| --- |
| title: OpenRAL |
| emoji: ๐ค |
| colorFrom: indigo |
| colorTo: indigo |
| sdk: static |
| pinned: true |
| short_description: The open harness for physical AI |
| license: apache-2.0 |
| thumbnail: >- |
| https://cdn-uploads.huggingface.co/production/uploads/679bec571de528e679aae409/KR7hrL_kADf-oPybj7Q0C.png |
| --- |
| |
| <div align="center"> |
|
|
| # OpenRAL |
|
|
| **The open harness for physical AI.** OpenRAL is the open-source **Robot Agentic Layer** (harness) for embodied AI. It unifies fast policies, slow reasoning, reward signals, perceptual AI and classical control into a **typed, traceable, safety-first runtime** โ on real hardware and in simulation. One fixed harness, swappable **rSkills**. |
|
|
| [](https://openral.com) |
| [](https://github.com/OpenRAL/openral) |
| [](https://github.com/OpenRAL/openral/blob/master/LICENSE) |
| [](https://github.com/OpenRAL/openral) |
| [](https://docs.ros.org/en/jazzy/) |
| [](https://discord.gg/3paXT2bVyB) |
|
|
| </div> |
|
|
| --- |
|
|
| ## What is OpenRAL? |
|
|
| A VLA alone is not an agent. OpenRAL wraps it in the loop it needs โ a typed, layered runtime between a robot's motor API and a task planner: |
|
|
| - **The harness** โ a slow LLM **reasoner** (S2) planning in typed tool-calls, fast visuomotor policies (S1, 30โ200 Hz) executing action chunks, perception and world state keeping both honest, and a separate C++ deny-by-default **safety kernel** gating every command. Pydantic v2 contracts at every layer boundary. |
| - **rSkills** โ every capability the agent has is an rSkill, not just VLAs: detectors, scene VLMs, reward monitors, MoveIt 2 / Nav2 actions and reasoner playbooks, packaged as Hub repos with weights, a typed `rskill.yaml` manifest and reproducible eval. Install like a model: `openral rskill install OpenRAL/rskill-smolvla-franka_panda-libero_spatial-bf16`. Swap any of them; the harness never changes. |
| - **Benchmark โ sim โ real** โ the same agent runs benchmark suites, headless sim rollouts and real hardware, and every run is an OpenTelemetry trace you can replay, audit, or fold into a LeRobot dataset flywheel. |
|
|
| --- |
|
|
| ## What's shipped |
|
|
| | | | |
| |---|---| |
| | ๐ค **15+ robot platforms** | SO-100/SO-101, Franka Panda, UR5e/UR10e, ALOHA bimanual, Galaxea A1, OpenArm v2, Unitree H1/G1, Rethink Sawyer, Fourier GR1, WidowX | |
| | ๐ง **30+ rSkills** | SmolVLA, ฯ0.5, GR00T N1.7, LingBot-VLA 2.0, InternVLA-N1 (VLN), MolmoAct2, xVLA, ACT, Diffusion Policy, RLDX-1, OpenVLA-OFT, RT-DETR, OmDet-Turbo, LocateAnything, Qwen3.5-4B VLM, Robometer-4B, MoveIt 2 / Nav2 actions, playbooks | |
| | ๐ฎ **Benchmark suites** | LIBERO, MetaWorld, ManiSkill3, SimplerEnv, RoboCasa, RoboTwin 2.0, RLBench, gym-aloha, gym-pusht | |
| | ๐ฌ **Sim engines** | MuJoCo, Isaac Sim, Genesis, SAPIEN, robosuite, CoppeliaSim | |
| | ๐ก **Sensors & perception** | RealSense D435/D435i/D415, Luxonis OAK-D Pro, USB UVC, Robotiq FT-300 ยท Depth Anything 3 metric depth ยท cuVSLAM stereo SLAM | |
|
|
| --- |
|
|
| ## Quick start |
|
|
| ```bash |
| curl -fsSL https://raw.githubusercontent.com/OpenRAL/openral/master/scripts/install.sh | bash |
| openral doctor |
| openral rskill install OpenRAL/rskill-smolvla-franka_panda-libero_spatial-bf16 |
| openral sim run scenes/benchmark/libero_spatial.yaml |
| ``` |
|
|
| --- |
|
|
| ## Community & support |
|
|
| - ๐ฌ **[Discord](https://discord.gg/3paXT2bVyB)** โ questions, help, design chat |
| - ๐ง **[hello@openral.com](mailto:hello@openral.com)** โ general enquiries |
| - ๐ **Security disclosures:** [security@openral.com](mailto:security@openral.com) โ never a public issue |
|
|
| --- |
|
|
| ## License |
|
|
| OpenRAL is **Apache-2.0**. Third-party model weights keep their own upstream licenses; the loader surfaces each weight's license at install time. |
|
|
