DEDUPED Hot AI repos, turned into use cases Get the Monday 5
208 stars · Python

How to use Open ETA: what you can do with it

OpenETA is a Python embodied task agent that runs a continuous observe, reason, act, verify loop across simulators and real robots.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

5 use cases

  • Check a LIBERO evaluation manifest before spending compute

    Confirm a parallel-evaluation manifest is well formed without calling a model or MCP service.

    View prompt
    Use the OpenETA repo to validate the manifest at <manifest path> with `uv run openeta-batch --manifest <manifest path> --validate-only`. Report whether validation passed and list any errors, without connecting to a model or MCP service.

  • Run one bounded task through a Planner and the simulator

    Send a single instruction to the Open ETA agent with a fixed turn limit against a LIBERO scene.

    View prompt
    In the OpenETA repo, run `uv run openeta --once "<task text>" --max-turns 8` with the LIBERO simulator MCP service running. Report the final status and whether the environment reports task completion, and do not treat a finished process as task success.

  • Watch simulator episodes on a live Dashboard

    Start the simulator MCP service and open its Web Dashboard to observe runs as they happen.

    View prompt
    In the OpenETA repo, start `uv run python -m sim.mcp_server` and confirm the Dashboard responds at http://localhost:8765/. Report whether the page loads and which simulator backend is installed.

  • Turn an episode log into a replay video

    Rebuild the timeline of a finished episode and export it as an MP4 for review.

    View prompt
    In the OpenETA repo, run `uv run openeta-replay <episode dir> --output replay.mp4` and report the output path and whether the file was created. Verify the timeline matches the episode's recorded turns.

  • Run LIBERO episodes in parallel with human recovery

    Execute a LIBERO manifest across ten concurrent isolated episodes and save results to JSON.

    View prompt
    In the OpenETA repo, run the parallel LIBERO evaluation with `uv run openeta-batch --manifest examples/parallel_libero_eval.json --concurrency 10 --approvement reviewed_autonomy --output outputs/parallel-libero.json`. Report the number of episodes completed and the success count backed by environment receipts, and flag any episode without a receipt.

Quick start with Open ETA

  1. Check you have what it needs: Python 3.10 or newer and uv installed; An OpenAI-compatible Planner LLM or VLM endpoint for any run that reasons over a task; One simulator backend installed through scripts/setup_envs.sh, such as libero.
  2. Open OpenMOSS/OpenETA on GitHub and read the README and license.
  3. Run uv sync --extra dev in the Open ETA repository folder.
  4. Run uv run openeta-batch --manifest examples/parallel_libero_eval.json --validate-only. (inferred, check the README)
  5. Read the validation output and fix any reported manifest problem before the next step.

These steps come from our top use case, Check a LIBERO evaluation manifest before spending compute, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for OpenMOSS/OpenETA

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Open ETA alternatives · Best AI repos for Research

About this repo

  • Who it is forRobotics and embodied AI researchers or engineers who want to run, evaluate, or replay agent-driven manipulation tasks in LIBERO and other supported simulators.
  • Why it is hot208 stars
  • LanguagePython
  • Sourcegithub.com/OpenMOSS/OpenETA · Back to Hot repos

Requirements

  • Python 3.10 or newer and uv installed
  • An OpenAI-compatible Planner LLM or VLM endpoint for any run that reasons over a task
  • One simulator backend installed through scripts/setup_envs.sh, such as libero

Add this badge to your README

Maintain Open ETA? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/OpenMOSS/OpenETA.svg)](https://dedupedai.com/use-cases/openmoss-openeta/?utm_source=github&utm_medium=badge&utm_campaign=OpenMOSS-OpenETA)

HTML 

<a href="https://dedupedai.com/use-cases/openmoss-openeta/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=OpenMOSS-OpenETA"><img src="https://dedupedai.com/badge/OpenMOSS/OpenETA.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Open ETA

What is Open ETA?

OpenETA is a Python embodied task agent that runs a continuous observe, reason, act, verify loop across simulators and real robots. It is an open-source project on GitHub: https://github.com/OpenMOSS/OpenETA.

Who is Open ETA for?

Robotics and embodied AI researchers or engineers who want to run, evaluate, or replay agent-driven manipulation tasks in LIBERO and other supported simulators.

What can I do with Open ETA?

5 use cases so far, for example: Check a LIBERO evaluation manifest before spending compute; Run one bounded task through a Planner and the simulator; Watch simulator episodes on a live Dashboard. Each has steps and a copy-paste agent prompt.

What do I need to run Open ETA?

Python 3.10 or newer and uv installed; An OpenAI-compatible Planner LLM or VLM endpoint for any run that reasons over a task; One simulator backend installed through scripts/setup_envs.sh, such as libero.

What are alternatives to Open ETA?

Other hot AI repos in Research: Trustworthy Agent Simulation, Kaas, By2 KB, Md2 HD, Loci.

Is Open ETA safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.