
rocketride-server
Open source engine to build, test and deploy AI pipelines from your IDE or code
rocketride-server is an open-source AI tool for developer tools. It is available on VS Code, CLI, API, Self-hosted, Linux, macOS and Windows.
- Pricing
- Open source
- Platforms
- VS Code, CLI, API
- GitHub stars
- 20K
- Last commit
- Language
- Python
- License
- MIT
Similar tools
About rocketride-server
RocketRide packages the components of an AI application, such as model calls, vector stores, OCR and PII detection, into visual pipelines saved as portable JSON files. You assemble and debug these pipelines on a canvas inside a VS Code or Open VSX extension, then run them on a local engine or on RocketRide Cloud without rewriting them.
The engine is written in C++ with a Python runtime for nodes, and the project offers Python and TypeScript SDKs so an existing service can call a pipeline like a function. Built-in observability traces token usage, LLM calls, latency and memory for each run.
The project suits developers who want to prototype retrieval, document processing or multi-agent flows and then host them on their own infrastructure, since the engine is MIT licensed and can run in Docker, on-prem or fully offline.
What it does
- Visual pipeline builder
- Connect source, model, tool and response nodes on a canvas and save the result as a .pipe JSON file.
- Python and TypeScript SDKs
- Call a running pipeline from application code with a few lines using either language's client library.
- Built-in run observability
- Trace call trees, LLM calls, token usage, latency and memory consumption for each pipeline run.
- Document processing nodes
- Includes OCR, named entity recognition, PII anonymization and chunking nodes for document workflows.
- Self-hosted or cloud runtime
- Run the same pipeline locally in Docker, on-prem, or on RocketRide Cloud without changing its file.
- MCP server included
- Drive the engine from AI coding assistants through a built-in Model Context Protocol server.
Good for
- Prototype a retrieval-augmented question answering pipeline over your own documents
- Extract text from PDFs and images and strip personal data before storage
- Expose a multi-step LLM workflow as a callable function inside an existing service
- Let a coding assistant build and modify pipelines through natural language
Pricing
Open source
Free and MIT-licensed to self-host; hosted RocketRide Cloud is also offered.
Prices change. Check rocketride.ai before you buy.
rocketride-server FAQ
Is RocketRide open source?
Yes. The engine is released under the MIT license and the project states there is no enterprise edition.
Can I run rocketride-server without paying?
Yes. The on-prem option runs locally, in Docker or on your own hardware at no cost, while RocketRide Cloud is a hosted option.
Do I need API keys to try rocketride-server?
The quick start pipeline runs on local models and needs no API keys, though adding a model node requires a provider key.
Which languages can I call pipelines from?
The project provides SDKs for Python and TypeScript.
Is rocketride-server free?
Yes. rocketride-server is open source, so you can use and self-host it for free.
What are the best alternatives to rocketride-server?
The closest alternatives to rocketride-server are Text Generator, Solarian, Berri.ai, codesnippets and theia.
Where this comes from
- Description: written from the project's README and the project's website.