rocketride-server is a free, open source ai development platforms project written in Python and released under MIT. It has 20,000 GitHub stars, 8,673 forks and 582 open issues, and was last pushed 7 hours ago. On this registry it ranks #48 of 165 tracked projects in AI Development Platforms, with 5 head-to-head comparisons available.

What is rocketride-server?

RocketRide is an MIT-licensed open-source AI meta-harness — a C++ runtime paired with a visual pipeline builder, Python and TypeScript SDKs, and a built-in MCP server — for developers and platform teams who need to compose, test, observe, and ship durable agentic applications without vendor lock-in.

What it is

RocketRide covers what its README calls the full AI Development Lifecycle: build, stage, test, release, and maintain. It provides one place to compose, debug, observe, and deploy AI runtimes from tools a team already uses — an IDE, a terminal, a coding agent, or MCP — and it coordinates across agent harnesses rather than replacing them. Underneath sits a node library covering agents, models, vector, graph and SQL databases, OCR, tools, data stores, and named-entity recognition, with workflows expressed as portable, version-controllable JSON pipelines saved as .pipe files that run unchanged between environments. The project ships a Python SDK, a TypeScript SDK, and an MCP server, and is distributed as an extension in the VS Code Marketplace and the Open VSX Registry.

The problem it targets is the glue around an AI application rather than the application itself. Dropping a pipeline into a Python or TypeScript app is meant to take a few lines of code with no infrastructure glue, and the runtime manages Python environments, C++ toolchains, Java/Tika, and node dependencies automatically, so a clone-build-run sequence needs no manual setup. Because every node is Python-extensible and the engine is model-, tool-, and framework-agnostic, the harness substitutes for the hand-wired scripts, bespoke orchestration code, and demo-grade scaffolding that teams otherwise assemble and maintain themselves before an agent workflow can reach production.

Key capabilities

  • Rocket Builder is a visual canvas for dragging, connecting, and configuring nodes without boilerplate, with real-time observability over token usage, LLM calls, latency, and execution.
  • Pipelines are portable JSON — version-controllable, shareable, and runnable anywhere — and live as .pipe files.
  • A native multithreading C++ runtime is purpose-built for the throughput demands of AI and data workloads.
  • Pipeline nodes span LLM providers, vector databases, OCR, NER, PII anonymization, chunking strategies, and embedding models, all Python-extensible for publishing custom nodes.
  • Multi-agent workflows ship with built-in CrewAI and LangChain support, including chained agents and memory shared across pipeline runs.
  • The harness auto-detects coding agents such as Claude and Cursor, so pipelines can be built, modified, and deployed through natural language.
  • TypeScript and Python SDKs plus a built-in MCP server integrate pipelines into native apps or drive the engine programmatically.

Who uses it and how

  • Developers evaluating locally install the IDE extension, pick Local, and run a pipeline on their own machine with nothing to sign up for.
  • Application developers embed pipelines into existing Python or TypeScript codebases through the SDKs rather than building orchestration infrastructure.
  • Teams working inside Claude, Cursor, or another coding agent build and modify pipelines conversationally, using the documented start page and llms.txt.
  • Platform teams self-host on their own infrastructure through Docker or on-prem, or hand operations to RocketRide Cloud where the engine is operated for them and .pipe files run unchanged.
  • Contributors claim an issue with a single comment, add a node in Python, or fix the documentation.

Getting started

Install the RocketRide extension from the VS Code Marketplace or the Open VSX Registry, select Local, and run a pipeline on your own machine without an account or API keys. Production deployment is offered through Docker, on-premises infrastructure, or RocketRide Cloud.

How it compares

The facts name CrewAI and LangChain as frameworks RocketRide supports and coordinates across, not as products it displaces, which places it a layer above individual agent frameworks: it runs, observes, and deploys their work rather than competing for the same authoring role. The engine is entirely MIT-licensed and OSI-compliant, with no enterprise edition and nothing held behind a paywall, so the differentiator it claims is the runtime and harness layer itself rather than a commercial tier.

