Skip to content
/ dora Public

DORA (Dataflow-Oriented Robotic Architecture) is middleware designed to streamline and simplify the creation of AI-based robotic applications. It offers low latency, composable, and distributed dataflow capabilities. Applications are modeled as directed graphs, also referred to as pipelines.

License

Notifications You must be signed in to change notification settings

dora-rs/dora

Repository files navigation

dora-rs%2Fdora | Trendshift

Highlights

  • πŸš€ dora-rs is a framework to run realtime multi-AI and multi-hardware applications.
  • πŸ¦€ dora-rs internals are 100% Rust making it extremely fast compared to alternative such as being ⚑️ 10-17x faster than ros2.
  • ❇️ Includes a large set of pre-packaged nodes for fast prototyping which simplifies integration of hardware, algorithms, and AI models.

Latency benchmark with Python API for both framework, sending 40M of random bytes.

Latest News πŸŽ‰

2025
  • [03/05] dora-rs has been accepted to GSoC 2025 πŸŽ‰, with the following idea list.
  • [03/04] Add support for Zenoh for distributed dataflow.
  • [03/04] Add support for Meta SAM2, Kokoro(TTS), Improved Qwen2.5 Performance using llama.cpp.
  • [02/25] Add support for Qwen2.5(LLM), Qwen2.5-VL(VLM), outetts(TTS)

Support Matrix

dora-rs
APIs Python >= 3.7 βœ…
Rust βœ…
C/C++ πŸ†—
ROS2 >= Foxy πŸ†—
OS Linux: Arm 32 βœ… Arm 64 βœ… x64_86 βœ…
MacOS: Arm 64 βœ… x64_86 βœ…
Windows: x64_86 πŸ†—
Android: πŸ› οΈ (Blocked by: elast0ny/shared_memory#32)
IOS: πŸ› οΈ
Message Format Arrow βœ…
Standard Specification πŸ› οΈ
Local Communication Shared Memory βœ…
Cuda IPC πŸ“
Remote Communication Zenoh πŸ“
Metrics, Tracing, and Logging Opentelemetry πŸ“
Configuration YAML βœ…
Package Manager pip: Python Node βœ… Rust Node βœ… C/C++ Node πŸ› οΈ
cargo: Rust Node βœ…
  • βœ… = First Class Support
  • πŸ†— = Best Effort Support
  • πŸ“ = Experimental and looking for contributions
  • πŸ› οΈ = Unsupported but hoped for through contributions

Everything is open for contributions πŸ™‹

Node Hub

Feel free to modify this README with your own nodes so that it benefits the community.

Camera

Title Support Description Downloads License Release
PyOrbbeckSDK πŸ“ Image and depth from Orbbeck Camera Downloads License Release
PyRealsense LinuxπŸ†—
MacπŸ› οΈ
Image and depth from Realsense Downloads License Release
Video Capture βœ… Image stream from Camera Downloads License Release

Peripheral

Title Support Description Downloads License Release
Keyboard βœ… Keyboard char listener Downloads License Release
Microphone βœ… Audio from microphone Downloads License Release
PyAudio(Speaker) βœ… Output audio from speaker Downloads License Release

Actuator

Title Support Description Downloads License Release
Feetech πŸ“ Feetech Client
Dynamixel πŸ“ Dynamixel Client

Chassis

Title Support Description Downloads License Release
Agilex - UGV πŸ†— Robomaster Client Downloads License Release
DJI - Robomaster S1 πŸ“ Robomaster Client
Dora Kit Car πŸ†— Open Source Chassis Downloads License Release

Arm

Title Support Description Downloads License Release
Alex Koch - Low Cost Robot πŸ“ Alex Koch - Low Cost Robot Client
Lebai - LM3 πŸ“ Lebai client
Agilex - Piper πŸ†— Agilex arm client Downloads License Release

Robot

Title Support Description Downloads License Release
Pollen - Reachy 1 πŸ“ Reachy 1 Client
Pollen - Reachy 2 πŸ†— Reachy 2 client Downloads License Release
Trossen - Aloha πŸ“ Aloha client

Voice Activity Detection(VAD)

Title Support Description Downloads License Release
Silero VAD βœ… Silero Voice activity detection Downloads License Release

Speech to Text(STT)

Title Support Description Downloads License Release
Whisper βœ… Transcribe audio to text Downloads License Release

Object Detection

Title Support Description Downloads License Release
Yolov8 βœ… Object detection Downloads License Release

Segmentation

Title Support Description Downloads License Release
SAM2 Cudaβœ…
MetalπŸ› οΈ
Segment Anything Downloads License Release

Large Language Model(LLM)

Title Support Description Downloads License Release
Qwen2.5 βœ… Large Language Model using Qwen Downloads License Release

Vision Language Model(VLM)

Title Support Description Downloads License Release
Qwen2.5-vl βœ… Vision Language Model using Qwen2.5 VL Downloads License Release
InternVL πŸ†— InternVL is a vision language model Downloads License Release

Vision Language Action(VLA)

Title Support Description Downloads License Release
RDT-1B πŸ†— Infer policy using Robotic Diffusion Transformer Downloads License Release

Translation

Title Support Description Downloads License Release
ArgosTranslate πŸ†— Open Source translation engine Downloads License Release
Opus MT πŸ†— Translate text between language Downloads License Release

