Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Gym
AI repositoriesEvaluate and improve models and agents using environments
git clone https://github.com/NVIDIA-NeMo/Gym.git -
AWorld
Agents & frameworksSearch, understand, reproduce, and improve an idea with ease
git clone https://github.com/inclusionAI/AWorld.git -
EasyR1
AI repositoriesEasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
git clone https://github.com/hiyouga/EasyR1.git -
CaPtain
Agents & frameworksCaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters
git clone https://github.com/waltstephen/CaPtain.git -
spomory
MCP serversExplainable graph-retrieval memory engine with an RL-trained management policy.
spomory@0.3.1 -
mobilegym
Datasets & benchmarks[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training
git clone https://github.com/Purewhiter/mobilegym.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.