# rocketride-org/rocketride-server

High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent orchestration, all from your IDE. Includes VS Code extension, TypeScript/Python SDKs, and Docker deployment.

Repository: https://github.com/rocketride-org/rocketride-server
Canonical: https://ross.abutalabs.com/products/rocketride-server
Language: Python
License: MIT
License Family: permissive
Topics: ai, cpp, data-pipeline, data-processing, machine-learning, mcp, python, sdk, typescript, vscode-extension
Last push: 2026-08-26T21:26:43+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 92, longevity 14
- inputs: {"age_days": 203, "days_push": 7, "days_rel": 57, "gap_med": 0, "n_releases_24m": 44}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7090, forks 2753 (observed 2026-08-28T04:09:55.788323+00:00)

## What it is
RocketRide is an open-source AI pipeline engine with a high-throughput C++ runtime and 100+ Python-extensible nodes for building, debugging, and deploying LLM and ML workflows. It integrates with your IDE via a VS Code extension, offers TypeScript/Python SDKs and an MCP server, and runs entirely on your own infrastructure with Docker deployment.

## Use cases
- build and debug LLM workflows from my IDE
- orchestrate AI agents with multiple model providers
- run RAG pipelines with vector databases on my own infrastructure
- process documents with OCR and NER in a data pipeline
- deploy production AI pipelines with Docker
- visually compose AI pipelines in VS Code
- connect AI tools to my editor via MCP

## When to choose
- you need a self-hosted, vendor-neutral AI pipeline runtime with deep observability
- you want to build, debug, and deploy LLM workflows without leaving your IDE
- you need high-throughput data processing for AI/ML workloads with a C++ core
- you want broad model provider and vector database support in one engine

## When to avoid
- you only need a simple single-model LLM API wrapper
- you prefer fully managed cloud AI orchestration without self-hosting
- your stack is limited to pure Python and a C++ runtime is unnecessary overhead

## Facets
- artifact type: framework
- maturity: active
- function: etl, rag, agent-framework, llm-inference, machine-learning, nlp, ocr, vector-database, workflow-automation, mcp, developer-tools
- domain: artificial-intelligence, large-language-models, machine-learning, developer-tools, self-hosted
- platform: self-hosted, python, cpp, editor-plugin, cli, cross-platform
- tags: ai-pipeline, aide, vscode-extension, data-pipeline, llm-workflows, vector-search, -pipelines, sdk, retrieval-augmented-generation, ai-agents, data-engineering, docker, nodejs

## Member repositories
- rocketride-org/rocketride-server (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:55.788323+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:40:10.383173+00:00, confidence not recorded.
  - readme: https://github.com/rocketride-org/rocketride-server (fetched 2026-08-28T04:09:55.788323+00:00, sha edc0dabb9200)
- Data as of 2026-08-30T08:39:29.467469+00:00.