loveSnowBest

shanghai-house-data-view. 上海二手房网签数据每日记录 数据来源：网上房地产

SCOPE. Python

OneResearchClaw. Any research. One Claw. 🦞 From any materials to research with fully autonomous & skill-driven researcher.

hermes-agent. The agent that grows with you

MOSS-Audio. MOSS-Audio is an open-source foundation model for unified audio understanding, enabling speech, sound, music, captioning, QA, and reasoning in real-world scenarios.

tool-reasoning-framework-PTE. Python

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

Vision-DeepResearch. [ICML 2026] Multimodal deep-research MLLM and benchmark. The first long-horizon multimodal deep-research MLLM, extending the number of reasoning turns to dozens and the number of search-engine interactions to hundreds.

UniCorn. Python

Frontier-CS. A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.

AI-Trader. "AI-Trader: 100% Fully-Automated Agent-Native Trading"

AGILE. [ICLR2026] Official Implement of "Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models"

AgentGym-RL. Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

SimpleTIR. [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

KernelBench. KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)

tau2-bench. τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

True-Story-of-Pangu. 诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

DeepResearch. Tongyi Deep Research, the Leading Open-source Deep Research Agent

MindLink. Python

awesome-agentic-search. 🔍 Awesome Agentic Search is a curated list of papers, tools, and resources on agentic search—where AI agents plan, search, and reason to answer complex questions. Explore the latest research, benchmarks, and industry solutions for next-gen search-enhanced AI! 🤖✨

Alita.

VRAG. Multimodal Retrieval-augmented Generation Framework Built by Tongyi Lab, Alibaba Group.

ai-hedge-fund. An AI Hedge Fund Team

MiMo. MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining

Learning_dynamics_LLM. Jupyter Notebook

ReCall. ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

tiingo-python. Python client for interacting with the Tiingo Financial Data API (stock ticker and news data)

GenPercept. [ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

VCR-Bench. VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning

DeepResearcher. Scaling Deep Research via Reinforcement Learning in Real-world Environments.

VeOmni. VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

SandboxFusion. Python

understand-r1-zero. Understanding R1-Zero-Like Training: A Critical Perspective

ADORA. Python

DAPO. An Open-source RL System from ByteDance Seed and Tsinghua AIR

MM-EUREKA. MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

big-math. A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models

owl. 🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

OpenManus. No fortress, purely open ground. OpenManus is Coming.

R1-Searcher. R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

PseDet. [ICLR 2025] PseDet: Revisiting the Power of Pseudo Label in Incremental Object Detection

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

ViDoRAG. [EMNLP 2025] ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents

MLGym. MLGym A New Framework and Benchmark for Advancing AI Research Agents

SWELancer-Benchmark. This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

OmniParser. A simple screen parsing tool towards pure vision based GUI agent

RAM. A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).

Kimi-k1.5.

OREAL. Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

NSFC-LaTex. BibTeX Style

s1. s1: Simple test-time scaling

Logic-RL. Reproduce R1 Zero on Logic Puzzle

LIFT3D. [CVPR 2025]Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation

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

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

Janus. Janus-Series: Unified Multimodal Understanding and Generation Models

DeepSeek-R1.

DeepSeek-V3. Python

simpleRL-reason. Simple RL training for reasoning

TinyZero. Minimal reproduction of DeepSeek R1-Zero

UI-TARS-desktop. The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

ToolBench. [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

BRIGHT. [ICLR 2025] BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

WorkArena. WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?

Agent-R. Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"

OpenRLHF. An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

LLM-RL-Papers. Monitoring recent cross-research on LLM & RL on arXiv for control. If there are good papers, PRs are welcome.

PRIME. Scalable RL solution for advanced reasoning of language models

AgentLaboratory. Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

crawl4ai. 🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

PatchRefinerV2. [ICLR 2026] PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation

Thinking-Claude. Let your Claude able to think

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

UFO. UFO³: Weaving the Digital Agent Galaxy

langfun. OO for LLMs

GTA. [NeurIPS 2024 D&B] GTA: A Benchmark for General Tool Agents & [arXiv 2026] GTA-2

VisionZip. Official repository for VisionZip (CVPR 2025)

Amodal-Depth-Anything. [ICCV 2025] Amodal Depth Anything: Amodal Depth Estimation in the Wild

LLaVA-CoT. [ICCV 2025] LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning

webarena. Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

fanoutqa. Companion code for FanOutQA: Multi-Hop, Multi-Document Question Answering for Large Language Models (ACL 2024)

OSWorld. [NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

WebRL. Building Open LLM Web Agents with Self-Evolving Online Curriculum RL

Retroformer. Python

UIM. The official pytorch implementation of Exploring the Interactive Guidance for Unified and Effective Image Matting [TOMM 2025]

swarm. Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

O1-Journey. O1 Replication Journey

SeeAct. [ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).

NAT. [NAACL 2025] The official implementation of paper "Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents"

LEMA. official repo for the paper "Learning From Mistakes Makes LLM Better Reasoner"

WindowsAgentArena. Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.

digirl. Official repo for paper DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.

MMSearch. [ICLR 2025] The First Multimodal Seach Engine Pipeline and Benchmark for LMMs

Awesome-LLM-Strawberry. A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Agent-Eval-Refine. Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]

JARVIS. JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

appworld. 🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

SuperPrompt. SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

gpt-neox. An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Agent-E. Agent driven automation starting with the web. Try it: https://www.emergence.ai/web-automation-api

WebVoyager. Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"

Awesome-GUI-Agent. 💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.

