes.

Integrate with an SDK

Drop pipelines into your TypeScript or Python application with a few lines of code.

02 · Run

Choose how you run RocketRide

RocketRide Cloud

Start building right away on the managed platform. Same pipeline JSON, zero infrastructure to manage.

Self-host

Run the runtime on your own infrastructure — Docker, on-prem, or anywhere the engine builds.

03 · Explore

Explore more

TypeScript SDK

Deploy, run, and observe pipelines from your TypeScript app.

Python SDK

The same client surface, native to Python.

Nodes

The full catalog: LLMs, vector stores, parsers, tools, and more.

MCP

Expose any pipeline as an MCP tool for AI assistants.

VS Code Extension

Build, run, and debug pipelines visually in your editor.

Pipeline Reference

Every field of the portable pipeline JSON format.

04 · Community

Community

Discord

Share what you're building, swap ideas, and get help from the community.

GitHub

RocketRide is open source. Report bugs, discuss in issues, and contribute code.