Text to Speech(TTS)

Title Support Description Downloads License Release
Kokoro TTS βœ… Efficient Text to Speech Downloads License Release

Recorder

Title Support Description Downloads License Release
Llama Factory Recorder πŸ†— Record data to train LLM and VLM Downloads License Release
LeRobot Recorder πŸ“ LeRobot Recorder helper

Visualization

Title Support Description Downloads License Release
Plot βœ… Simple OpenCV plot visualization Downloads License Release
Rerun βœ… Visualization tool Downloads License Release

Simulator

Title Support Description Downloads License Release
Mujoco πŸ“ Mujoco Simulator
Carla πŸ“ Carla Simulator
Gymnasium πŸ“ Experimental OpenAI Gymnasium bridge

Getting Started

Installation

pip install dora-rs-cli
Additional installation methods

Install dora with our standalone installers, or from crates.io:

With cargo

cargo install dora-cli

With Github release for macOS and Linux

curl --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/dora-rs/dora/main/install.sh | bash

With Github release for Windows

powershell -c "irm https://raw.githubusercontent.com/dora-rs/dora/main/install.ps1 | iex"

With Source

git clone https://github.com/dora-rs/dora.git
cd dora
cargo build --release -p dora-cli
PATH=$PATH:$(pwd)/target/release

Run

  • Run the yolo python example:
## Create a virtual environment
uv venv --seed -p 3.11

## Install nodes dependencies of a remote graph
dora build https://raw.githubusercontent.com/dora-rs/dora/refs/heads/main/examples/object-detection/yolo.yml --uv

## Run yolo graph
dora run yolo.yml --uv

Make sure to have a webcam

To stop your dataflow, you can use ctrl+c

  • To understand what is happening, you can look at the dataflow with:
cat yolo.yml
  • Resulting in:
nodes:
  - id: camera
    build: pip install opencv-video-capture
    path: opencv-video-capture
    inputs:
      tick: dora/timer/millis/20
    outputs:
      - image
    env:
      CAPTURE_PATH: 0
      IMAGE_WIDTH: 640
      IMAGE_HEIGHT: 480

  - id: object-detection
    build: pip install dora-yolo
    path: dora-yolo
    inputs:
      image: camera/image
    outputs:
      - bbox

  - id: plot
    build: pip install dora-rerun
    path: dora-rerun
    inputs:
      image: camera/image
      boxes2d: object-detection/bbox
  • In the above example, we can understand that the camera is sending image to both the rerun viewer as well as a yolo model that generates bounding box that is visualized within rerun.

Documentation

The full documentation is available on our website. A lot of guides are available on this section of our website.

What is Dora? And what features does Dora offer?

Dataflow-Oriented Robotic Architecture (dora-rs) is a framework that makes creation of robotic applications fast and simple.

dora-rs implements a declarative dataflow paradigm where tasks are split between nodes isolated as individual processes.

The dataflow paradigm has the advantage of creating an abstraction layer that makes robotic applications modular and easily configurable.

TCP Communication and Shared Memory

Communication between nodes is handled with shared memory on a same machine and TCP on distributed machines. Our shared memory implementation tracks messages across processes and discards them when obsolete. Shared memory slots are cached to avoid new memory allocation.

Arrow Message Format

Nodes communicate with Apache Arrow Data Format.

Apache Arrow is a universal memory format for flat and hierarchical data. The Arrow memory format supports zero-copy reads for lightning-fast data access without serialization overhead. It defines a C data interface without any build-time or link-time dependency requirement, that means that dora-rs has no compilation step beyond the native compiler of your favourite language.

Opentelemetry

dora-rs uses Opentelemetry to record all your logs, metrics and traces. This means that the data and telemetry can be linked using a shared abstraction.

Opentelemetry is an open source observability standard that makes dora-rs telemetry collectable by most backends such as elasticsearch, prometheus, Datadog...

Opentelemetry is language independent, backend agnostic, and easily collect distributed data, making it perfect for dora-rs applications.

ROS2 Bridge

Note: this feature is marked as unstable.

  • Compilation Free Message passing to ROS 2
  • Automatic conversion ROS 2 Message <-> Arrow Array
import pyarrow as pa

# Configuration Boilerplate...
turtle_twist_writer = ...

## Arrow Based ROS2 Twist Message
## which does not require ROS2 import
message = pa.array([{
            "linear": {
                "x": 1,
            },
            "angular": {
                "z": 1
            },
        }])

turtle_twist_writer.publish(message)

You might want to use ChatGPT to write the Arrow Formatting: https://chat.openai.com/share/4eec1c6d-dbd2-46dc-b6cd-310d2895ba15

Contributing

We are passionate about supporting contributors of all levels of experience and would love to see you get involved in the project. See the contributing guide to get started.

Discussions

Our main communication channels are:

Feel free to reach out on any topic, issues or ideas.

We also have a contributing guide.

License

This project is licensed under Apache-2.0. Check out NOTICE.md for more information.

About

DORA (Dataflow-Oriented Robotic Architecture) is middleware designed to streamline and simplify the creation of AI-based robotic applications. It offers low latency, composable, and distributed dataflow capabilities. Applications are modeled as directed graphs, also referred to as pipelines.

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published