Skip to content

Twitter GitHub Org's stars GitHub Org's follows GitHub license

OpenDILab is the first decision intelligence platform covering the most comprehensive algorithms and applications both in academia and industry. Since July 2021, OpenDILab has been officially open-sourced at the World Artificial Intelligence Conference(WAIC) opening ceremony.

As an important part of OpenXLab from Shanghai AI Laboratory, OpenDILab features a complete set of training and deployment frameworks for decision intelligence, consisting of the application ecological layer, algorithm abstraction layer, distributed management layer, and distributed execution layer. OpenDILab also supports full-scale scheduling system optimization from a single machine to the joint training of thousands of CPU/GPU.


OpenDILab contributes to the integration of the latest and most comprehensive achievements in academia as well as the standardization of complex problems in the industry. Our future vision is to promote the development of AI from perceptual intelligence to decision intelligence, taking AI technology to a higher level of the general intelligence era.

Pinned Loading

  1. DI-engine DI-engine Public

    OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

    Python 3.3k 394

  2. PPOxFamily PPOxFamily Public

    PPO x Family DRL Tutorial Course(决策智能入门级公开课:8节课帮你盘清算法理论,理顺代码逻辑,玩转决策AI应用实践 )

    Python 2.1k 183

  3. DI-star DI-star Public

    An artificial intelligence platform for the StarCraft II with large-scale distributed training and grand-master agents.

    Python 1.3k 119

  4. LightZero LightZero Public

    [NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

    Python 1.3k 141

  5. CleanS2S CleanS2S Public

    High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体!

    Python 361 34

  6. LMDrive LMDrive Public

    [CVPR 2024] LMDrive: Closed-Loop End-to-End Driving with Large Language Models

    Jupyter Notebook 721 63

Repositories

Showing 10 of 48 repositories
  • DI-engine Public

    OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

    opendilab/DI-engine’s past year of commit activity
    Python 3,298 Apache-2.0 394 6 (1 issue needs help) 13 Updated Mar 13, 2025
  • awesome-ui-agents Public

    A curated list of of awesome UI agents resources, encompassing Web, App, OS, and beyond (continually updated)

    opendilab/awesome-ui-agents’s past year of commit activity
    159 Apache-2.0 17 1 0 Updated Mar 12, 2025
  • LightZero Public

    [NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

    opendilab/LightZero’s past year of commit activity
    Python 1,300 Apache-2.0 141 4 19 Updated Mar 11, 2025
  • DI-engine-docs Public

    DI-engine docs (Chinese and English)

    opendilab/DI-engine-docs’s past year of commit activity
    Python 295 Apache-2.0 63 0 2 Updated Mar 10, 2025
  • DI-sheep Public

    羊了个羊 + 深度强化学习(Deep Reinforcement Learning + 3 Tiles Game)

    opendilab/DI-sheep’s past year of commit activity
    Python 440 Apache-2.0 25 0 0 Updated Mar 10, 2025
  • CleanS2S Public

    High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体!

    opendilab/CleanS2S’s past year of commit activity
    Python 361 Apache-2.0 34 1 1 Updated Mar 5, 2025
  • PsyDI Public

    PsyDI: Towards a Personalized and Progressively In-depth Chatbot for Psychological Measurements. (e.g. MBTI Measurement Agent)

    opendilab/PsyDI’s past year of commit activity
    TypeScript 162 Apache-2.0 15 0 1 Updated Feb 28, 2025
  • awesome-RLHF Public

    A curated list of reinforcement learning with human feedback resources (continually updated)

    opendilab/awesome-RLHF’s past year of commit activity
    3,795 Apache-2.0 232 1 1 Updated Feb 19, 2025
  • GenerativeRL Public

    Python library for solving reinforcement learning (RL) problems using generative models (e.g. Diffusion Models).

    opendilab/GenerativeRL’s past year of commit activity
    Python 122 Apache-2.0 8 0 1 Updated Feb 18, 2025
  • awesome-model-based-RL Public

    A curated list of awesome model based RL resources (continually updated)

    opendilab/awesome-model-based-RL’s past year of commit activity
    1,029 Apache-2.0 58 0 0 Updated Feb 17, 2025