RocketRide

// Overview

RocketRide calls itself an AI Development Environment: an open-source data pipeline builder and runtime for AI and ML workloads that lives inside the code editor you already use. You install its extension, open a `.pipe` file and get a visual canvas where nodes are dragged in and wired together by typed input and output lanes. Every pipeline starts at a source node — a `webhook`, a `chat` or a `dropper` for file drops — and ends in a response, with the steps in between doing the work.

Those steps come from a catalogue of more than 100 nodes spanning 15+ LLM providers, 9 vector databases, OCR, named-entity recognition, PII anonymisation, chunking strategies and embedding models, plus agent nodes with built-in CrewAI and LangChain support. An agent node is an LLM allowed to call other nodes in a loop until it is done, and LLMs or agents can be attached to a parent node as tools. Nodes are small Python packages, so adding a provider, tool or store means writing one more of them. The pipeline itself is saved as plain JSON, so it can be diffed, reviewed and version-controlled like any other config file.

Execution happens on a multithreaded C++ engine. The same engine runs locally inside the IDE, in Docker or on-prem (with a Helm chart for clusters), or on the project's hosted RocketRide Cloud, and the README states that a `.pipe` file moves between them unchanged. Applications call a running pipeline through the Python or TypeScript SDK, and pipelines can be exposed to AI assistants through an MCP server. The whole engine is MIT-licensed; the README states there is no enterprise edition and nothing behind a paywall, with the hosted cloud offered as an optional managed way to run it.

// Getting started

The project's own on-ramp is the IDE extension with a local engine and an example pipeline that needs no API keys; the SDK then turns that pipeline into a function your code can call.

pip install rocketride

import asyncio
from rocketride import RocketRideClient


async def main():
    async with RocketRideClient() as client:
        run = await client.use(filepath='examples/document-processor.pipe')
        out = await client.send(
            run['token'], 'Alice Smith, 12 Elm St, Springfield.', objinfo={'name': 'note.txt'}, mimetype='text/plain'
        )
        print(out)
        await client.terminate(run['token'])


asyncio.run(main())

docker pull ghcr.io/rocketride-org/rocketride-engine:latest
docker create --name rocketride-engine -p 5565:5565 ghcr.io/rocketride-org/rocketride-engine:latest

Commands and code are distilled from the project's own documentation — always check the official repo for the latest.

// How RocketRide compares

RocketRide alongside other open-source app frameworks tools AI/TLDR tracks, ranked by GitHub stars.