Awesome Agent Environments

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

Learn Claude Code — 基于源码的完整技术分析文档集，15章深度解析 Agent Loop、工具系统、权限系统等核心机制

🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.

Roadmap of learning blockchain technology and business knowledge summarized by ZJUBCA（浙大区块链协会总结的区块链知识学习路线）

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

CL-bench: A Benchmark for Context Learning

A memory OS that makes your agents more personal while saving tokens.

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!

Democratizing Reinforcement Learning for LLMs

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

[COLM 2025] Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale

AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill memory for cross-task skill reuse and evolution.

[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

A collection of awesome think with videos papers.

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication

（原创）全网最全-币圈区块链各类常用工具与相关信息资料大全-虚拟加密货币-欧易OKX币安Binace芝麻开门Gate-交易所App注册-NFT-Defi-加密钱包-比特币-新手入门教程 -持续更新

A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

A version of verl to support diverse tool use

SkyRL: A Modular Full-stack RL Library for LLMs

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

[EMNLP 2025 Industry] Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning

Code for the preprint "Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?"

【三年面试五年模拟】AIGC算法工程师面试秘籍。涵盖AIGC、LLM大模型、AI Agent、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、具身智能、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

SoTA open-source TTS