JiangZhaoh

SDAR. SDAR (Synergy of Diffusion and AutoRegression), a large diffusion language model（1.7B, 4B, 8B, 30B）

SDAR. Official code for "Self-Distilled Agentic Reinforcement Learning"

AtomMem. AtomMem: a long-term memory system for personalized LLM agents.

aohp. An OS-level agent harness for personalized, efficient and secure interaction

vitabench. [ICLR 2026] VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

VitaBench-2.0. Python

MemGUI-Bench. [ACM MM 2026] MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments

GUI-Odyssey. [ICCV 2025] GUIOdyssey is a comprehensive dataset for training and evaluating cross-app navigation agents. GUIOdyssey consists of 8,834 episodes from 6 mobile devices, spanning 6 types of cross-app tasks, 212 apps, and 1.4K app combos.

headroom. Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

mempalace. The best-benchmarked open-source AI memory system. And it's free.

Rubrics_Survey.

prompts.chat. f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

TaskMem. Python

MAI-UI. MAI-UI: Real-World Centric Foundation GUI Agents ranging from 2B to 235B

MobileAgent. Mobile-Agent: The Powerful GUI Agent Family

screen_qa. ScreenQA dataset was introduced in the "ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots" paper. It contains ~86K question-answer pairs collected by human annotators for ~35K screenshots from Rico. It should be used to train and evaluate models capable of screen content understanding via question answering.

MiroThinker. MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

Awesome-Agent-Memory. [Up-To-Date] Awesome Agent Memory Paper Resource

ReMe. ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

dspy. DSPy: The framework for programming—not prompting—language models

hermes-agent-self-evolution. ⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

SkillZero. Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"

memU. Personal memory for agents - fast memory retrieval, self-evolving skills, and lower cost.

claude-mem. Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

miniforge. A conda-forge distribution.

skillsbench. SkillsBench evaluates how well skills work and how effective agents are at using them.

hermes-agent. The agent that grows with you

SkillNet. Create, Evaluate, and Connect AI Skills

SkillClaw. Let Skills Evolve Collectively with Agentic Evolver

MetaClaw. 🦞 Just talk to your agent — it learns and EVOLVES 🧬.

claude-code-analysis. 🤖 The analysis of Claude Code

deepwiki-open. Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

beautiful-mermaid. TypeScript

claude-code. 原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复

leetcode-company-wise-problems. Lists of company wise questions. Every csv file in the companies directory corresponds to a list of questions on leetcode for a specific company based on the leetcode company tags. Updated as of 20 June, 2025

GEMS. GEMS: Agent-Native Multimodal Generation with Memory and Skills

claw-code. An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

FingerTip-20K. Python

SkillRL. SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Tree-GRPO. [ICLR 2026] Tree Search for LLM Agent Reinforcement Learning

alfworld. ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Paper2Slides. "Paper2Slides: From Paper to Presentation in One Click"

android_world. AndroidWorld is an environment and benchmark for autonomous agents

ATM-Bench. ATM-Bench: A benchmark for long-term personalized memory QA spanning ~4 years of multimodal data (images, videos, emails). Features referential queries, evidence-grounded answering, and multi-source reasoning. Paper: "According to Me: Long-Term Personalized Referential Memory QA"

elasticsearch. Free and Open Source, Distributed, RESTful Search Engine

Search-R1. Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Mem-T. Mem-T: Densifying Rewards for Long-Horizon Memory Agents

TokMem. Python

LMEB. Code for "LMEB: Long-horizon Memory Embedding Benchmark"

testlib. C++ library to develop competitive programming problems

EvoScientist. 🔬 Harness Vibe Research with Self-evolving AI Scientists

ICRL. In-Context Reinforcement Learning for Tool Use in Large Language Models

Open-AgentRL. RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

CLI-Anything. "CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

OpenMAIC. Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click

OpenClaw-RL. OpenClaw-RL: Train any agent simply by talking

MemoryLLM. The official implementation of the ICML 2024 paper "MemoryLLM: Towards Self-Updatable Large Language Models" and "M+: Extending MemoryLLM with Scalable Long-Term Memory"

argos-translate. Open-source offline translation library written in Python

Agent-Memory-Paper-List. The paper list of "Memory in the Age of AI Agents: A Survey"

mem0. Universal memory layer for AI Agents

evolver. The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

Awesome-Memory-for-Agents. A Collection of Papers about Memory for Language Agents

CURE. [NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning

zeroclaw. Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀

MemSkill. MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

autoresearch. AI agents running research on single-GPU nanochat training automatically

agent-workflow-memory. AWM: Agent Workflow Memory

Grammar-based-test-case-generation. Python

Engram. Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

awesome-agent-skills. Agent Skills 终极指南：快速入门、资源推荐、精选技能与实用工具 ｜The Ultimate Guide to Agent Skills: QuickStart, Resources, Features&Toolkit

slime. slime is an LLM post-training framework for RL Scaling.

