Robonix — The Embodied AI Operating System

A system substrate for building embodied intelligence across heterogeneous robots.

Robonix

Robonix is an operating system for embodied intelligence. It explores how to construct a robot's "brain" at the system level: a common substrate on which models can perceive, understand, plan, and act through heterogeneous robot bodies without being rewritten around every vendor SDK.

Robonix treats AI models and skills as programs and exposes robot hardware as discoverable capabilities. This separation lets robot developers integrate a body once, while model and skill developers build against shared interfaces for cameras, lidar, chassis, arms, mapping, navigation, speech, and other capabilities. The long-term goal is simple: train once, deploy on any robot.

Warning

Robonix is in early development. APIs and internal designs may change before a versioned release.

Supported Robots

Robot	Integrated hardware	Maintained by	Deployment	Catalog
AgileX Ranger Mini v3	Ranger Mini v3 chassis; Livox MID-360 lidar and IMU; Intel RealSense D435i RGB-D camera; optional AgileX Piper arm; audio	syswonder	robot-agilex-ranger_mini_v3	robonix.robot.agilex.ranger_mini_v3
DEEP Robotics Lite3	Lite3 quadruped chassis; Livox MID-360 lidar and IMU; Orbbec Gemini 330-series RGB-D camera	Bunnycxk	robot-deep_robotics-lite3	robonix.robot.deep_robotics.lite3

Each deployment links the complete robot manifest and its primitive, service, and skill dependencies. See the robot catalog for published integrations.

Quick Start

Install Robonix:

git clone --recursive --branch dev https://github.com/syswonder/robonix.git
cd robonix
curl -LsSf https://astral.sh/uv/install.sh | sh
export PATH="$HOME/.local/bin:$HOME/.cargo/bin:$PATH"
make install

Start the Webots simulator in one terminal:

export DISPLAY=:0
bash examples/webots/sim/start.sh

Boot Robonix in a second terminal with any OpenAI-compatible VLM endpoint:

export RMW_IMPLEMENTATION=rmw_zenoh_cpp
export VLM_BASE_URL=https://api.openai.com/v1
export VLM_API_KEY=sk-...
export VLM_MODEL=your-model-name

cd examples/webots
rbnx build
rbnx boot

Then run rbnx chat in a third terminal. Try go to room 101, what can you see?, or explore the office. See the Getting Started guide for the complete walkthrough.

robonix-v0.1-demo-github.mp4

Services, Skills, and Robot Integrations

Robonix grows in two directions: reusable services and skills above the system layer, and reusable robot integrations below it. Both use the same package and capability model, so a model or skill depends on what a robot can do rather than on a particular vendor implementation.

Services and skills

A service provides a general capability that many models and skills can reuse, such as mapping, navigation, memory, speech, or voice identification. Services own their runtime state and interfaces, and a deployment can replace one implementation without changing the skills that consume it.

A skill is a task-facing package and is the closest Robonix equivalent to an application in the operating-system analogy. It may orchestrate several services and primitives, wrap a learned VLA policy, or combine model inference with scripts and task-specific logic. Exploration, greeting people, transporting an object, and grasp-and-place behaviors are examples of skills. Skills remain independently installable and can be activated only when a task needs them.

Services and skills declare capabilities through Atlas. Pilot can select those capabilities while planning, and Executor dispatches the resulting RTDL nodes while preserving per-task state, concurrency, and cancellation. Browse current drivers, services, and skills in the package catalog. The package badge above is updated from the catalog API.

Hardware and robot deployments

A primitive adapts one physical device, such as a camera, lidar, chassis, arm, gripper, or audio device, to Robonix capability contracts. A robot deployment repository assembles these primitives with the complete body description, selected services and skills, and runtime configuration for one platform. This gives models and skills one consistent view of each robot. Browse complete integrations in the robot catalog.

Build services and skills

template-rbnx provides a minimal service and skill package that can be built and booted without robot hardware. Use it to define capability interfaces, configuration, lifecycle hooks, and package metadata before connecting the package to a real deployment.

Robonix Skill Toolkit supports the VLA skill workflow: collect teleoperation data, fine-tune an OpenVLA-OFT policy, and deploy the resulting skill on a real robot arm such as the AgileX Piper.

Why an Operating System?

Robonix is more than a set of robot APIs. It provides the shared execution environment in which models, skills, services, and hardware providers coexist. Models and skills use common capability contracts, while the system handles discovery, body and environment state, task execution, provider lifecycle, policy checks, cancellation, and structured history.

In the operating-system analogy, models and skills are programs and robot capabilities are resources. Long-running and concurrent plans have explicit identity and state, so they can be observed, steered, and cancelled without embedding these mechanisms independently in every skill.

