Bảng xếp hạng repo GitHub theo sao, tốc độ tăng trưởng và mức độ hoạt động.

• Mintplex-Labs

  #1Mintplex-Labs/anything-llm

  Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

  JavaScript65.854 saopush cuối Hôm qua
• bojieli

  #2bojieli/ai-agent-book

  《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

  Python45.436 saopush cuối 23 giờ trước
• bytedance

  #3bytedance/UI-TARS-desktop

  The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

  TypeScript38.915 saopush cuối 1 tháng trước
• haotian-liu

  #4haotian-liu/LLaVA

  [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

  Python25.016 saopush cuối 2 năm trước
• microsoft

  #5microsoft/unilm

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

  Python22.205 saopush cuối 2 tuần trước
• screenpipe

  #6screenpipe/screenpipe

  YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes, Runner...)

  Rust21.509 saopush cuối Hôm qua
• deepseek-ai

  #7deepseek-ai/Janus

  Janus-Series: Unified Multimodal Understanding and Generation Models

  Python17.762 saopush cuối 2 năm trước
• modelscope

  #8modelscope/ms-swift

  Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

  Python15.567 saopush cuối 2 ngày trước
• rerun-io

  #9rerun-io/rerun

  Visualize, query, and stream to train on multimodal robotics data.

  Rust11.423 saopush cuối Hôm qua
• datawhalechina

  #10datawhalechina/all-in-rag

  🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/

  Python10.939 saopush cuối 7 ngày trước

#	Repo	Ngôn ngữ	Sao	Xu hướng 30 ngày	Cập nhật lần cuối
1	Mintplex-Labs Mintplex-Labs/anything-llm Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience	JavaScript	65.854		push cuối Hôm qua
2	bojieli bojieli/ai-agent-book 《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码	Python	45.436		push cuối 23 giờ trước
3	bytedance bytedance/UI-TARS-desktop The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra	TypeScript	38.915		push cuối 1 tháng trước
4	haotian-liu haotian-liu/LLaVA [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.	Python	25.016		push cuối 2 năm trước
5	microsoft microsoft/unilm Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities	Python	22.205		push cuối 2 tuần trước
6	screenpipe screenpipe/screenpipe YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes, Runner...)	Rust	21.509		push cuối Hôm qua
7	deepseek-ai deepseek-ai/Janus Janus-Series: Unified Multimodal Understanding and Generation Models	Python	17.762		push cuối 2 năm trước
8	modelscope modelscope/ms-swift Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).	Python	15.567		push cuối 2 ngày trước
9	rerun-io rerun-io/rerun Visualize, query, and stream to train on multimodal robotics data.	Rust	11.423		push cuối Hôm qua
10	datawhalechina datawhalechina/all-in-rag 🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/	Python	10.939		push cuối 7 ngày trước

Tất cả · 11.474