WangRongsheng/awesome-LLM-resources — Star 增长与排名

🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

全世界最好的大语言模型资源汇总持续更新

挖掘那些真正有价值的项目，而不仅仅是噱头

[!TIP] 如果您对医疗数据集/大模型/多模态/评估相关资源感兴趣！请访问我们的 🤗 Awesome-AI4Med !

📢友情赞助

PackyCode 是一家稳定、高效的 API 中转服务商，一句话接入主流大模型。统一域名、统一密钥、智能容灾切换，97% 可用性。人民币1:1充值，无汇率无手续费坑，新用户首充立享折扣 + $1免费体验额度，多分组折扣低至 2 折起，提供专属Codex/Claude Code高速通道。

点此链接注册，立即开始使用！

感谢 Infistar.cc 无限星河赞助本项目！

⚡ 稳定高效的模型通道：价格低至官方渠道0.3折，模型倍率公开透明，多节点冗余保障，有效降低限流、429 与断连影响； 🧠 主流模型一站式接入：一个 API Key 即可调用 Claude、ChatGPT、Gemini、Kimi、GLM、DeepSeek 等主流模型，覆盖文本生成、图像生成、多模态推理等场景； 📚 契合本仓库资源实践：无论是多模态生成、辅助编程、模型推理还是 MCP / Agent 开发，都可直接把 Infistar 作为 OpenAI、Claude、Gemini 兼容上游，边学边练，零门槛跑通仓库中收录的各类项目与教程；

🎁 专属福利：通过 [专属推广链接] 注册即可领取 5 美元等值测试额度 / 首充专属优惠，快速接入并开始调用！

感谢 APIMart 赞助了本项目！APIMart 是专注 AI 图片/视频生成的低价 API 平台，GPT-Image-2 低至 $0.006/张，1 美元可出图 160+ 张。图片、视频一套异步 API 通吃，提交任务拿 ID、回调取结果，跑批万张不超时、换模型不改代码。按量付费、无月费，通过此注册链接注册即可开用。

推荐 Suggestion 🌟
数据 Data
微调 Fine-Tuning
Agentic RL 🌟
推理 Inference
评估 Evaluation
体验 Usage
知识库 RAG
智能体 Agents
研究 Research 🔥
代码 Coding
视频 Video
图片 Image 🔥
搜索 Search
语音 Speech 🔥
世界模型 World Models 🔥
龙虾 OpenClaw
统一模型 Unified Model 🌟
书籍 Book
课程 Course
教程 Tutorial
论文 Paper
社区 Community
模型上下文协议 MCP
技能 Skills
推理 Open o1
推理 Open o3
小语言模型 Small Language Model 🌟
小多模态模型 Small Vision Language Model 🌟
技巧 Tips

数据 Data

[!NOTE]

此处命名为数据，但这里并没有提供具体数据集，而是提供了处理获取大规模数据的方法

AotoLabel: Label, clean and enrich text datasets with LLMs.
LabelLLM: The Open-Source Data Annotation Platform.
data-juicer: A one-stop data processing system to make data higher-quality, juicier, and more digestible for LLMs!
OmniParser: a native Golang ETL streaming parser and transform library for CSV, JSON, XML, EDI, text, etc.
MinerU (🔥): MinerU is a one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.
PDF-Extract-Kit: A Comprehensive Toolkit for High-Quality PDF Content Extraction.
Parsera: Lightweight library for scraping web-sites with LLMs.
Sparrow: Sparrow is an innovative open-source solution for efficient data extraction and processing from various documents and images.
Docling: Get your documents ready for gen AI.
GOT-OCR2.0: OCR Model.
LLM Decontaminator: Rethinking Benchmark and Contamination for Language Models with Rephrased Samples.
DataTrove: DataTrove is a library to process, filter and deduplicate text data at a very large scale.
llm-swarm: Generate large synthetic datasets like Cosmopedia.
Distilabel: Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
Common-Crawl-Pipeline-Creator: The Common Crawl Pipeline Creator.
Tabled: Detect and extract tables to markdown and csv.
Zerox: Zero shot pdf OCR with gpt-4o-mini.
DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception.
TensorZero: make LLMs improve through experience.
Promptwright: Generate large synthetic data using a local LLM.
pdf-extract-api: Document (PDF) extraction and parse API using state of the art modern OCRs + Ollama supported models.
pdf2htmlEX: Convert PDF to HTML without losing text or format.
Extractous: Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
MegaParse: File Parser optimised for LLM Ingestion with no loss.
MarkItDown: Python tool for converting files and office documents to Markdown.
datasketch: datasketch gives you probabilistic data structures that can process and search very large amount of data super fast, with little loss of accuracy.
semhash: lightweight and flexible tool for deduplicating datasets using semantic similarity.
ReaderLM-v2: a 1.5B parameter language model that converts raw HTML into beautifully formatted markdown or JSON.
Bespoke Curator: Data Curation for Post-Training & Structured Data Extraction.
LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). Extracts signals from prompts & responses, ensuring safety & security.
Curator: Synthetic Data curation for post-training and structured data extraction.
olmOCR: A toolkit for training language models to work with PDF documents in the wild.
Easy Dataset (🔥): A powerful tool for creating fine-tuning datasets for LLM.
BabelDOC: PDF scientific paper translation and bilingual comparison library.
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting.
EasyDistill: Easy Knowledge Distillation for Large Language Models.
ContextGem: a free, open-source LLM framework that makes it radically easier to extract structured data and insights from documents.
OCRFlux: a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page content merging.
DataFlow: Easy Data Preparation with latest LLMs-based Operators and Pipelines.
DatasetLoom (multimodal): 一个面向多模态大模型训练的智能数据集构建与评估平台.
Logics-Parsing
DeepSeek-OCR
PaddleOCR-VL
Chandra: a highly accurate OCR model that converts images and PDFs into structured HTML/Markdown/JSON while preserving layout information.
HunyuanOCR: a leading end-to-end OCR expert VLM powered by Hunyuan's native multimodal architecture.
DeepSeek-OCR-2: Visual Causal Flow.
PaddleOCR-VL-1.5 (🔥): Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing.
GLM-OCR: a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.

