Repositories list

• harbor

  Public
  Harbor is a framework for running agent evaluations and creating and using RL environments.

  Python

  •

  Apache License 2.0

  •1.7k1.7k forks•33 stars•00 issues•66 pull requests•Updated Sep 3, 2026Sep 3, 2026

• SkyRL

  Public
  SkyRL: A Modular Full-stack RL Library for LLMs

  Python

  •

  Apache License 2.0

  •420420 forks•11 star•00 issues•22 pull requests•Updated Sep 1, 2026Sep 1, 2026

• harbor-aq

  Public
  Framework for evaluating and improving agents

  Python

  •

  Apache License 2.0

  •1.7k1.7k forks•00 stars•00 issues•11 pull request•Updated Aug 28, 2026Aug 28, 2026

• mcp-atlas

  Public
  MCP Atlas

  Python

  •

  MIT License

  •3838 forks•00 stars•00 issues•00 pull requests•Updated Aug 27, 2026Aug 27, 2026

• RL

  Public
  Scalable toolkit for efficient model reinforcement

  Python

  •

  Apache License 2.0

  •547547 forks•00 stars•00 issues•00 pull requests•Updated Aug 24, 2026Aug 24, 2026

• verl

  Public
  verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

  Python

  •

  Apache License 2.0

  •4.5k4.5k forks•00 stars•00 issues•11 pull request•Updated Aug 4, 2026Aug 4, 2026

• swift-anvil

  Public
  Python

  •00 forks•33 stars•00 issues•00 pull requests•Updated May 6, 2026May 6, 2026

• anvil

  Public
  Python

  •1111 forks•88 stars•33 issues•11 pull request•Updated Mar 28, 2026Mar 28, 2026

• mle-reasoning-environment

  Public
  AfterQuery's MLE Reasoning Harness

  Python

  •11 fork•00 stars•00 issues•00 pull requests•Updated Feb 2, 2026Feb 2, 2026

• IDE-Bench

  Public
  Comprehensive framework for evaluating AI IDE agents on real-world, cross-stack SWE tasks

  Python

  •1010 forks•66 stars•00 issues•00 pull requests•Updated Feb 1, 2026Feb 1, 2026

• RL-Take-Home

  Public
  RL Intern Take-Home Assignment

  Python

  •11 fork•00 stars•00 issues•00 pull requests•Updated Dec 30, 2025Dec 30, 2025

• appbench.ai-docs

  Public
  public documentation for appbench.ai

  11 fork•11 star•11 issue•00 pull requests•Updated Dec 10, 2025Dec 10, 2025

• FullStackBoilerplate

  Public
  Python

  •77 forks•00 stars•00 issues•00 pull requests•Updated Oct 27, 2025Oct 27, 2025

• vader

  Public
  Java

  •33 forks•1010 stars•11 issue•00 pull requests•Updated May 24, 2025May 24, 2025

• FinanceQA

  Public
  FinanceQA: A Benchmark for Evaluating Financial Analysis Capabilities in Large Language Models

  33 forks•99 stars•00 issues•00 pull requests•Updated Feb 2, 2025Feb 2, 2025