Bảng xếp hạng repo GitHub theo sao, tốc độ tăng trưởng và mức độ hoạt động.
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
🤗 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.
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode & 20+ CLIs via BYOK.
A high-throughput and memory-efficient inference and serving engine for LLMs
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A coding agent for open models like Kimi K3 and GLM 5.3
| # | Repo | Ngôn ngữ | Sao | Xu hướng 30 ngày | Cập nhật lần cuối |
|---|---|---|---|---|---|
| 1 | Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. | Go | 180.490 | — | push cuối 2 ngày trước |
| 2 | 🤗 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. | Python | 165.014 | — | push cuối 2 ngày trước |
| 3 | Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发 | JavaScript | 158.380 | — | push cuối 5 ngày trước |
| 4 | Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack. | TypeScript | 155.102 | — | push cuối 2 ngày trước |
| 5 | 🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode & 20+ CLIs via BYOK. | TypeScript | 94.977 | — | push cuối 2 ngày trước |
| 6 | A high-throughput and memory-efficient inference and serving engine for LLMs | Python | 91.290 | — | push cuối 2 ngày trước |
| 7 | 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team. | TypeScript | 82.334 | — | push cuối 2 ngày trước |
| 8 | Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more. | Python | 75.889 | — | push cuối 2 ngày trước |
| 9 | Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) | Python | 74.658 | — | push cuối 3 ngày trước |
| 10 | A coding agent for open models like Kimi K3 and GLM 5.3 | Rust | 68.271 | — | push cuối 3 ngày trước |
Tất cả · 11.474