Shared flagship product / SAGE
SAGE
Streaming-computing ideas for LLM inference and agent execution.
The IntelliStream research ecosystem's shared flagship product: explicit dataflow, state, backpressure, orchestration, RAG, evaluation, and agent-facing services.
- 24
- public projects
- 05
- capability groups
- L1–L5
- learning path
Platform surfaces
From intent to running workflow.
RIDE Lab stewards SAGE core and agent-facing surfaces. Data engines stay in DataSys; model execution stays in vLLM-HUST.
SAGE Core
Execution model, operators, services, and shared lifecycle semantics.
Repository ↗ 02 / AGENTAgentic
Planning, tool selection, coordination, and composable agent workflows.
Repository ↗ 03 / RETRIEVALRAG
Document, chunking, retrieval, refinement, and knowledge workflow primitives.
Repository ↗ 04 / EXPERIENCEStudio
Visual workflow construction and an inspectable playground for SAGE pipelines.
Repository ↗Repository atlas
Public projects by capability.
The directory separates framework surfaces, reusable libraries, evaluation assets, and developer tools.
Start with the core
Install. Compose. Observe.
The homepage routes to the maintained learning path; detailed APIs and examples stay in SAGE Docs.
pip install isageShared product governance
One SAGE. Clear stewardship.
SAGE spans the ecosystem as a shared product. RIDE Lab stewards its core; DataSys and vLLM-HUST retain their data-system and inference ownership.