↥ back to top

微调 Fine-Tuning

LLaMA-Factory (🔥): Unify Efficient Fine-Tuning of 100+ LLMs.
360-LLaMA-Factory: Unify Efficient Fine-Tuning of 100+ LLMs. (add Sequence Parallelism for supporting long context training)
unsloth (🔥): 2-5X faster 80% less memory LLM finetuning.
TRL: Transformer Reinforcement Learning.
Firefly: Firefly: 大模型训练工具，支持训练数十种大模型
Xtuner: An efficient, flexible and full-featured toolkit for fine-tuning large models.
torchtune: A Native-PyTorch Library for LLM Fine-tuning.
Swift: Use PEFT or Full-parameter to finetune 200+ LLMs or 15+ MLLMs.
AutoTrain: A new way to automatically train, evaluate and deploy state-of-the-art Machine Learning models.
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO).
Ludwig: Low-code framework for building custom LLMs, neural networks, and other AI models.
mistral-finetune: A light-weight codebase that enables memory-efficient and performant finetuning of Mistral's models.
aikit: Fine-tune, build, and deploy open-source LLMs easily!
H2O-LLMStudio: H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs.
LitGPT: Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.
LLMBox: A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.
PaddleNLP: Easy-to-use and powerful NLP and LLM library.
workbench-llamafactory: This is an NVIDIA AI Workbench example project that demonstrates an end-to-end model development workflow using Llamafactory.
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral).
TinyLLaVA Factory: A Framework of Small-scale Large Multimodal Models.
LLM-Foundry: LLM training code for Databricks foundation models.
lmms-finetune: A unified codebase for finetuning (full, lora) large multimodal models, supporting llava-1.5, qwen-vl, llava-interleave, llava-next-video, phi3-v etc.
Simplifine: Simplifine lets you invoke LLM finetuning with just one line of code using any Hugging Face dataset or model.
Transformer Lab: Open Source Application for Advanced LLM Engineering: interact, train, fine-tune, and evaluate large language models on your own computer.
Liger-Kernel: Efficient Triton Kernels for LLM Training.
ChatLearn: A flexible and efficient training framework for large-scale alignment.
nanotron: Minimalistic large language model 3D-parallelism training.
Proxy Tuning: Tuning Language Models by Proxy.
Effective LLM Alignment: Effective LLM Alignment Toolkit.
Autotrain-advanced
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Vision-LLM Alignemnt: This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.
finetune-Qwen2-VL: Quick Start for Fine-tuning or continue pre-train Qwen2-VL Model.
Online-RLHF: A recipe for online RLHF and online iterative DPO.
InternEvo: an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.
veRL (🔥): Volcano Engine Reinforcement Learning for LLM.
Axolotl: Axolotl is designed to work with YAML config files that contain everything you need to preprocess a dataset, train or fine-tune a model, run model inference or evaluation, and much more.
Oumi: Everything you need to build state-of-the-art foundation models, end-to-end.
Kiln: The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.
DeepSeek-671B-SFT-Guide: An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions.
MLX-VLM: MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
RL-Factory: Train your Agent model via our easy and efficient framework.
RM-Gallery: A One-Stop Reward Model Platform.
ART: rain multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training.
LMMs-Engine: A simple, any-to-any modality framework for pretraining and finetuning. Lean, flexible, and built for research.
dLLM: a library that unifies the training and evaluation of diffusion language models, bringing transparency and reproducibility to the entire development pipeline. diffusion
Miles: an enterprise-facing reinforcement learning framework for large-scale MoE post-training and production workloads.
Skills: a collection of pipelines to improve "skills" of large language models (LLMs).
Twinkle: a lightweight, client-server training framework engineered with modular, high-cohesion interfaces.
NeMo AutoModel: Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support.
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo.
Soup: One-config CLI for LLM post-training (SFT/DPO/GRPO/KTO/ORPO). Layer streaming trains an 8B model on a 4 GB laptop GPU by streaming the frozen base from host RAM one decoder layer at a time.

↥ back to top

Agentic RL

veRL (🔥): https://github.com/volcengine/verl
AReaL: https://github.com/inclusionAI/AReaL
slime (🔥): https://github.com/THUDM/slime
Agent Lightning: https://github.com/microsoft/agent-lightning
Molt: https://github.com/NVIDIA-NeMo/labs-molt
prime-rl: https://github.com/PrimeIntellect-ai/prime-rl

