Embodied Agents (mbodi)
- Software
- Humanoids and robot learning
- Framework
A Python toolkit that plugs large language, robot-control and vision models into existing robot software with a few lines of code. It aims at research and prototyping.
Made by mbodi ai, United States (checked on github.com/mbodiai (opens in a new tab)).
Source on GitHub: github.com/mbodiai/embodied-agents (opens in a new tab). Facts read at commit b0ae7f7 (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 b0ae7f7 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Provides language, motor and sensory agents that always return a string, a Motion or a SensorReading respectively.
- AutoAgent picks the right agent for a given task and model.
- Supports remote inference through Gradio, httpx and LLM clients such as OpenAI, Anthropic, Gemini, Ollama and vLLM.
- Motor agents include OpenVLA; sensory agents cover depth estimation, object detection and image segmentation.
- Sample class converts observations and actions to Gym spaces, arrays, tensors, Hugging Face datasets and Pydantic models.
- Records robot datasets natively via the Recorder and Replayer classes, with optional upload to the Hugging Face hub.
Written by Robotheca from the project's README (opens in a new tab) at commit b0ae7f7.
Getting started
- Difficulty
- Intermediate
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 16 Dec 2025 on main
- Latest release
- None published on GitHub
Checked on GitHub on 16 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.