When to use it — and when not to

It suits teams that want a production runtime, observability, and a visual canvas without assembling dependency management and orchestration glue themselves, and that are comfortable running the engine on Docker, on-prem, or through the hosted cloud option. It is a weaker fit for organizations that need a long-settled platform: the registry records 582 open issues, the README excerpt provided here does not document the operational dependencies — database, storage, SMTP, or otherwise — that a self-hoster must run, and the listing classifies the project as Python while the runtime is written in C++, so procurement and operations reviews should start from the full documentation.

project readme (upstream, from github) — read inline

RocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++.
Build, test and publish durable agents that scale in production.

rocketride-org/rocketride-server: C++ Repository Of The Day on Trendshift   rocketride-org/rocketride-server: Repository Of The Day on Trendshift

     

RocketRide gives you one place to compose, debug, observe, and deploy AI runtimes from the tools you already use: your IDE, your terminal, your coding agent or MCP. Use any model, any tool, any framework, with zero vendor lock-in. Equipped with deep observability and backed by a battle-tested, high-throughput C++ engine, what you build is production-ready the moment it runs. It harnesses the whole stack behind your AI applications, not only the agents.

Under the hood, RocketRide is an open source meta-harness spanning the full AI Development Lifecycle (AIDLC): build, stage, test, release and maintain. With a rapidly growing node library including agents, models, vector/graph/SQL databases, OCR, tools, data stores, NER and more, it coordinates across agent harnesses while running on an enterprise-grade runtime. Self-host on your own infrastructure or deploy to RocketRide Cloud.

Home | Documentation | Python SDK | TypeScript SDK | MCP Server | For coding agents: start page, llms.txt | VS Code Marketplace | Open VSX Registry

CI Runtime version Discord MIT License

Design, test, and ship complex AI workflows from a visual canvas, right where you write code.

Drop pipelines into any Python or TypeScript app with a few lines of code, no infrastructure glue required.

Where to start

Run it locally

Install the extension, pick Local, and run a pipeline on your own machine. Nothing to sign up for.

Quick Start →
Shipping your first AI feature?

Start from what you already know: a working pipeline in three steps, no API keys.

Start here →
Want to contribute?

Claim an issue with one comment, add a node in Python, or fix the docs you're reading.

Contributing →
Want to run it without ops?

We operate the engine; your .pipe runs unchanged, with nothing to provision.

RocketRide Cloud →

Open source, MIT. The whole engine is MIT-licensed and OSI-compliant. No enterprise edition, nothing behind a paywall.

Features

Feature Description
Rocket Builder Drag, connect, and configure nodes visually, no boilerplate. Real-time observability tracks token usage, LLM calls, latency, and execution. Pipelines are portable JSON, version-controllable, shareable, and runnable anywhere.
High-Performance C++ Runtime Native multithreading purpose-built for the throughput demands of AI and data workloads. No bottlenecks, no compromises for production scale.
Pipeline Nodes LLM providers, vector databases, OCR, NER, PII anonymization, chunking strategies, embedding models, and more. All nodes are Python-extensible, build and publish your own.
Multi-Agent Workflows Built-in CrewAI and LangChain support. Chain agents, share memory across pipeline runs, and manage multi-step reasoning at scale.
Coding Agent Ready RocketRide auto-detects your coding agent: Claude, Cursor, and more. Build, modify, and deploy pipelines through natural language.
TypeScript & Python SDKs, MCP Server Integrate pipelines into native apps, drive the engine through the built-in MCP server, or build programmatic workflows into your existing codebase.
Zero Dependency Headaches Python environments, C++ toolchains, Java/Tika, and all node dependencies managed automatically. Clone, build, run, no manual setup.
One-Click Deploy Run on Docker, on-prem, or RocketRide Cloud. Production-ready architecture from day one, not retrofitted from a demo.

Quick Start

  1. Install the extension for your IDE. Search for RocketRide in the extension marketplace:

Not seeing your IDE? Open an issue · Download directly

  1. Click the RocketRide extension in your IDE

  2. Deploy a server - you'll be prompted on how you want to run the server. Choose the option that fits your setup:

    • Local (Recommended) - This pulls the server directly into your IDE without any additional setup.
    • On-Premises - Run the server on your own hardware for full control and data residency. Pull the image and deploy to Docker or clone this repo and build from source.

Your first AI feature

Whether you build web apps, integrate APIs, or run backend services, you already have the mental model.