↥ back to top

推理 Inference

ollama (🔥): Get up and running with Llama 3, Mistral, Gemma, and other large language models.
Open WebUI: User-friendly WebUI for LLMs (Formerly Ollama WebUI).
Text Generation WebUI: A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
Xinference: A powerful and versatile library designed to serve language, speech recognition, and multimodal models.
LangChain: Build context-aware reasoning applications.
LlamaIndex: A data framework for your LLM applications.
lobe-chat: an open-source, modern-design LLMs/AI chat framework. Supports Multi AI Providers, Multi-Modals (Vision/TTS) and plugin system.
TensorRT-LLM: TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs.
vllm (🔥): A high-throughput and memory-efficient inference and serving engine for LLMs.
LlamaChat: Chat with your favourite LLaMA models in a native macOS app.
NVIDIA ChatRTX: ChatRTX is a demo app that lets you personalize a GPT large language model (LLM) connected to your own content—docs, notes, or other data.
LM Studio (🔥): Discover, download, and run local LLMs.
chat-with-mlx: Chat with your data natively on Apple Silicon using MLX Framework.
LLM Pricing: Quickly Find the Perfect Large Language Models (LLM) API for Your Budget! Use Our Free Tool for Instant Access to the Latest Prices from Top Providers.
Open Interpreter: A natural language interface for computers.
Chat-ollama: An open source chatbot based on LLMs. It supports a wide range of language models, and knowledge base management.
chat-ui: Open source codebase powering the HuggingChat app.
MemGPT: Create LLM agents with long-term memory and custom tools.
koboldcpp: A simple one-file way to run various GGML and GGUF models with KoboldAI's UI.
LLMFarm: llama and other large language models on iOS and MacOS offline using GGML library.
enchanted: Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.
Flowise: Drag & drop UI to build your customized LLM flow.
Jan: Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM).
LMDeploy: LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
RouteLLM: A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!
MInference: About To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.
Mem0: The memory layer for Personalized AI.
SGLang (🔥): SGLang is yet another fast serving framework for large language models and vision language models.
AirLLM: AirLLM optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card without quantization, distillation and pruning. And you can run 405B Llama3.1 on 8GB vram now.
LLMHub: LLMHub is a lightweight management platform designed to streamline the operation and interaction with various language models (LLMs).
YuanChat
LiteLLM (🔥): Call all LLM APIs using the OpenAI format [Bedrock, Huggingface, VertexAI, TogetherAI, Azure, OpenAI, Groq etc.]
GuideLLM: GuideLLM is a powerful tool for evaluating and optimizing the deployment of large language models (LLMs).
LLM-Engines: A unified inference engine for large language models (LLMs) including open-source models (VLLM, SGLang, Together) and commercial models (OpenAI, Mistral, Claude).
OARC: ollama_agent_roll_cage (OARC) is a local python agent fusing ollama llm's with Coqui-TTS speech models, Keras classifiers, Llava vision, Whisper recognition, and more to create a unified chatbot agent for local, custom automation.
g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains.
MemoryScope: MemoryScope provides LLM chatbots with powerful and flexible long-term memory capabilities, offering a framework for building such abilities.
OpenLLM: Run any open-source LLMs, such as Llama 3.1, Gemma, as OpenAI compatible API endpoint in the cloud.
Infinity: The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense embedding, sparse embedding, tensor and full-text.
optillm: an OpenAI API compatible optimizing inference proxy which implements several state-of-the-art techniques that can improve the accuracy and performance of LLMs.
LLaMA Box: LLM inference server implementation based on llama.cpp.
ZhiLight: A highly optimized inference acceleration engine for Llama and its variants.
DashInfer: DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures.
LocalAI: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required.
ktransformers: A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations.
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 14+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
Chitu: High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
TokenSwift: From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation.
Cherry Studio (🔥): a desktop client that supports for multiple LLM providers, available on Windows, Mac and Linux.
Shimmy: Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary.
LlamaBarn: Run local LLMs on your Mac with a simple menu bar app.
Parallax: a distributed model serving framework that lets you build your own AI cluster anywhere.
xLLM: A high-performance inference engine for LLMs, optimized for diverse AI accelerators.
Rapid-MLX: OpenAI-compatible local LLM inference server for Apple Silicon, 2-4x faster than Ollama.
TokenSpeed: a speed-of-light LLM inference engine designed for agentic workloads, with TensorRT-LLM-level performance and vLLM-level usability. Our goal is to be the most performant inference engine for production agentic workloads.
FreeToken: Unlock datacenter-class intelligence on the hardware you already own.
NInfer: High-performance single-GPU inference for selected model checkpoints and GPUs.

↥ back to top

评估 Evaluation

lm-evaluation-harness: A framework for few-shot evaluation of language models.
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.
llm-comparator: LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed.
EvalScope (🔥)
Weave: A lightweight toolkit for tracking and evaluating LLM applications.
MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures.
Evaluation guidebook: If you've ever wondered how to make sure an LLM performs well on your specific task, this guide is for you!
Ollama Benchmark: LLM Benchmark for Throughput via Ollama (Local LLMs).
VLMEvalKit: Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 40+ benchmarks.
AGI-Eval
EvalScope: A streamlined and customizable framework for efficient large model evaluation and performance benchmarking.
DeepEval: a simple-to-use, open-source LLM evaluation framework, for evaluating and testing large-language model systems.
Lighteval: Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends.
QwQ/eval: QwQ is the reasoning model series developed by Qwen team, Alibaba Cloud.
Evalchemy: A unified and easy-to-use toolkit for evaluating post-trained language models.
MathArena: Evaluation of LLMs on latest math competitions.
YourBench: A Dynamic Benchmark Generation Framework.
MedEvalKit: A Unified Medical Evaluation Framework.
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards.

