Skip to content
@walkinglabs

walkinglab

Empower everyone to teach machines to think.

WalkingLab

WalkingLab is an open-source AI lab exploring the future of intelligent systems, including agentic AI, LLM systems, reinforcement learning (RL), and embodied intelligence.

Our mission is to make frontier AI accessible to everyone — enabling more people to understand, build, and create intelligent systems through open-source projects, hands-on tutorials, and reproducible experiments.

We believe everyone can teach machines how to think.

If you are interested in agents, RL, LLM systems, embodied intelligence, or next-generation AI infrastructure, welcome to explore and build with WalkingLabs.

Discord

WalkingLabs community banner

中文介绍

WalkingLab

WalkingLab 是一个探索下一代智能系统的开源 AI 实验室,关注 Agentic AI、智能体系统(Agents)、大语言模型系统(LLM Systems)、强化学习(RL)与具身智能(Embodied Intelligence) 等前沿方向。

我们相信,人工智能的未来不应该只属于少数人。

WalkingLab 致力于让最前沿的人工智能知识向每个人开放,让更多人能够理解、实现并创造智能系统。

我们相信:每个人,都能教会机器思考。

我们通过开源项目、实践教程与可复现实验,将前沿智能研究转化为人人可探索、可构建的技术实践。

重点方向

  • Agentic AI:面向复杂任务的自主智能体架构、规划与执行系统
  • LLM Systems:大语言模型训练、推理、评估与基础设施
  • Reinforcement Learning:强化学习与智能体能力优化
  • Multi-Agent Systems:多智能体协作、通信与任务编排机制
  • Embodied Intelligence:连接感知、行动与世界模型的新一代智能系统
  • Open Source AI:开放代码、教程与实验,共建下一代智能系统

我们希望建立一个开放、严谨、长期主义的技术空间,让学习者从理解前沿,到亲手构建,再到独立创造。

如果你关注 Agent、RL、LLM Systems、Embodied Intelligence 或下一代 AI 基础设施,欢迎加入 WalkingLabs,一起探索与构建。

欢迎加入 WalkingLabs Discord 社区:

https://discord.gg/ETWczxp62

Pinned Loading

  1. learn-harness-engineering learn-harness-engineering Public

    Harness engineering beginner tutorial, from 0 to 1

    TypeScript 12.3k 1.3k

  2. modern-llm-notebook modern-llm-notebook Public

    A hands-on course for building modern LLMs from scratch in PyTorch, with 26 runnable Jupyter Notebooks covering tokenizers, attention, MoE, RLHF, inference, evaluation, and distillation.

    Jupyter Notebook 172 35

  3. hands-on-modern-rl hands-on-modern-rl Public

    🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

    Python 4k 292

  4. awesome-harness-engineering awesome-harness-engineering Public

    🛠️ Awesome tools & guides for harness engineering.

    3.9k 329

  5. microLLM-rocm microLLM-rocm Public

    From-scratch tiny LLM training & inference engine for AMD ROCm/HIP GPUs — pure C++/HIP, PyTorch performance

    C++ 1 1

  6. self-improving-agent-notebook self-improving-agent-notebook Public

    Master self-improving LLM agents systematically with runnable Stanford CS329A notebooks.

    Jupyter Notebook 11 3

Repositories

Showing 9 of 9 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…