You already know Same idea in RocketRide
A route that receives a request A source node: webhook, chat, or dropper (file drop)
Middleware chained in order Nodes, wired together on a canvas. Most are Python you can open and read
The response you return A response node
Config in git, like a Dockerfile The .pipe file: plain JSON, diffable, reviewable
Calling a service from your app The Python or TypeScript SDK: one call in, one result out

Three steps, no API keys:

  1. Run it locally. Follow the Quick Start and pick Local when asked. That's the whole install.

  2. Open a working pipeline. Open examples/document-processor.pipe in your IDE. Give it a PDF or an image and it pulls out the text (including text inside images), finds names, addresses and other personal data, and returns a cleaned copy. It runs on local models, so nothing leaves your machine. Press ▶ on the source node to start it. Its source is a webhook, so it waits for input — step 3 is how you send some.

  3. Call it from your code. The pipeline is now a function your service can call. Run it from the folder you opened in your IDE: the extension writes the engine's connection details into a .env there, and the SDK reads them automatically. Run it from anywhere else and the client falls back to RocketRide Cloud instead.

    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())
    

    TypeScript works the same way: npm install rocketride · SDK docs

Next steps, one at a time:

  • Add a model. Drop an llm_* node between the source and the response and add one API key. Same pipeline, now with an LLM in the loop.
  • Search by meaning. examples/rag-pipeline.pipe is the standard "ask questions about my documents" pattern. Needs one LLM key and a vector database (Qdrant can run locally).
  • Give it tools. An agent node is an LLM allowed to call other nodes in a loop until it's done. examples/agent-workflow.pipe shows the shape.
Words you'll see, translated
Term What it means here
Pipeline A request handler built from steps, saved as a .pipe JSON file
Node One step. Providers (OpenAI, Anthropic…), tools (GitHub, Slack…), stores, parsers
Embedding Turning text into a list of numbers so "similar meaning" becomes "nearby numbers"
Vector database A store that finds records by meaning instead of exact match
RAG Retrieve the relevant documents first, then ask the model with them in context
Agent An LLM that can call tools and nodes repeatedly until the task is done
OCR / NER / PII Read text out of images / find names, dates, organisations / detect personal data
Chunking Splitting long documents into pieces small enough to embed and retrieve

Building Your First Pipe

  1. All pipelines are recognized with the *.pipe format. Each pipeline and its configuration are JSON objects - but the extension in your IDE will render within our visual builder canvas.

  2. All pipelines begin with a source node: webhook, chat, or dropper. For specific usage, examples, and inspiration on how to build pipelines, check out our guides and documentation.

  3. Connect input lanes and output lanes by type to properly wire your pipeline. Some nodes like agents or LLMs can be invoked as tools for use by a parent node as shown below:

  1. You can run a pipeline from the canvas by pressing the ▶ button on the source node or from the Connection Manager directly.

  2. Deploy your pipelines - pick the path that fits:

    • Docker - Download the RocketRide server image and create a container. Requires Docker to be installed.

      docker pull ghcr.io/rocketride-org/rocketride-engine:latest
      docker create --name rocketride-engine -p 127.0.0.1:5565:5565 ghcr.io/rocketride-org/rocketride-engine:latest
      docker start rocketride-engine
      

      The image is amd64 only. On Apple Silicon, add --platform linux/amd64 to both docker pull and docker create.

      Clients need a non-empty key, and an engine started without one accepts any value (for example export ROCKETRIDE_APIKEY=rr_local). To use the engine's built-in MCP server, start it with -e ROCKETRIDE_APIKEY=rr_... and send that same value; the coding-agents start page has the full MCP setup.

    • Local Deployment - Download your preferred runtime as a standalone process from the Deploy page in the Connection Manager.

    • RocketRide Cloud - Skip the setup and ship straight to managed hosting. Same portable pipeline JSON, zero infrastructure to run, from prototype to production. Get started

  3. Run your pipelines as standalone processes or integrate them into your existing Python and TypeScript/JS applications utilizing our SDK.

Observability

Selecting running pipelines allows for in-depth analytics. Trace call trees, token usage, memory consumption, and more to optimize your pipelines before scaling and deploying. Find the models, agents, and tools best fit for your task.