GatedDeltaNet. [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule

LLaDA2.X. LLaDA2.0 is the diffusion language model series developed by InclusionAI team, Ant Group.

opencompass. OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Slow_Thinking_with_LLMs. A series of technical report on Slow Thinking with LLM

cyaron. CYaRon: Yet Another Random Olympic-iNformatics test data generator

CL-bench. CL-bench: A Benchmark for Context Learning

deepconf. DeepConf: Deep Think with Confidence

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

JustGRPO. [ICML 2026 Outstanding Paper] Minimalist RL for Diffusion LLMs. 89.1% on GSM8K.

SandboxFusion. Python

dflash. DFlash: Block Diffusion for Flash Speculative Decoding

ROLL. An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

LiveCodeBench. Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"

xcpc-algorithm-templates. XCPC/ICPC/CCPC 算法模板

Awesome-Multimodal-Large-Language-Models. Reading notes about Multimodal Large Language Models, Large Language Models, and Diffusion Models

How-To-Ask-Questions-The-Smart-Way. 本文原文由知名 Hacker Eric S. Raymond 所撰寫，教你如何正確的提出技術問題並獲得你滿意的答案。

dLLM-RL. [ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.

Awesome-DLMs. The official GitHub repo for the survey paper "A Survey on Diffusion Language Models".

VibeThinker. Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

lmdeploy. LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

MiniCPM-V. A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

claude-cookbooks. A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

AReaL. The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

Math-Verify. Python

mathlib4. The math library of Lean 4

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

Awesome_Efficient_LRM_Reasoning. 😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond

Awesome-Efficient-Reasoning-Models. [TMLR 2025] Efficient Reasoning Models: A Survey

RLHF-Reward-Modeling. Recipes to train reward model for RLHF.

Functional-Analysis.

monotonic-nn. Keras implementation of the constrained monotonic neural networks

Real-world-bandwidth-traces. Real-world network throughputs traces used in MERINA(+)

Comyco-Video-Description-Dataset. The Comyco's Video Description Dataset

hierarchical-rule-induction. Neuro-Symbolic Hierarchical Rule Induction

paper-qa. High accuracy RAG for answering questions from scientific documents with citations

RLPHF. Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

Pensieve-PPO. The simplest implementation of Pensieve (SIGCOMM' 17) via state-of-the-art RL algorithms, including PPO, DQN, SAC, and support for both TensorFlow and PyTorch.

vmaf. Perceptual video quality assessment based on multi-method fusion.

CleanDiffuser. CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making

dash.js. A reference client implementation for the playback of MPEG DASH via Javascript and compliant browsers.

awesome-multi-task-learning. A curated list of DATASETS, CODEBASES and PAPERS on Multi-Task Learning (MTL), from Machine Learning perspective.

955.WLB. 955 不加班的公司名单 - 工作 955，work–life balance (工作与生活的平衡)

Uni-RLHF-Platform. Uni-RLHF platform for "Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback" (ICLR2024)

reinforcement-learning-an-introduction. Solutions to exercises in Reinforcement Learning: An Introduction (2nd Edition).

learning_research. 本人的科研经验

sam. SAM: Sharpness-Aware Minimization (PyTorch)

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

awesome-RLHF. A curated list of reinforcement learning with human feedback resources (continually updated)

imitation-learning. Imitation learning algorithms

ARP. Guide Your Agent with Adaptive Multimodal Rewards (NeurIPS 2023 Accepted)

enn. Python

SJTUBeamer. 上海交通大学 Beamer 模版 | Beamer template for Shanghai Jiao Tong University

SJTUThesis. 上海交通大学 LaTeX 论文模板 | Shanghai Jiao Tong University LaTeX Thesis Template

imitation. Clean PyTorch implementations of imitation and reward learning algorithms

dopamine. Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

cook. 🍲 好的，今天我们来做菜！OK, Let's Cook!

few-shot-preference-rl. Python

inverse-preference-learning. Python

OPER. code for the paper Offline Prioritized Experience Replay

pytorch_sac. PyTorch implementation of Soft Actor-Critic (SAC)

TD7. Author's PyTorch implementation of TD7 for online and offline RL

PreferenceTransformer. Preference Transformer: Modeling Human Preferences using Transformers for RL (ICLR2023 Accepted)

jaxrl. JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.

safe-rlhf. Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Gymnasium. A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

B_Pref. Jupyter Notebook

BPref. Official codebase for "B-Pref: Benchmarking Preference-BasedReinforcement Learning" contains scripts to reproduce experiments.

