Repolode
Submit
rocketride-org

rocketride-org/rocketride-server

Open source AI pipeline engine with a C++ runtime and visual builder inside VS Code, for building LLM workflows with many model providers and vector databases.

View on GitHub
Stars
19,945
Forks
8,686
Open issues
510
Last commit
15 hours ago

What is it?

RocketRide is an AI development environment that runs pipelines built from nodes: model providers, vector databases, OCR, NER, chunking, embeddings, and agent nodes. Pipelines are defined as portable JSON .pipe files, composed on a visual canvas in VS Code or driven from the CLI, and executed by a multithreaded C++ runtime.

The project targets developers who want to add LLM features to existing applications without hand-wiring infrastructure. A pipeline can be called from Python or TypeScript SDKs, exposed as tools over MCP, or run locally, in Docker, or on-premises. Node dependencies such as Python environments and Java/Tika are managed by the included build tool.

Observability features trace call trees, token usage, latency, and memory for running pipelines. The engine is MIT-licensed, and the same pipeline format is also used by the hosted RocketRide Cloud service.

Key features

  • 01Visual pipeline builder inside VS Code with portable JSON .pipe files
  • 02Multithreaded C++ runtime for executing pipelines
  • 03100+ nodes covering LLM providers, vector databases, OCR, and NER
  • 04Python and TypeScript SDKs plus an MCP server for calling pipelines
  • 05Tracing of token usage, latency, and memory for running pipelines
  • 06Docker and on-premises deployment

Use cases

  • Building retrieval-augmented question answering over your own documents
  • Extracting text and removing personal data from PDFs and images with local models
  • Adding an LLM step to an existing Python or TypeScript backend through the SDK
  • Creating agent workflows where an LLM calls other pipeline nodes as tools

Quick start

  1. 1

    Install the RocketRide extension from your IDE's marketplace

  2. 2

    Click the RocketRide extension in your IDE

  3. 3

    Deploy a server by choosing Local (recommended) when prompted

  4. 4

    Optionally install the Python SDK

    pip install rocketride

Things to know

  • The visual pipeline builder requires VS Code or another supported IDE.
  • Running LLM and cloud nodes needs API keys from the relevant providers.
  • On-premises setup requires Docker or building from source, which adds setup effort.

In collections

PDF, OCR & document tools

Topics

#llm#ai-pipeline#rag#vector-database#agent#vscode-extension#data-pipeline#ocr#ai#cpp

FAQ

What is rocketride-server?
Open source AI pipeline engine with a C++ runtime and visual builder inside VS Code, for building LLM workflows with many model providers and vector databases. RocketRide is an AI development environment that runs pipelines built from nodes: model providers, vector databases, OCR, NER, chunking, embeddings, and agent nodes. Pipelines are defined as portable JSON .pipe files, composed on a visual canvas in VS Code or driven from the CLI, and executed by a multithreaded C++ runtime.
Is rocketride-server free to use? What license does it have?
rocketride-server is open source under the MIT license. Check the license terms before using it in commercial products.
Is rocketride-server still maintained?
Actively maintained. The last commit to rocketride-server was on Nov 5, 2026.
What can I use rocketride-server for?
Building retrieval-augmented question answering over your own documents Extracting text and removing personal data from PDFs and images with local models Adding an LLM step to an existing Python or TypeScript backend through the SDK Creating agent workflows where an LLM calls other pipeline nodes as tools
How do I install rocketride-server?
Install the RocketRide extension from your IDE's marketplace Click the RocketRide extension in your IDE Deploy a server by choosing Local (recommended) when prompted Optionally install the Python SDK: pip install rocketride
Where can I get rocketride-server?
The source code and installation instructions are on GitHub: https://github.com/rocketride-org/rocketride-server

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects