RAI
- Software
- Humanoids and robot learning
- Framework
RAI is an agent framework for building and deploying embodied AI features on robots, with multi-agent, human-robot interaction and multi-modal support.
Made by Robotec.ai, Poland (checked on github.com/RobotecAI (opens in a new tab)).
Source on GitHub: github.com/RobotecAI/rai (opens in a new tab). Facts read at commit b018729 (opens in a new tab).
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit b018729 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Core multi-agent system with human-robot interaction and multi-modal inputs and outputs.
- Tool that synthesizes robot embodiment information from documentation, images and URDFs.
- Speech-to-text and text-to-speech packages.
- Connects RAI to simulation environments and includes a benchmarking suite for agents, models, tools and simulators.
- Object detection based on open-set models, and navigation integration with NoMaD.
- Planned rai_finetune package to finetune LLMs on embodied data is not yet finished.
Written by Robotheca from the project's README (opens in a new tab) at commit b018729.
Getting started
- Difficulty
- Advanced
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 12 Oct 2026 on main
- Latest release
- 2.12.4 (8 Sept 2026)
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.