System architecture

The system components below keep planning, execution, state, communication, health, and safety separate from individual hardware drivers and skills.

Component	Responsibility
atlas	Capability registry and discovery: the catalog of every registered capability and its contract
chronos	Unified clock and cross-sensor timestamp alignment (PTP / IEEE-1588)
executor	RTDL plan execution and capability dispatch (sequence / parallel / do)
keystone	User identity, persistent configuration, and access policy
liaison	Human–machine interaction gateway: chat, voice, and TUI
nexus	Communication libraries for gRPC / MCP / ROS 2 (not a standalone process)
pilot	VLM-driven planning and decision loop; emits RTDL plans for the executor
scene	Live environment estimate: object registry, semantic relations, and occupancy grid
scribe	Structured, persistent, replayable system journal for audit
sentinel	Rule-based safety gate checked before each capability dispatch
soma	Robot self-description (body model): device topology and primitive abstraction
vitals	Robot power and component-health monitoring

Robot-facing and model- or skill-facing packages fall into three open categories. They implement shared contracts from capabilities/ and may be replaced independently in each deployment:

• primitive — one device per package (camera, lidar, chassis, arm). Lives in deployment repos and per-example folders (e.g. examples/webots/primitives/).
• service — runtime functionality (mapping, navigation, semantic map, memory, speech, voiceprint). Default reference implementations ship in services/; each can be swapped out by a deployment.
• skill — user-defined reusable execution flows (grasp, place, explore, fold-clothes …). Lives wherever the deploy/integrator wants.

Supported platforms

Arch	OS / Distribution	Status
x86_64	Ubuntu 22.04	✅ Tested
x86_64	Debian 13	✅ Tested
arm64	NVIDIA Jetson — JetPack 6.2 (L4T 36.4.3, Ubuntu 22.04)	✅ Tested
x86_64 / arm64	Ubuntu 24.04 and newer	🚧 Planned
x86_64 / arm64	Arch Linux	🚧 Planned
arm64	macOS	🚧 Planned

"Tested" means the full Robonix pipeline runs end-to-end on that platform — in simulation or on a real robot: voice & interaction, task execution, body movement, scene & mapping (semantic map + spatial map), navigation, and skill execution. Other Linux distributions will likely work but are not regularly verified.

Relationship with ROS 2. Robonix itself does not depend on ROS 2 — it is one of the transports nexus offers, not a requirement of the system. If a capability provider needs the ROS 2 communication libraries and the host OS has no ROS 2 support, run that provider in a Docker container. Within a single Robonix deployment, all ROS 2-based capability providers must use the same ROS 2 distribution (Foxy / Humble / Jazzy); Humble is recommended.

Webots Environments

The simulator launcher supports multiple built-in .wbt environments. Select one explicitly with --world or ROBONIX_WEBOTS_WORLD:

bash examples/webots/sim/start.sh --world office.wbt
bash examples/webots/sim/start.sh --world apartment.wbt
ROBONIX_WEBOTS_WORLD=break_room.wbt bash examples/webots/sim/start.sh

Available worlds in examples/webots/sim/ros_ws/src/eaios_webots/worlds/: office.wbt, apartment.wbt, complete_apartment.wbt, break_room.wbt, and kitchen.wbt.

office.wbt is the fully seeded default and is recommended for a first run. Other worlds may need Cyberbotics' offline asset bundle on their first launch:

ROBONIX_WEBOTS_DOWNLOAD_ALL_ASSETS=1 \
  bash examples/webots/sim/start.sh --world apartment.wbt

The launcher caches the bundle in the webots_cache Docker volume. Network mirror overrides are documented in the Webots example.

office.wbt	apartment.wbt
complete_apartment.wbt	break_room.wbt
kitchen.wbt

Stop the example with rbnx shutdown from examples/webots, followed by bash examples/webots/sim/stop.sh from the repository root.

Quick Development

The Robonix package template contains a mock primitive, a service, and a skill that boot without robot hardware:

git clone https://github.com/syswonder/template-rbnx.git
cd template-rbnx
cp .env.example .env
# Fill in the three VLM values in .env.
set -a; source .env; set +a
rbnx build
rbnx boot

Run rbnx caps to inspect the live providers, then try rbnx chat and ask the robot to say hello. Each example package keeps its manifest, config.spec, build/start scripts, implementation, and optional capability definitions in one directory. Start there, then follow the package integration guide to publish a reusable package.

