DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Evo Bot

EvoBot is a Python agent and reusable skill library that runs manipulation tasks in the LIBERO robot benchmark, reporting 25 of 30 tasks passed.

Trended earlier

ABC12345anouys/EvoBot on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

4 use cases

  • Reproduce the 25 of 30 LIBERO evaluation result

    Run all 30 LIBERO tasks from the three suites and check the pass count against the README.

    View prompt
    Work in the EvoBot repo at <repo path>. Set up the Python 3.10 environment and PYTHONPATH from the README, then run `bash scripts/verify_30.sh 8 verify`. Report the number of passed tasks out of 30 and list any failed task names. Verify that logs/libero_agent_progress.json has an entry for every task you ran.

  • Watch one LIBERO task learn across retry attempts

    Run a single LIBERO task with a persistent simulator and see how failures change the next attempt.

    View prompt
    In the EvoBot repo at <repo path>, run the task libero_spatial:0 with scripts/ipc_learn.py and --max-attempts 10. Report how many attempts were used, whether the task passed, and the failure reasons you saw. Verify that the progress entry for libero_spatial:0 matches the outcome you report.

  • Resume the LIBERO agent runner and skip passed tasks

    Run the agent over all three LIBERO suites so that tasks already passed are skipped on each rerun.

    View prompt
    In the EvoBot repo at <repo path>, run darwin.agents.libero_runner for the three suites with the PYTHONPATH and MUJOCO_GL settings from the README. Report how many tasks were skipped as already passed and how many were newly run. Verify the counts against the entries in logs/libero_agent_progress.json.

  • Regenerate LIBERO task specs with deterministic ordering

    Rebuild subgoal orders for LIBERO tasks using only the automatic sort, with no model calls.

    View prompt
    In the EvoBot repo at <repo path>, run `python scripts/gen_task_specs.py --no-llm`. Report how many task spec files were written and confirm that each has source set to deterministic. Verify by opening one spec and comparing its subgoals list with the reference_order field.

How to use Evo Bot

  1. Check you have what it needs: Python 3.10 in a conda environment (the README says Python 3.12 cannot run robosuite and its dependencies); LIBERO source code, added to PYTHONPATH as described in the README; MuJoCo and robosuite (bundled with LIBERO).
  2. Open ABC12345anouys/EvoBot on GitHub and read the README and license.
  3. Create the environment with conda create -n darwin python=3.10 -y && conda activate darwin
  4. Install the project with pip install -e . and the base dependencies with pip install mujoco h5py numpy pyyaml
  5. Install LIBERO following its official instructions, then set export PYTHONPATH=$PWD:/path/to/LIBERO and export MUJOCO_GL=egl
  6. Run the full verification with bash scripts/verify_30.sh 8 verify

These steps come from our top use case, Reproduce the 25 of 30 LIBERO evaluation result, which also has a copy-paste agent prompt.

Evo Bot alternatives · Best AI repos for Research

About this repo

  • Who it is forRobotics and machine learning researchers who want to reproduce or extend LIBERO manipulation results without reinforcement learning or runtime LLM calls.
  • Why it is hot
  • LanguagePython
  • Sourcegithub.com/ABC12345anouys/EvoBot · Back to Hot repos

Requirements

  • Python 3.10 in a conda environment (the README says Python 3.12 cannot run robosuite and its dependencies)
  • LIBERO source code, added to PYTHONPATH as described in the README
  • MuJoCo and robosuite (bundled with LIBERO)
  • MUJOCO_GL=egl on machines without a display
  • DEEPSEEK_API_KEY only if you want to regenerate task specs with the model
Maintain Evo Bot? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/abc12345anouys-evobot.svg)](https://dedupedai.com/use-cases/abc12345anouys-evobot/?ref=badge)

More badge styles and HTML

Questions about Evo Bot

What is Evo Bot?

EvoBot is a Python agent and reusable skill library that runs manipulation tasks in the LIBERO robot benchmark, reporting 25 of 30 tasks passed. It is an open-source project on GitHub: https://github.com/ABC12345anouys/EvoBot.

Who is Evo Bot for?

Robotics and machine learning researchers who want to reproduce or extend LIBERO manipulation results without reinforcement learning or runtime LLM calls.

What can I do with Evo Bot?

4 use cases so far, for example: Reproduce the 25 of 30 LIBERO evaluation result; Watch one LIBERO task learn across retry attempts; Resume the LIBERO agent runner and skip passed tasks. Each has steps and a copy-paste agent prompt.

What do I need to run Evo Bot?

Python 3.10 in a conda environment (the README says Python 3.12 cannot run robosuite and its dependencies); LIBERO source code, added to PYTHONPATH as described in the README; MuJoCo and robosuite (bundled with LIBERO); MUJOCO_GL=egl on machines without a display.

What are alternatives to Evo Bot?

Other hot AI repos in Research: Scientific Agent Skills, Speaker Mem R1, DSH Council, AI Engineering Course, AI System Design.

Is Evo Bot 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.