DataSys

Open-source data systems

DataSys

Data management and processing for continuously evolving data: streams, dynamic graphs, vectors, online indexes, queries, and reproducible benchmarks.

17
public projects
5
technical pillars
Open
research infrastructure
Streams Dynamic graphs Vector and ANNS Approximate computing Benchmarks

Project directory

Systems and benchmarks

MorphStream logo Flagship

MorphStream

Transactional stream-processing engine for ACID transactions over streaming data.

Open repository
CBFlagship

CANDOR-Bench

Continuous ANNS evaluation under dynamic, open-world streams.

Open repository
GRFlagship

GRACE

Dynamic graph processing for continuously evolving graph data.

Open repository
SEFlagship

Sesame

Data-stream clustering system and reproducible benchmark.

Open repository

AMM-Algorithms

Framework-neutral C++ implementations of approximate matrix multiplication algorithms with Python bindings.

Open repository

LibAMM

Reproducible benchmark suite for approximate matrix multiplication systems.

Open repository

AllianceDB

Research infrastructure for modern data processing.

Open repository

CFInjectBench

Benchmark tooling for reproducible systems evaluation.

Open repository

CC-bench-tools

Utilities supporting concurrency-control benchmarks.

Open repository

SentiStream

Streaming sentiment analysis system and evaluation artifact.

Open repository

SRTFD

Streaming research implementation and experimental artifact.

Open repository

Stream Processing Reading List

Community-maintained references for stream-processing research.

Open repository

State Management Survey

Research resources for parallel and distributed state management.

Open repository

Layered ecosystem

From research idea to execution

IntelliStreamResearch incubator spanning every layer SAGEAgent, RAG, workflow, and service orchestration DataSysStreams, graphs, vectors, indexes, updates, and queries vLLM-HUSTModel runtime, scheduling, kernels, and hardware execution

Project graduation

Stable boundaries earn durable homes.

Projects graduate from IntelliStream when they have a clear public abstraction, named maintainers, reproducible evaluation, documentation, tests, licensing, and a sustainable release path.

Contribution guide