Repository Layout

system/         system components, one directory each
services/       default reference service implementations (memsearch, voiceprint, speech)
pylib/          Python SDK (robonix-api on PyPI)
capabilities/   contract TOMLs + ROS-style IDL tree (capabilities/lib/)
tools/          dev tooling — rbnx CLI + codegen
examples/       end-to-end deployments (webots, test_ci)
docs/           mdBook developer guide (submodule)
Cargo.toml      workspace for the Rust components (4 in system/, 2 in tools/)
Makefile        top-level orchestrate (build / install / fmt / check)

system/<name>/ and services/<name>/ and tools/<name>/ are each self-contained packages — Rust ones carry their own Cargo.toml, Python ones their own pyproject.toml. There is no top-level rust/ / python/ split; the runtime role is what determines where a component lives, not the implementation language.

Learn More

Dive deeper:

• Overview — control plane, one full request end-to-end
• Namespaces & contracts — how robonix/primitive/* / robonix/service/* / robonix/skill/* / robonix/system/* work
• Interface catalog — every primitive + service contract

Package Model

Robonix is built from small, swappable packages, each implementing one or more capability contracts normally grouped under a primary robonix/<kind>/<area>/* namespace. Shared framework contracts may be implemented across those provider namespaces. Namespace mismatches are diagnostic rather than a runtime authorization boundary. The contract definitions are documented in the interface catalog.

This repository contains Robonix system components, built-in reference services, and examples such as Webots/Tiago. Reusable community packages are indexed by the Robonix Package Catalog; their source stays in separate package repositories instead of being duplicated here.

Built-in services — services/

Package	Namespace	What it does
memsearch	robonix/service/memory/*	Long-term fact / preference memory; the planner queries it for relevant past context.
speech	robonix/service/speech/*	Voice I/O — ASR, TTS (incl. streaming), dialog, speaker listing.
voiceprint	robonix/service/voiceprint/*	Speaker identification (ECAPA-TDNN) — enroll / identify / list / delete.

scene (3D scene graph), atlas, executor, pilot, and liaison are system components under system/, not services.

External packages

Use the Robonix Package Catalog to find reusable primitive, service, and skill packages maintained outside this repository. The catalog also exposes a machine-readable static JSON API:

Method	Path	Parameters
GET	https://syswonder.github.io/robonix-package-catalog/api/v1/packages	none
GET	https://syswonder.github.io/robonix-package-catalog/api/v1/search	none; filter client-side
GET	https://syswonder.github.io/robonix-package-catalog/api/v1/package/<package-name>	package-name is the exact package.name, URL-encoded

Example:

const base = 'https://syswonder.github.io/robonix-package-catalog/api/v1';
const catalog = await fetch(`${base}/packages`).then(r => r.json());
const mapping = await fetch(`${base}/package/${encodeURIComponent('robonix.service.mapping')}`)
  .then(r => r.json());

Repository naming follows the catalog convention:

• primitive-[company]-[model]-[primitive_type]-rbnx for primitive packages.
• service-[service_namespace]-rbnx for service packages.
• skill-[skill_namespace]-rbnx for skill packages.

To contribute a community package:

1. Put the package source in its own GitHub repository. The repository root must contain package_manifest.yaml.
2. In package_manifest.yaml, provide catalog metadata under package: name, version, description, tags, and maintainers. maintainers is a list of Name <email@domain> entries.
3. Open a pull request to syswonder/robonix-package-catalog and add only name + repo to catalog.yaml. The catalog CI fetches the package manifest from GitHub, validates the name and metadata, generates the website/API, and deploys it to GitHub Pages.

ROS 2 and Zenoh

ROS 2 is an optional Robonix transport rather than a dependency of the system itself. Providers that use ROS 2 may run natively or in containers, but all of them in one deployment must use the same ROS 2 distribution and RMW implementation. Humble is currently recommended for robot deployments.

The Webots deployment uses rmw_zenoh_cpp and starts one rmw_zenohd router for its multi-container ROS graph. Primitive, service, and skill code continues to use normal ROS 2 APIs; the deployment selects the RMW through its process environment. See the rmw_zenoh design and the robot integration guide for topology and deployment details.

Contributors

Thanks goes to these wonderful people:

wheatfox 💻 🚧	Zhaobo Zhang 💻	Guowei Li 💻	wuzheng 💻	Kaile Liu 💻
Feiyang Li 💻	MuJue 💻	Zhenyu Zhang 💻	lhw2002426 💻	Zihao Zheng 🔧 🔣
qingfeng123 🔧 🔣	longyunhou 💻	Origamii520 💻	Xiankun Chen 💻

This project follows the all-contributors specification. Contributions of any kind welcome!

License

Mulan Permissive Software License, Version 2 (MulanPSL-2.0). See LICENSE.