↥ back to top

体验 Usage

知识库 RAG

AnythingLLM: The all-in-one AI app for any LLM with full RAG and AI Agent capabilites.
MaxKB: 基于 LLM 大语言模型的知识库问答系统。开箱即用，支持快速嵌入到第三方业务系统
RAGFlow: An open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Dify: An open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
FastGPT: A knowledge-based platform built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization.
Langchain-Chatchat: 基于 Langchain 与 ChatGLM 等不同大语言模型的本地知识库问答
QAnything: Question and Answer based on Anything.
Quivr: A personal productivity assistant (RAG) ⚡️🤖 Chat with your docs (PDF, CSV, ...) & apps using Langchain, GPT 3.5 / 4 turbo, Private, Anthropic, VertexAI, Ollama, LLMs, Groq that you can share with users ! Local & Private alternative to OpenAI GPTs & ChatGPT powered by retrieval-augmented generation.
RAG-GPT: RAG-GPT, leveraging LLM and RAG technology, learns from user-customized knowledge bases to provide contextually relevant answers for a wide range of queries, ensuring rapid and accurate information retrieval.
Verba: Retrieval Augmented Generation (RAG) chatbot powered by Weaviate.
FlashRAG: A Python Toolkit for Efficient RAG Research.
GraphRAG: A modular graph-based Retrieval-Augmented Generation (RAG) system.
LightRAG: LightRAG helps developers with both building and optimizing Retriever-Agent-Generator pipelines.
GraphRAG-Ollama-UI: GraphRAG using Ollama with Gradio UI and Extra Features.
nano-GraphRAG: A simple, easy-to-hack GraphRAG implementation.
RAG Techniques: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.
ragas: Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines.
kotaemon: An open-source clean & customizable RAG UI for chatting with your documents. Built with both end users and developers in mind.
RAGapp: The easiest way to use Agentic RAG in any enterprise.
TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text.
LightRAG: Simple and Fast Retrieval-Augmented Generation.
TEN: the Next-Gen AI-Agent Framework, the world's first truly real-time multimodal AI agent framework.
AutoRAG: RAG AutoML tool for automatically finding an optimal RAG pipeline for your data.
KAG: KAG is a knowledge-enhanced generation framework based on OpenSPG engine, which is used to build knowledge-enhanced rigorous decision-making and information retrieval knowledge services.
Fast-GraphRAG: RAG that intelligently adapts to your use case, data, and queries.
Tiny-GraphRAG
DB-GPT GraphRAG: DB-GPT GraphRAG integrates both triplet-based knowledge graphs and document structure graphs while leveraging community and document retrieval mechanisms to enhance RAG capabilities, achieving comparable performance while consuming only 50% of the tokens required by Microsoft's GraphRAG. Refer to the DB-GPT Graph RAG User Manual for details.
Chonkie: The no-nonsense RAG chunking library that's lightweight, lightning-fast, and ready to CHONK your texts.
RAGLite: RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with PostgreSQL or SQLite.
KAG: KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs.
CAG: CAG leverages the extended context windows of modern large language models (LLMs) by preloading all relevant resources into the model’s context and caching its runtime parameters.
MiniRAG: an extremely simple retrieval-augmented generation framework that enables small models to achieve good RAG performance through heterogeneous graph indexing and lightweight topology-enhanced retrieval.
XRAG: a benchmarking framework designed to evaluate the foundational components of advanced Retrieval-Augmented Generation (RAG) systems.
Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation.
RAG-Anything: All-in-One RAG System.

↥ back to top

智能体 Agents

AutoGen: AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. AutoGen AIStudio
CrewAI: Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Coze
AgentGPT: Assemble, configure, and deploy autonomous AI Agents in your browser.
XAgent: An Autonomous LLM Agent for Complex Task Solving.
MobileAgent: The Powerful Mobile Device Operation Assistant Family.
Lagent: A lightweight framework for building LLM-based agents.
Qwen-Agent: Agent framework and applications built upon Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.
LinkAI: 一站式 AI 智能体搭建平台
Baidu APPBuilder
agentUniverse: agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications. Furthermore, through the community, they can exchange and share practices of patterns across different domains.
LazyLLM: 低代码构建多Agent大模型应用的开发工具
AgentScope: Start building LLM-empowered multi-agent applications in an easier way.
AgentField: Open-source control plane for building and operating AI agents like APIs at scale, with routing, memory, observability, identity, auth, and policy controls.
MoA: Mixture of Agents (MoA) is a novel approach that leverages the collective strengths of multiple LLMs to enhance performance, achieving state-of-the-art results.
Agently: AI Agent Application Development Framework.
OmAgent: A multimodal agent framework for solving complex tasks.
Tribe: No code tool to rapidly build and coordinate multi-agent teams.
CAMEL: First LLM multi-agent framework and an open-source community dedicated to finding the scaling law of agents.
PraisonAI: PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration.
IoA: An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.
llama-agentic-system : Agentic components of the Llama Stack APIs.
Agent Zero: Agent Zero is not a predefined agentic framework. It is designed to be dynamic, organically growing, and learning as you use it.
Agents: An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents.
AgentScope: Start building LLM-empowered multi-agent applications in an easier way.
FastAgency: The fastest way to bring multi-agent workflows to production.
Swarm: Framework for building, orchestrating and deploying multi-agent systems. Managed by OpenAI Solutions team. Experimental framework.
Agent-S: an open agentic framework that uses computers like a human.
PydanticAI: Agent Framework / shim to use Pydantic with LLMs.
Agentarium: open-source framework for creating and managing simulations populated with AI-powered agents.
smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.
Cooragent: Cooragent is an AI agent collaboration community.
Agno: Agno is a lightweight library for building Agents with memory, knowledge, tools and reasoning.
Suna: Open Source Generalist AI Agent.
rowboat: Let AI build multi-agent workflows for you in minutes.
EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents.
ii-agent: a new open-source framework to build and deploy intelligent agents.
OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation.
OpenManus: No fortress, purely open ground. OpenManus is Coming.
JoyAgent-JDGenie: 业界首个开源高完成度轻量化通用多智能体产品.
coze-studio: An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before.
OxyGent: An advanced Python framework that empowers developers to quickly build production-ready intelligent systems.
LazyCraft: LazyCraft 是一个基于 LazyLLM 构建的 AI Agent 应用开发与管理平台，旨在协助开发者以低门槛、低成本快速构建和发布大模型应用。
OpenAgents: AI Agent Networks for Open Collaboration.
SandBox: All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
DeepAnalyze: First agentic LLM for autonomous data science, supporting specific data tasks (data preparation, analysis, modeling, visualization, and insight) and data-oriented deep research (produce analyst-grade research reports).
Astron Agent: Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
Youtu-Agent: A simple yet powerful agent framework that delivers with open-source models.
MiroThinker: an open-source search agent model, built for tool-augmented reasoning and real-world information seeking, aiming to match the deep research experience of OpenAI Deep Research and Gemini Deep Research.
Nexent: A zero-code platform for auto-generating agents — no orchestration, no complex drag-and-drop required, using pure language to develop any agent you want.
Yunjue-Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks.
Hindsight: State-of-the-art long-term memory for AI agents by Vectorize. Open-source, self-hostable, with integrations for LangChain, CrewAI, LlamaIndex, MCP, and more.
AgentsMesh: The AI Agent Workforce Platform. Self-hostable multi-agent orchestration with remote AI workstations (AgentPods), PTY sandbox + git worktree isolation, channels-based agent collaboration, built-in Kanban, and per-pod MCP server. Supports Claude Code, Codex CLI, Gemini CLI, Aider, OpenCode.
BitFun: Open-source agentic development environment with a Rust/Tauri desktop app and CLI for coding, research, office work, browser and desktop automation, extensible through MCP, Skills, and custom agents.

