EmbodiedAgents (Automatika Robotics)
- Software
- Humanoids and robot learning
- Framework
A Python framework for building robot agents as graphs of ML components, such as language, vision, speech and manipulation models, wired together through ROS 2 topics and events.
Made by Automatika Robotics.
Source on GitHub: github.com/automatika-robotics/embodied-agents (opens in a new tab). Facts read at commit 0cac6d2 (opens in a new tab).
Licenses
- Code
- MIT (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit 0cac6d2 (opens in a new tab), on 22 Oct 2026.
- Commercial use
- Yes
What it does
- Recipes are single Python files that connect models that see, listen, speak, remember, plan and act.
- Components are managed ROS 2 lifecycle nodes, and the graph can reconfigure itself while running.
- Components can react to each other's outputs, and a local model can take over if a cloud model goes down.
- Manipulation covers MoveIt motion planning around objects seen by cameras, and learned vision-language-action policies served by LeRobot.
- Local built-in models can run LLM, VLM, detection, speech-to-text and text-to-speech with no server.
- Cortex plans tasks in plain language using the recipe's components as tools, and each plan runs as a routine that can be paused or aborted.
Written by Robotheca from the project's README (opens in a new tab) at commit 0cac6d2.
Getting started
- Difficulty
- Intermediate
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 21 Oct 2026 on main
- Latest release
- 0.5.1 (16 Feb 2026)
Checked on GitHub on 22 Oct 2026.
Links
Robots that can run 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.