RocketRide Docs

Build AI workflows that run anywhere

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. Build visually in VS Code, integrate with a few lines of TypeScript or Python, and trace every LLM call, token, and millisecond as it happens.

RocketRide sits one layer below your application and your agent framework. It handles the models, vector stores, observability, and orchestration that come after the code, so you can swap providers, scale workloads, and ship production AI without rebuilding your stack every time the landscape shifts.

Quickstart

QuickstartInstall the extension, deploy a local runtime, and run your first pipeline in minutes.Developer GuidesDrop pipelines into your TypeScript or Python application with the SDKs.DeployRun on Docker, on-prem, or one-click deploy to RocketRide Cloud.Discord CommunityJoin the Discord, ask questions, show what you built.

ProtocolsConnect over WebSocket, or expose any pipeline as an MCP tool for AI assistants.

RocketRide CloudManaged hosting at rocketride.ai. Same pipeline JSON, zero infrastructure.

ContributeChart the course to the next frontier. Join the RocketRide journey on GitHub.