Harness

pi: AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI.
DeepSeek Harness: Everything is a Plugin.
OpenSquilla: a token-efficient, microkernel AI agent.
PenguinHarness: Your Automated Agent Builder, Right on Your Desktop / Server.
FrontierAgent: an open-source agent runtime, terminal product, and evaluation suite for long-horizon research and file-based work.

↥ back to top

研究 Research

代码 Coding

Cloi CLI: Local debugging agent that runs in your terminal.
Devin
v0
Blot.new
cursor
Windsurf
cline
Trae
MGX
Roo Code
Kilo Code
AugmentCode
Claude Code (🔥)
Claude Code (🔥) + Happy Coder / CodePilot / cc-connect
Gemini CLI
Serena
Claudia
OpenCode
Kiro
CodeBuddy
Kiro
CodeX (🔥)
Kimi-CLI
opencode
Multica
Atomic Agent
DeepSeek Harness

↥ back to top

视频 Video

模型

[!NOTE] 🤝Awesome-Video-Diffusion

编辑

Wan2.1-VACE-14B: https://huggingface.co/Wan-AI/Wan2.1-VACE-14B
Ditto: https://github.com/EzioBy/Ditto
Bernini (🔥): https://github.com/bytedance/Bernini
JoyAI-Video-Edit: https://huggingface.co/jdopensource/JoyAI-Video-Edit

训练

推理

实用工具

PySceneDetect: Python and OpenCV-based scene cut/transition detection program & library.
DOVER: Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives.
ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding.

↥ back to top

图片 Image

生成

awesome-nano-banana
Awesome-Nano-Banana-images
HunyuanImage-3.0：https://github.com/Tencent-Hunyuan/HunyuanImage-3.0
Seedream 4.0：https://arxiv.org/abs/2509.20427
LongCat-Image：https://huggingface.co/meituan-longcat/LongCat-Image
Z-Image-Turbo：https://huggingface.co/Tongyi-MAI/Z-Image-Turbo
- https://huggingface.co/inclusionAI/TwinFlow
Qwen-Image：https://huggingface.co/Qwen/Qwen-Image
Qwen-Image-2512：https://huggingface.co/Qwen/Qwen-Image-2512
Z-Image：https://huggingface.co/Tongyi-MAI/Z-Image
ERNIE-Image: https://huggingface.co/baidu/ERNIE-Image
- ERNIE-Image-Turbo: https://huggingface.co/Baidu/ERNIE-Image-Turbo
Nucleus-Image: https://huggingface.co/NucleusAI/Nucleus-Image
HiDream-O1-Image: https://huggingface.co/HiDream-ai/HiDream-O1-Image
Ideogram 4: https://github.com/ideogram-oss/ideogram4
Boogu-Image: https://github.com/boogu-project/Boogu-Image
Krea-2-Raw: https://huggingface.co/krea/Krea-2-Raw
SenseNova-U1: https://github.com/OpenSenseNova/SenseNova-U1
Mage-Flow: https://huggingface.co/collections/microsoft/mage
Qwen-Image-2.1: https://huggingface.co/Qwen/Qwen-Image-2.1
Ming-Image-0.1: https://huggingface.co/inclusionAI/Ming-Image-0.1-Design

编辑

ChronoEdit-14B: https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers
Eigen-Banana-Qwen-Image-Edit: https://huggingface.co/eigen-ai-labs/eigen-banana-qwen-image-edit
Qwen-Image-Edit-2509: https://huggingface.co/Qwen/Qwen-Image-Edit-2509
- Upscale: https://huggingface.co/vafipas663/Qwen-Edit-2509-Upscale-LoRA
- Multiple-angles: https://huggingface.co/dx8152/Qwen-Edit-2509-Multiple-angles
- Multi-Angle-Lighting: https://huggingface.co/dx8152/Qwen-Edit-2509-Multi-Angle-Lighting
LongCat-Image-Edit: https://huggingface.co/meituan-longcat/LongCat-Image-Edit
Qwen-Image-Edit-2511: https://huggingface.co/Qwen/Qwen-Image-Edit-2511
- Qwen-Image-Edit-2511-Upscale2K: https://huggingface.co/valiantcat/Qwen-Image-Edit-2511-Upscale2K
- Qwen-Image-Edit-2511-Multiple-Angles-LoRA: https://huggingface.co/fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA
FireRed-Image-Edit: https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.0
JoyAI-Image-Edit: https://huggingface.co/jdopensource/JoyAI-Image-Edit

统一

训练

Ostris：https://github.com/ostris/ai-toolkit
FlymyAI：https://github.com/FlyMyAI/flymyai-lora-trainer
Nitro-T：https://github.com/AMD-AGI/Nitro-T
(🔥) DiffSynth-Studio：https://github.com/modelscope/DiffSynth-Studio
Musubi Tuner: https://github.com/kohya-ss/musubi-tuner
SimpleTuner: https://github.com/bghira/SimpleTuner
MS Training: https://www.modelscope.cn/aigc/modelTraining
Finetune HunyuanImage-3.0: https://github.com/PhotonAISG/hunyuan-image3-finetune
OneTrainer: https://github.com/Nerogar/OneTrainer
Finetune LongCat-Image and Edit: https://github.com/meituan-longcat/LongCat-Image/tree/main/train_examples
Flow-Factory: https://github.com/X-GenGroup/Flow-Factory
UniRL: https://github.com/Tencent-Hunyuan/UniRL

评估

ULMEvalKit：https://github.com/ULMEvalKit/ULMEvalKit

推理

TypemovieInfer: https://github.com/typemovie/TypemovieInfer

↥ back to top

搜索 Search

OpenSearch GPT: SearchGPT / Perplexity clone, but personalised for you.
MindSearch: An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT).
nanoPerplexityAI: The simplest open-source implementation of perplexity.ai.
curiosity: Try to build a Perplexity-like user experience.
MiniPerplx: A minimalistic AI-powered search engine that helps you find information on the internet.

