#48 · Primary category： LLM Application Frameworks
rocketride-server
High-performance AI pipeline engine with C++ core, 50+ nodes, multi-model/vector DB support, and IDE integration for building and deploying LLM workflows.
Project last updated：08/29/26
GitHub Stars
7.4K
Forks
2.8K
Contributors
59
License
MIT
Why we included this project
RocketRide is aimed at teams that stitch LLM calls, vector stores, and custom logic into repeatable workflows and want something that actually runs the result, not just a diagram. Pipelines are plain portable JSON, so the same definition runs on a laptop, your own servers, or a hosted cloud, and the nodes, from LLM and embedding calls to chunking and OCR, are open to extension in Python. The C++ core matters for anyone who has watched a prototype stall under real data loads. TypeScript and Python SDKs plus an MCP server let you embed the same pipeline in a native app or surface it as tools to an AI assistant. It runs on your own infrastructure with no vendor lock-in and no separate enterprise edition, which is a real plus for smaller teams.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform