ArchestackBest of Open-Source AI: List on GitHub ↗3 stars (opens in a new tab)

#2121st of 28 in Agent platforms

rocketride-server

Visual AI pipeline builder in VS Code with a C++ runtime

Documentation ↗ (opens in a new tab)Website ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
Stars
17.8k
License
MIT
Last commit
Oct 2026
Last release
Sep 2026
Language
Python

Missed the latest GitHub check; these facts may be older.

Overview

RocketRide is a pipeline builder and runtime for AI workloads. Pipelines are saved as portable JSON .pipe files, built on a visual canvas in a VS Code extension, and run by a multithreaded C++ engine. It ships 100+ nodes covering 15+ LLM providers, 9 vector databases, OCR, NER and agents, with Python and TypeScript SDKs and an MCP server.

Who it is for: Developers building AI pipelines, RAG and agent backends from their IDE

Strengths

  • Pipelines are plain JSON .pipe files, diffable and version-controllable
  • 100+ nodes, including 15+ LLM providers and 9 vector databases; nodes are Python-extensible
  • Built-in tracing of token usage, LLM calls, latency and call trees
  • MIT license with no enterprise edition; Python and TypeScript SDKs plus MCP server

Weaknesses

  • Visual builder is delivered as an IDE extension (VS Code or Open VSX editors)
  • SDK falls back to RocketRide Cloud when run outside the extension's folder
  • RAM and GPU requirements are not stated in the README
  • RAG example needs an LLM key and a vector database such as Qdrant

What it needs

  • Needs VS Code or compatible IDE, Docker (optional), Vector database (for RAG), LLM API key (for hosted models)
  • Models: OpenAI, Anthropic, 15+ LLM providers, local models
  • port 5565

Also in Agent platforms

See all 28
Also in Agent platforms
RankProjectScore
1LangflowVisual builder for AI agents and workflows, exposed as API or MCP server155.7k starsMIT81 out of 100
2daily_stock_analysisDaily LLM stock analysis for A-share, HK, US and other markets, pushed to chat apps66.4k starsMIT80 out of 100
3mindshubAgent workspace for knowledge work, with swappable open agent harnesses Live demo ↗ (opens in a new tab)39.8k starsMIT78 out of 100
#4deer-flowAgent harness that runs sub-agents, memory and sandboxed skills for long tasks83.9k starsMIT76 out of 100
#5DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs Live demo ↗ (opens in a new tab)158.5k starscustom license75 out of 100