↥ back to top

语音 Speech

TTS

SpeechGPT-2.0-preview: https://github.com/OpenMOSS/SpeechGPT-2.0-preview
Moss-TTSD：https://github.com/OpenMOSS/MOSS-TTSD
Index-TTS：https://github.com/index-tts/index-tts
MegaTTS3：https://github.com/bytedance/MegaTTS3
F5-TTS：https://github.com/SWivid/F5-TTS
GPT-SoVITS：https://github.com/RVC-Boss/GPT-SoVITS
CosyVoice：https://github.com/FunAudioLLM/CosyVoice
Spark-TTS：https://github.com/SparkAudio/Spark-TTS
OpenVoice：https://github.com/myshell-ai/OpenVoice
Dia：https://github.com/nari-labs/dia
ChatTTS：https://github.com/2noise/ChatTTS
Fish Speech：https://github.com/fishaudio/fish-speech
Edge-TTS：https://github.com/rany2/edge-tts
Bark：https://github.com/suno-ai/bark
kokoro: https://github.com/hexgrad/kokoro
Higgs Audio V2: https://github.com/boson-ai/higgs-audio 【Training】
KittenTTS: https://github.com/KittenML/KittenTTS
ZipVoice: https://github.com/k2-fsa/ZipVoice
VyvoTTS: https://github.com/Vyvo-Labs/VyvoTTS
VibeVoice: https://github.com/microsoft/VibeVoice
Index-TTS-2: https://huggingface.co/IndexTeam/IndexTTS-2
FireRedTTS2: https://github.com/FireRedTeam/FireRedTTS2
VoxCPM: https://github.com/OpenBMB/VoxCPM/
Neutts-Air: https://github.com/neuphonic/neutts-air
Maya1: https://huggingface.co/maya-research/maya1
VibeVoice: https://huggingface.co/collections/microsoft/vibevoice
GLM-TTS: https://github.com/zai-org/GLM-TTS
Fun-CosyVoice3: https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512
Qwen3-TTS:https://huggingface.co/collections/Qwen/qwen3-tts
Ming-Omni-TTS: https://github.com/inclusionAI/Ming-omni-tts
VoxCPM2: https://huggingface.co/openbmb/VoxCPM2
OmniVoice: https://github.com/k2-fsa/OmniVoice
MOSS-TTS-v1.5: https://huggingface.co/OpenMOSS-Team/MOSS-TTS-v1.5
Higgs Audio v3 TTS: https://huggingface.co/bosonai/higgs-audio-v3-tts-4b
Confucius4-TTS: https://github.com/netease-youdao/Confucius4-TTS
Dia-1.6B: https://huggingface.co/nari-labs/Dia-1.6B-0626
FireRedTTS3: https://github.com/FireRedTeam/FireRedTTS3

STT/ASR

Kyutai: https://github.com/kyutai-labs/delayed-streams-modeling
Whisper: https://github.com/openai/whisper
Audio Flamingo 3: https://huggingface.co/nvidia/audio-flamingo-3
Voxtral: https://huggingface.co/mistralai/Voxtral-Mini-3B-2507
Step-Audio2: https://github.com/stepfun-ai/Step-Audio2
SoulX-Podcast: https://huggingface.co/collections/Soul-AILab/soulx-podcast
Omnilingual ASR: https://github.com/facebookresearch/omnilingual-asr
Fun-ASR: https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512
FunASR: https://github.com/modelscope/FunASR
SenseVoice: https://github.com/FunAudioLLM/SenseVoice
VibeVoice-ASR: https://huggingface.co/microsoft/VibeVoice-ASR
Qwen3-ASR: https://github.com/QwenLM/Qwen3-ASR
Mega-ASR: https://github.com/xzf-thu/Mega-ASR
MOSS-Transcribe-Diarize: https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize

Voice Interaction

Fun-Audio-Chat: https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B
Chroma 1.0: https://huggingface.co/FlashLabs/Chroma-4B
AudioInteraction: https://huggingface.co/zhifeixie/AudioInteraction

↥ back to top

世界模型 World Models

模型

ShadowDancer: https://github.com/AlayaLab/ShadowDancer
PhiZero: https://github.com/yaoyao-jpg/PhiZero
Wonder: https://arxiv.org/pdf/2607.26037
open-dreamer: https://github.com/next-state/open-dreamer
Cosmos3-Edge: https://huggingface.co/nvidia/Cosmos3-Edge
WorldWander: https://github.com/showlab/WorldWander
Matrix-Game-3.5: https://github.com/Riemann-Dynamics/Matrix-Game-3.5
ABot-World: https://github.com/amap-cvlab/ABot-World
LingBot-World-V2: https://huggingface.co/collections/robbyant/lingbot-world-v2
AlayaWorld: https://github.com/AlayaLab/AlayaWorld
MoWorld: https://moxin-tech.github.io/moworld/
Warp-as-History: https://github.com/yyfz/Warp-as-History
MIRA: https://github.com/mira-wm/mira Multiplayer
ActWorld: https://interactwm.github.io/ActWorld/
Sana-WM: https://nvlabs.github.io/Sana/WM/
Cosmos-3: https://github.com/nvidia/cosmos
DreamX-World-5B: https://huggingface.co/GD-ML/DreamX-World-5B
DreamX-World-5B-Cam: https://modelscope.cn/models/GD-ML/DreamX-World-5B-Cam
Astra: https://eternalevan.github.io/Astra-project/
Yume-5B: https://huggingface.co/stdstu123/Yume-5B-720P
LingBot-World: https://github.com/robbyant/lingbot-world
HY-WorldPlay: https://huggingface.co/tencent/HY-WorldPlay
Matrix-Game-3.0: https://huggingface.co/Skywork/Matrix-Game-3.0
Matrix-Game-2.0: https://huggingface.co/Skywork/Matrix-Game-2.0
Waypoint-1.5-1B: https://huggingface.co/Overworld/Waypoint-1.5-1B
Hunyuan-GameCraft: https://hunyuan-gamecraft.github.io/
AlayaWorld: https://github.com/AlayaLab/AlayaWorld
WorldWander: https://github.com/showlab/WorldWander