Documentation

Everything on docs.rocketride.org is built from the docs/ tree in this repo, split by audience. docs/README.md is the full map; the short version:

Looking for Start at
Using RocketRide: quickstart, concepts, guides, cloud, self-hosting docs/public/product/ (the site, page for page)
SDK guides TypeScript · Python · MCP
Building your own client on the engine protocol docs/public/product/connect/websocket/
Contributing: setup, builder, engine internals, node authoring docs/development/
Node catalog each node's README.md under nodes/src/nodes/
Apps: VS Code extension and the shell UIs each app's own folder under apps/; how they fit the monorepo in docs/development/apps/
Pointing an AI assistant at RocketRide docs/agents/

Repo-wide contributor rules live in AGENTS.md.

Contributing

Good places to start

  • Claim an issue with one comment. Comment /assign on any open issue and it's yours. No permissions or membership needed.
  • Good first issues are labelled good first issue; help wanted marks bigger ones we'd like a hand with.
  • Add a node. Every node is a small Python package under nodes/src/nodes/. A new provider, tool, or store makes a good first contribution. Guide: Adding a New Node.
  • Fix what you just read. Docs PRs are welcome, including this README.

How it works

  • Fork, branch as /RR--, open a PR against develop, link the issue. Full process, style guides, and test commands: CONTRIBUTING.md.
  • One build tool for the whole monorepo: ./builder manages the C++ toolchain, Python environments, and Java/Tika for you. Clone, build, run.
  • Roles and decisions: GOVERNANCE.md · Releases: RELEASE.md · Security reports: SECURITY.md · Questions: Discussions, Discord, SUPPORT.md

Two ways to run RocketRide

Let us handle the infrastructure, or own every layer.


ROCKETRIDE CLOUD  ·  NOW LIVE ON-PREM
Let us run it, zero ops

The fastest way to get started. We operate the engine; you point a client at the endpoint and build. The same .pipe file runs unchanged, with no infrastructure to provision, from prototype to production.
Run it yourself, free

Docker, on-prem, or local. Full control and data residency. Open source, MIT, no lock-in, ever.
Get Started Quick Start

RocketRide Cloud  NOW LIVE

Run pipelines, not infrastructure.

With RocketRide Cloud, offload the complex, heavy lifting of production AI.
Build your pipeline once, in the same portable .pipe format, and we run it, scale it, and keep it fast. No servers, no ops, no rewrite from prototype to production.

A fraction of the cost

Our model server runs your AI workloads far more efficiently, so you pay a fraction of what standard hosting costs.
Collaborate as a team

Work together on shared pipelines. Your whole team builds, runs, and iterates in one place.
No-hassle infra

We handle everything: servers, scaling, upgrades, uptime. Nothing to provision, nothing to operate.
Higher performance, built-in scale

More throughput on the multithreaded C++ engine, with automatic scalability built in.

Connecting takes two lines. Same portable pipeline JSON, now hosted for you:

ROCKETRIDE_URI=https://api.rocketride.ai
ROCKETRIDE_APIKEY=your-api-key

Get Started   ·   Read the Cloud docs

On-Prem  FREE & MIT

Own every layer.

Run the very same engine yourself, wherever your data lives.
Docker, on-premises, or a local process in your IDE. Full control, full data residency, and zero lock-in. The exact .pipe you build on Cloud runs unchanged on your own hardware.

Full control and data residency

Your data and model calls never leave your infrastructure. Run it behind your firewall, or fully air-gapped.
Open source, MIT

The whole engine is MIT-licensed and OSI-compliant. No enterprise edition, nothing behind a paywall.
Runs anywhere

Docker, on-premises, bare metal, or local. Scale out to a cluster with the Helm chart when you need to.
The same C++ engine

Identical multithreaded runtime and execution semantics as Cloud. Move a pipeline between them anytime.

Point a client at your local engine:

ROCKETRIDE_URI=ws://localhost:5565
ROCKETRIDE_APIKEY=rr_local

Quick Start   ·   Read the On-Prem docs

Ready to ship? Deploy your pipeline on RocketRide Cloud, or run on-prem, free.

Contributors

RocketRide is built by a growing community of contributors. Whether you've fixed a bug, added a node, improved docs, or helped someone on Discord, thank you. New contributions are always welcome - check out our contributing guide to get started.

contributors

Made with ♥ in SF & EU

Frequently asked questions

Is rocketride-server free to use?

rocketride-server is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does rocketride-server do?

RocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++. Build, test and publish durable agents that scale in productio

What is rocketride-server written in?

rocketride-server is primarily written in Python. Its source is publicly available at https://github.com/rocketride-org/rocketride-server, and it has 20,000 GitHub stars.