Minigrid. Simple and easily configurable grid world environments for reinforcement learning

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

Pre-Trained-Language-Models-for-Interactive-Decision-Making. Pre-Trained Language Models for Interactive Decision-Making [NeurIPS 2022]

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

purejaxrl. Really Fast End-to-End Jax RL Implementations

acme. A library of reinforcement learning components and agents

alpaca.cpp. Locally run an Instruction-Tuned Chat-Style LLM

CausalTransformer. Code for the paper "Causal Transformer for Estimating Counterfactual Outcomes"

cid-in-rl. Code for the paper: "Causal Influence Detection for Improving Efficiency in Reinforcement Learning", by Seitzer, M., Schölkopf, B., Martius, G., NeurIPS 2021

deep-symbolic-optimization. A deep learning framework for symbolic optimization.

annotated_deep_learning_paper_implementations. 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

Grounding_LLMs_with_online_RL. We perform functional grounding of LLMs' knowledge in BabyAI-Text

Mega-Agent-2. Python

mario-gpt. [Neurips 2023] Generating Mario Levels with GPT2. Code for the paper "MarioGPT: Open-Ended Text2Level Generation through Large Language Models" https://arxiv.org/abs/2302.05981

Imagine. Code for the paper Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration

cockpit. Cockpit: A Practical Debugging Tool for Training Deep Neural Networks

dino. PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

OptimalRepresentationRL. An implementation in PyTorch of the paper "A Geometric Perspective on Optimal Representations for Reinforcement Learning" by Bellemare et al

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

ray. Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

rainbow-is-all-you-need. Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow

rlpyt. Reinforcement Learning in PyTorch

spr. Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"

SGI. Official code for "Pretraining Representations For Data-Efficient Reinforcement Learning" (NeurIPS 2021)

symbolic-rl. Symbolic Reinforcement Learning using Inductive Logic Programming

neural-symbolic-machines. Neural Symbolic Machines is a framework to integrate neural networks and symbolic representations using reinforcement learning, with applications in program synthesis and semantic parsing.

pytorch_geometric. Graph Neural Network Library for PyTorch

graph_nets. Build Graph Nets in Tensorflow

VTs-Drloc. [NeurIPS 2021] Official codes for "Efficient Training of Visual Transformers with Small Datasets".

HowToCook. Programmer's guide about how to cook at home.

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Arcade-Learning-Environment. A simple framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games

atari-model-zoo. A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release that enables easy visualization and analysis of models, and comparison across training algorithms.

vision_transformer. Jupyter Notebook

convmixer. Implementation of ConvMixer for "Patches Are All You Need? 🤷"

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

rl-baselines3-zoo. A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

MAE-pytorch. Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

scene_generation. A PyTorch implementation of the paper: Specifying Object Attributes and Relations in Interactive Scene Generation

simclr. SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

imm. Code for unsupervised learning of object landmarks as proposed in "Unsupervised Learning of Object Landmarks through Conditional Image Generation", Tomas Jakab*, Ankush Gupta*, Hakan Bilen, Andrea Vedaldi, Advances in Neural Information Processing Systems (NeurIPS) 2018.

SMORL. Python

permakey. Code repository complementing the ICLR 2021 paper "Unsupervised Object Keypoint Learning using Local Spatial Predictability" (https://arxiv.org/abs/2011.12930)

keras-io. Keras documentation, hosted live at keras.io

atari-representation-learning. Code for "Unsupervised State Representation Learning in Atari"

deepmind-research. This repository contains implementations and illustrative code to accompany DeepMind publications

stable-baselines3. PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

ILASP-releases.

Popper. An inductive logic programming system

metagol. Metagol - an inductive logic programming system

HighwayEnv. A collection of environments for autonomous driving and tactical decision-making tasks

Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions. Solutions of Reinforcement Learning, An Introduction

mujoco. Multi-Joint dynamics with Contact. A general purpose physics simulator.

decision-transformer. Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

seed_rl. SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

lhpo. Lightweight HyperParameter Optimizer

InterGPS. Data and Code for ACL 2021 Paper "Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning"

NLIL. Neural Logic Inductive Learning

Neural-LP. Differentiable Learning of Logical Rules for Knowledge Base Reasoning

KB2E. Knowledge Graph Embeddings including TransE, TransH, TransR and PTransE