RepoAlerts

mit-han-lab/pear

Library

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 9 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change today.

  • Licence OK

    Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

PEAR is a post-training engine for agentic robotics that trains reasoning models to use robots through reinforcement learning in simulation. It uses asynchronous GRPO on veRL, with MuJoCo and Isaac Sim simulators on a Ray cluster, and deploys trained models with a vLLM model…

Who it's for

Researchers and engineers training reasoning models for robot manipulation with reinforcement learning in simulation

How to use it

Install

bash scripts/install.sh libero_run

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up mit-han-lab/pear in my project. Follow its README: https://github.com/mit-han-lab/pear. Explain each step and check it is safe before running anything.

Star curve

783From 0 to 783 stars between 13 Nov 2026 and 22 Nov 2026.

On the radar

16 Nov 2026: #3917 Nov 2026: #5518 Nov 2026: #9319 Nov 2026: #93
Best place #39, on 16 Nov 2026. In the top 100 on 4 of the last 36 days.

Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.

Records

  • Best place on RepoAlerts: #39, on 16 Nov 2026
  • In the top 100 for 4 days since 16 Nov 2026

Alternatives

Similar projects named in its profile. Each link searches the directory.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![mit-han-lab/pear on RepoAlerts](https://repoalerts.com/badge/mit-han-lab/pear.svg)](https://repoalerts.com/repo/mit-han-lab/pear?ref=badge)
Share on X

  • NVlabs/ASPIRE

    A research framework for robotics in which an LLM-driven coding agent refines sensorimotor skills through iterative debugging and evolutionary search instead of gradient-based training. Evaluated on L

    AgentAI agentsPython · 1,049 stars · +39 this week · 137 days old

  • ArcheOne-AI/RoboScript

    Agent framework for robot manipulation that learns a task from one demonstration by rehearsing it in a simulator and storing the learned knowledge in the model's context rather than in weights. Valida

    AgentAI agentsPython · 336 stars · +97 this week · 17 days old

  • datawhalechina/agentic-rl-lab

    A collection of reproductions and tutorials of reinforcement learning algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, OPSD, Search-R1, ReTool and ALFWorld. Each method is explained and imp

    ResourceAI agentsPython · 1,551 stars · +85 this week · 139 days old

  • apple-aiml-research/ml-halo

    Research code for the HALO paper on perceptive humanoid motion learned from simulation. It covers synthetic data generation (Infinigen scenes, Kimodo motion, Isaac and MuJoCo rendering), training of a

    Models & inferencePython · 476 stars · +79 this week · 18 days old

  • Agentic-Intelligence-Lab/CleanRUA

    A collection of single-file Python implementations of robot-use agents, where each file contains the prompt, tools and interaction loop of one agent. Agents include Direct, Code, Delegate and Monitor

    AI skillAI agentsPython · 85 stars · +85 this week · 7 days old

  • shengshu-ai/Motus2

    A research world model for robotic dexterous manipulation that uses one shared-weight model as a policy proposing action chunks, a simulator predicting their visual outcomes, and an evaluator scoring

    AI agentsPython · 588 stars · +70 this week · 72 days old