ROSA (ROS Agent)
- Software
- Humanoids and robot learning
- Framework
ROSA is an AI assistant built on LangChain that lets people interact with ROS 1 and ROS 2 robotic systems through natural language queries.
Made by NASA Jet Propulsion Laboratory, United States (checked on github.com/nasa-jpl (opens in a new tab)).
Source on GitHub: github.com/nasa-jpl/rosa (opens in a new tab). Facts read at commit e7e5375 (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 e7e5375 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Lets users control and query ROS-based robots using natural language, built on the LangChain framework.
- Can be adapted to different robots by inheriting from the ROSA class or creating custom agents with added tools and prompts.
- Includes a TurtleSim demo that controls the simulated robot, which requires Docker.
- An IsaacSim extension is listed as coming soon, to let users control IsaacSim itself.
- Installed with pip as jpl-rosa and needs an LLM, configured as described in the wiki.
Written by Robotheca from the project's README (opens in a new tab) at commit e7e5375.
Getting started
- Difficulty
- Intermediate
- Hardware it needs, as the project states it
- Requires Python 3.9+ and ROS Noetic or higher; the TurtleSim demo needs Docker installed.
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 17 Mar 2026 on main
- Latest release
- v1.0.10 (17 Mar 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.