框架

nano-world-model: https://github.com/simchowitzlabpublic/nano-world-model
minWM: https://github.com/shengshu-ai/minWM
stable-worldmodel: https://github.com/galilai-group/stable-worldmodel
OpenWorldLib: https://github.com/OpenDCAI/OpenWorldLib
BiWM: https://github.com/LynnReal-AI/BiWM

↥ back to top

龙虾 OpenClaw

MultiUserClaw: https://github.com/johnson7788/MultiUserClaw
ClawManager: https://github.com/Yuan-lab-LLM/ClawManager
Qclaw: https://github.com/qiuzhi2046/Qclaw
NEXU: https://github.com/nexu-io/nexu
OpenHanako: https://github.com/liliMozi/openhanako

↥ back to top

统一模型 Unified Model

现在统一模型已经从理解+生成变成理解+生成+编辑

Emu-2：https://arxiv.org/abs/2312.13286
Emu-3：https://arxiv.org/abs/2409.18869
Emu-1：https://arxiv.org/abs/2307.05222
Janus：https://github.com/deepseek-ai/Janus
Janus-Pro：http://arxiv.org/abs/2508.05954
show-o：https://arxiv.org/abs/2408.12528
Any-GPT：https://arxiv.org/abs/2402.12226
Next-GPT：https://arxiv.org/pdf/2309.05519.pdf
CoDi：https://arxiv.org/abs/2305.11846
Seed-X：https://arxiv.org/abs/2404.14396
Dream-LLM：https://arxiv.org/abs/2309.11499
Chameleon：https://arxiv.org/abs/2405.09818
Spider：https://arxiv.org/abs/2411.09439
MedViLaM：https://arxiv.org/abs/2409.19684
VITRON：https://github.com/SkyworkAI/Vitron
TokenFlow：https://github.com/ByteFlow-AI/TokenFlow
OneDiffusion：https://github.com/lehduong/OneDiffusion
MetaMorph: https://arxiv.org/abs/2412.14164
LlamaFusion：https://arxiv.org/abs/2412.15188
InstructSeg：https://arxiv.org/abs/2412.14006
VILA-U：https://arxiv.org/abs/2409.04429
Ullava: https://github.com/OPPOMKLab/u-LLaVA
ILLUME: https://arxiv.org/abs/2412.06673
Vitron:https://arxiv.org/abs/2412.19806
SynerGen-VL：https://arxiv.org/abs/2412.09604
Align Anything：https://arxiv.org/abs/2412.15838
Mico：https://arxiv.org/abs/2406.09412
OneLLM:https://arxiv.org/abs/2312.03700
X-VILA:https://arxiv.org/abs/2405.19335
OLA：https://arxiv.org/abs/2502.04328
Transfusion: https://arxiv.org/abs/2408.11039
JanusFlow: https://arxiv.org/abs/2411.07975
HealthGPT：https://arxiv.org/abs/2502.09838 Medical
BAGEL：https://arxiv.org/abs/2505.14683
Qwen2.5-Omni：https://arxiv.org/abs/2503.20215
X2I：https://arxiv.org/abs/2503.06134
Bifrost-1：https://arxiv.org/abs/2508.05954
OmniGen2：https://arxiv.org/abs/2506.18871
UniPic：https://github.com/SkyworkAI/UniPic
VeOmni：https://github.com/ByteDance-Seed/VeOmni Training
NextStep-1：https://arxiv.org/abs/2508.10711
UniUGG: https://arxiv.org/abs/2508.11952 3D
Omni-Video：https://arxiv.org/abs/2507.06119
OneCAT：https://arxiv.org/abs/2509.03498
Lumina-DiMOO：https://github.com/Alpha-VLLM/Lumina-DiMOO
UAE：https://github.com/PKU-YuanGroup/UAE
RecA：https://arxiv.org/abs/2509.07295
UniLM：https://arxiv.org/abs/1905.03197
Hyper-Bagel：https://arxiv.org/abs/2509.18824
Ming-UniVision：https://arxiv.org/abs/2510.06590
EditVerse：https://arxiv.org/abs/2509.20360
LightBagel: https://arxiv.org/abs/2510.22946
DreamLLM: https://arxiv.org/abs/2309.11499
X-Omni: https://arxiv.org/abs/2507.22058
Ming-flash-omni-Preview: https://huggingface.co/inclusionAI/Ming-flash-omni-Preview
Omni-View: https://arxiv.org/abs/2511.07222
NExT-OMNI: https://arxiv.org/abs/2510.13721
Uni-MoE-2.0-Omni: https://arxiv.org/abs/2511.12609
LongCat-Flash-Omni: https://huggingface.co/meituan-longcat/LongCat-Flash-Omni
ShapeLLM-Omni: https://arxiv.org/abs/2506.01853
UniGen-1.5: https://arxiv.org/abs/2511.14760
Jodi: https://arxiv.org/abs/2505.19084
UniModel: https://arxiv.org/abs/2511.16917
TUNA: https://arxiv.org/abs/2512.02014
HBridge: https://arxiv.org/abs/2511.20520
EMMA: https://arxiv.org/abs/2512.04810
OpenOmni: https://github.com/RainBowLuoCS/OpenOmni
Ming-Flash-Omni: https://arxiv.org/abs/2510.24821
STAR: https://github.com/mm-mvr/star
InternVL-U: https://github.com/OpenGVLab/InternVL-U
LongCat-Next: https://github.com/meituan-longcat/LongCat-Next
SenseNova-U1: https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-SFT
TUNA-2: https://github.com/facebookresearch/tuna-2
Lance: https://github.com/bytedance/Lance
JoyAI-VL-Interaction: https://arxiv.org/abs/2606.14777 Interaction
MOSS-VL-Realtime: https://huggingface.co/OpenMOSS-Team/MOSS-VL-Realtime Interaction
SenseNova-Vision: https://huggingface.co/collections/sensenova/sensenova-vision
Mage-VL: https://huggingface.co/microsoft/Mage-VL Interaction