MC-Planner. Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents"

LEGENT. Open Platform for Embodied Agents

Super_MARIO. Python

egoposeformer. [ECCV 2024] EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation

LLM-Planning-Papers. Must-read Papers on Large Language Model (LLM) Planning.

ECCV-2024-Papers-Autonomous-Driving. ECCV 2024 Paper List about Autonomous Driving

AgentVerse. 🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

BadMerging. [CCS 2024] "BadMerging: Backdoor Attacks Against Model Merging": official code implementation.

AI-Scientist. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

AgentGym. Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

MCTS-DPO. This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

llm-compression-intelligence. Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]

llama_index. LlamaIndex is the leading document agent and OCR platform

sam2. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

llama-stack-apps. Agentic components of the Llama Stack APIs

MindSearch. 🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Awesome-Code-LLM. [TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.

Multi-LLM-Agent. Python

graphrag. A modular graph-based Retrieval-Augmented Generation (RAG) system

DeepSeek-V2. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Cradle. The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

storm. An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

self-ask. Code and data for "Measuring and Narrowing the Compositionality Gap in Language Models"

openinterpreter. A lightweight coding agent for open models like Deepseek, Kimi, and Qwen

IoA. An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.

k-Find. 基于kOS的新一代搜索引擎，汇聚深度和速度的搜索引擎，为您提供一触即达的信息体验。

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

Eurus. Python

ProAgent. An LLM-based Agent for the New Automation Paradigm - Agentic Process Automation

TravelPlanner. [ICML'24 Spotlight] "TravelPlanner: A Benchmark for Real-World Planning with Language Agents"

ragflow. RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

StabilityIndex. [ECCV 2024] Towards Stable 3D Object Detection

Bench2DriveZoo. BEVFormer, UniAD, VAD in Closed-Loop CARLA Evaluation with World Model RL Expert Think2Drive

ReST-MCTS. ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

SaySelf. Public code repo for paper "SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales"

PaddleOCR. Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

PatchRefiner. [ECCV 2024] Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation

Voxel-Mamba. [NeurIPS24 Spotlight] Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection

KnowPAT. [Paper][ACL 2024 Findings] Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering

letta. Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

mi-gpt. 🏠 将小爱音箱接入 ChatGPT 和豆包，改造成你的专属语音助手。

DiLu. [ICLR 2024] DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models

LLM101n. LLM101n: Let's build a Storyteller

agentUniverse. agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.

Awesome-LLMs-for-Video-Understanding. 🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.

World-Models-Autonomous-Driving-Survey. A curated list of world models for autonomous driving.

llm-action. 本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

llama-moe. ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)

VideoLLaMA2. VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

ETO. Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)

AnyGPT. Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

ChatTTS. A generative speech model for daily dialogue.

DeepSeek-Coder-V2. DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

TrustRAG. TrustRAG：The RAG Framework within Reliable input,Trusted output

Awesome-LLM-RAG. Awesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language Models

GPT4RoI. (ECCVW 2025)GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

RULER. This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

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

Awesome-LLM-Long-Context-Modeling. 📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

Index-1.9B. A lightweight multilingual LLM

Qwen3. Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Vane. Vane is an AI-powered answering engine.

Bench2Drive. [NeurIPS 2024 Datasets and Benchmarks Track] Closed-Loop E2E-AD Benchmark Enhanced by World Model RL Expert

LEval. [ACL'24 Outstanding] Data and code for L-Eval, a comprehensive long context language models evaluation benchmark

Qwen-Agent. Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

prm800k. 800,000 step-level correctness labels on LLM solutions to MATH problems

awesome-vlm-architectures. Famous Vision Language Models and Their Architectures

Awesome-Code-LLM. 👨‍💻 An awesome and curated list of best code-LLM for research.

Awesome-LLM4Math. Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied with elaborately-written concise descriptions to help readers get the gist as quickly as possible.

RQ-RAG. Codes for our paper "RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation"

SAIL. SAIL: Search Augmented Instruction Learning

distill-bev. DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation (ICCV 2023)

VL-RLHF. A RLHF Infrastructure for Vision-Language Models

ShareGPT4Video. [NeurIPS 2024] An official implementation of "ShareGPT4Video: Improving Video Understanding and Generation with Better Captions"

flash-attention. Fast and memory-efficient exact attention

llm-continual-learning-survey. [CSUR 2025] Continual Learning of Large Language Models: A Comprehensive Survey

Long-CLIP. [ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

UPIDet. Unleash the Potential of Image Branch for Cross-modal 3D Object Detection [NeurIPS2023]

GLM-4. GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

Ice. Powerful menu bar manager for macOS

LLaMA-Adapter. [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

LLaVA-RLHF. Aligning LMMs with Factually Augmented RLHF

Video-MME. ✨✨[CVPR 2025] Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

OccSora. OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving

DevEval. A Comprehensive Benchmark for Software Development.

ANAH. [ACL 2024] ANAH & [NeurIPS 2024] ANAH-v2 & [ICLR 2025] Mask-DPO

search_with_lepton. Building a quick conversation-based search demo with Lepton AI.

MMFuser. The official implementation of the paper "MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding". MMFuser addresses the limitations of current MLLMs in capturing complex image details by simply yet efficiently integrating multi-layer features from ViTs.

AIOS. AIOS: AI Agent Operating System

MMInA. [ACL2025 Findings] Benchmarking Multihop Multimodal Internet Agents

LaVague. Large Action Model framework to develop AI Web Agents

Megatron-LM. Ongoing research training transformer models at scale