↥ back to top

书籍 Book

课程 Course

LLM Resources Hub

斯坦福 CS224N: Natural Language Processing with Deep Learning
吴恩达: Generative AI for Everyone
吴恩达: LLM series of courses
ACL 2023 Tutorial: Retrieval-based Language Models and Applications
llm-course: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
微软: Generative AI for Beginners
微软: State of GPT
HuggingFace NLP Course
清华 NLP 刘知远团队大模型公开课
斯坦福 CS25: Transformers United V4
斯坦福 CS324: Large Language Models
普林斯顿 COS 597G (Fall 2022): Understanding Large Language Models
约翰霍普金斯 CS 601.471/671 NLP: Self-supervised Models
李宏毅 GenAI课程
openai-cookbook: Examples and guides for using the OpenAI API.
Hands on llms: Learn about LLM, LLMOps, and vector DBS for free by designing, training, and deploying a real-time financial advisor LLM system.
滑铁卢大学 CS 886: Recent Advances on Foundation Models
Mistral: Getting Started with Mistral
斯坦福 CS25: Transformers United V4
Coursera: Chatgpt 应用提示工程
LangGPT: Empowering everyone to become a prompt expert!
mistralai-cookbook
Introduction to Generative AI 2024 Spring
build nanoGPT: Video+code lecture on building nanoGPT from scratch.
LLM101n: Let's build a Storyteller.
Knowledge Graphs for RAG
LLMs From Scratch (Datawhale Version)
OpenRAG
通往AGI之路
Andrej Karpathy - Neural Networks: Zero to Hero
Interactive visualization of Transformer
andysingal/llm-course
LM-class
Google Advanced: Generative AI for Developers Learning Path
Anthropics：Prompt Engineering Interactive Tutorial
LLMsBook
Large Language Model Agents
Cohere LLM University
LLMs and Transformers
Smol Vision: Recipes for shrinking, optimizing, customizing cutting edge vision models.
Multimodal RAG: Chat with Videos
LLMs Interview Note
RAG++ : From POC to production: Advanced RAG course.
Weights & Biases AI Academy: Finetuning, building with LLMs, Structured outputs and more LLM courses.
Prompt Engineering & AI tutorials & Resources
Learn RAG From Scratch – Python AI Tutorial from a LangChain Engineer
LLM Evaluation: A Complete Course
HuggingFace Learn
Andrej Karpathy: Deep Dive into LLMs like ChatGPT
LLM技术科普
CS25: Transformers United V5
RAG_Techniques: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.
100+ LLM & RL Algorithm Maps | 原创 LLM / RL 100+原理图
Reinforcement Learning of Large Language Models
NanoChat: The best ChatGPT that $100 can buy.
斯坦福CS146S: The Modern Software Developer
Reinforcement Learning of Large Language Models

↥ back to top

教程 Tutorial

论文 Paper

[!NOTE] 🤝Huggingface Daily Papers、Cool Papers、ML Papers Explained

社区 Community

模型上下文协议 MCP

MCP工具聚合：

技能 Skills

推理 Open o1

[!NOTE]

开放的技术是我们永恒的追求

[↥ back to top](#Contents)

推理 Open o3

Mini-o3: https://arxiv.org/abs/2509.07969
Simple-o3: https://arxiv.org/abs/2508.12109
Thyme: https://arxiv.org/abs/2508.11630
Open o3 Video: https://arxiv.org/abs/2510.20579

↥ back to top

小语言模型 Small Language Model

小多模态模型 Small Vision Language Model

技巧 Tips

What We Learned from a Year of Building with LLMs (Part I)
What We Learned from a Year of Building with LLMs (Part II)
What We Learned from a Year of Building with LLMs (Part III): Strategy
轻松入门大语言模型（LLM）
LLMs for Text Classification: A Guide to Supervised Learning
Unsupervised Text Classification: Categorize Natural Language With LLMs
Text Classification With LLMs: A Roundup of the Best Methods
LLM Pricing
Uncensor any LLM with abliteration
Tiny LLM Universe
Zero-Chatgpt
Zero-Qwen-VL
finetune-Qwen2-VL
MPP-LLaVA
build_MiniLLM_from_scratch
Tiny LLM zh
MiniMind: 3小时完全从0训练一个仅有26M的小参数GPT，最低仅需2G显卡即可推理训练.
LLM-Travel: 致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用
Knowledge distillation: Teaching LLM's with synthetic data
Part 1: Methods for adapting large language models
Part 2: To fine-tune or not to fine-tune
Part 3: How to fine-tune: Focus on effective datasets
Reader-LM: Small Language Models for Cleaning and Converting HTML to Markdown
LLMs应用构建一年之心得
LLM训练-pretrain
pytorch-llama: LLaMA 2 implemented from scratch in PyTorch.
Preference Optimization for Vision Language Models with TRL 【support model】
Fine-tuning visual language models using SFTTrainer 【docs】
A Visual Guide to Mixture of Experts (MoE)
Role-Playing in Large Language Models like ChatGPT
Distributed Training Guide: Best practices & guides on how to write distributed pytorch training code.
Chat Templates
Top 20+ RAG Interview Questions
LLM-Dojo 开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架
o1 isn’t a chat model (and that’s the point)
Beam Search快速理解及代码解析
基于 transformers 的 generate() 方法实现多样化文本生成：参数含义和算法原理解读
The Ultra-Scale Playbook: Training LLMs on GPU Clusters

↥ back to top

贡献者:

如果你觉得本项目对你有帮助，欢迎引用：

@misc{wang2024llm,
      title={awesome-LLM-resourses}, 
      author={Rongsheng Wang},
      year={2024},
      publisher = {GitHub},
      journal = {GitHub repository},
      howpublished = {\url{https://github.com/WangRongsheng/awesome-LLM-resourses}},
}

Alt

awesome-LLM-resources