Discover trending repositories tagged qwen, ranked by recent growth and activity.
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
GitHub repository with 16,362 stars and 2,458 forks.
Trending score: 5.17; stars gained: +581; forks gained: +85.
Language: JavaScript
Topics: claude-code, cursor, ai-agents, ai-gateway, anthropic, chatgpt
Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
GitHub repository with 173,212 stars and 16,447 forks.
Trending score: 3.96; stars gained: +222; forks gained: +40.
Language: Go
Topics: deepseek, gemma, gemma3, glm, go, golang
A high-throughput and memory-efficient inference and serving engine for LLMs
GitHub repository with 81,978 stars and 17,668 forks.
Trending score: 3.75; stars gained: +79; forks gained: +46.
Language: Python
Topics: amd, blackwell, cuda, deepseek, deepseek-v3, gpt
🤗 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.
GitHub repository with 161,297 stars and 33,416 forks.
Trending score: 3.69; stars gained: +78; forks gained: +27.
Language: Python
Topics: nlp, natural-language-processing, pytorch, pytorch-transformers, transformer, model-hub
A GPU cluster manager that configures and orchestrates inference engines like vLLM and SGLang for high-performance AI model deployment.
GitHub repository with 5,103 stars and 541 forks.
Trending score: 2.51; stars gained: +11; forks gained: +1.
Language: Python
Topics: ascend, cuda, deepseek, distributed-inference, genai, high-performance-inference
Fast LLM speculative inference server for consumer hardware.
GitHub repository with 2,330 stars and 217 forks.
Trending score: 2.31; stars gained: +17; forks gained: +3.
Language: C++
Topics: kernel, llama-cpp, local-ai, nvidia-cuda, qwen, rtx3090
Local, open-source AI app builder for power users ✨ v0 / Lovable / Replit / Bolt alternative 🌟 Star if you like it!
GitHub repository with 20,518 stars and 2,435 forks.
Trending score: 2.05; stars gained: +8; forks gained: +7.
Language: TypeScript
Topics: ai-app-builder, anthropic, artificial-intelligence, bolt, deepseek, gemini
TokenSpeed is a speed-of-light LLM inference engine.
GitHub repository with 1,366 stars and 141 forks.
Trending score: 1.86; stars gained: +6; forks gained: +2.
Language: Python
Topics: blackwell, deepseek, gpt-oss, kimi, lightseek, llm
AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models
GitHub repository with 7,388 stars and 1,439 forks.
Trending score: 1.76; stars gained: +10; forks gained: +2.
Language: Rust
Topics: ai-pair-programming, ai-workflows, artifical-intelligense, claude-3-7-sonnet, claude-4, claude-4-sonnet
Never stop coding. Free AI gateway: one endpoint, 160+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline & Copilot to FREE Claude/GPT/Gemini. RTK+Caveman stacked compression saves 15-95% tokens, smart auto-fallback, MCP/A2A, multimodal APIs, Desktop/PWA.
GitHub repository with 5,742 stars and 993 forks.
Trending score: 1.72; stars gained: +65; forks gained: +15.
Language: TypeScript
Topics: a2a, ai-agents, ai-gateway, anthropic, claude, claude-code
SGLang is a high-performance serving framework for large language models and multimodal models.
GitHub repository with 28,889 stars and 6,343 forks.
Trending score: 1.72; stars gained: -55; forks gained: +18.
Language: Python
Topics: attention, blackwell, cuda, deepseek, diffusion, glm
FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B
GitHub repository with 281 stars and 32 forks.
Trending score: 1.65; stars gained: +7; forks gained: +0.
Language: C++
Topics: cuda, cuda-kernels, realtime-inference, realtime-vla, gr00t, gr00t-n1-6-3b
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
GitHub repository with 28,268 stars and 7,128 forks.
Trending score: 1.55; stars gained: +24; forks gained: +4.
Language: TypeScript
Topics: agent, claude, deepseek, llm, mcp, nextjs
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
GitHub repository with 4,212 stars and 331 forks.
Trending score: 1.34; stars gained: +13; forks gained: +1.
Language: C++
Topics: amd, llama, llm, llm-inference, local-server, mistral
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
GitHub repository with 71,891 stars and 8,787 forks.
Trending score: 1.30; stars gained: +22; forks gained: +2.
Language: Python
Topics: fine-tuning, llama, llm, peft, transformers, rlhf
🧑🚀 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.
GitHub repository with 8,482 stars and 887 forks.
Trending score: 1.12; stars gained: +10; forks gained: +2.
Topics: awesome-list, book, course, large-language-models, llama, llm
♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️
GitHub repository with 779 stars and 75 forks.
Trending score: 1.06; stars gained: +2; forks gained: +0.
Language: Go
Topics: golang, llm, openai, self-hosted, api, llm-agent
Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.
GitHub repository with 194 stars and 10 forks.
Trending score: 1.04; stars gained: +10; forks gained: +1.
Language: TypeScript
Topics: agent, aliyun, cli, happyhorse, modelstudio, qwen
Continuum — the agent runtime by ShyftLabs. Build, orchestrate, ship.
GitHub repository with 69 stars and 6 forks.
Trending score: 0.93; stars gained: +8; forks gained: +0.
Language: Python
Topics: agent-framework, agentic-ai, ai-agents, ai-orchestration, anthropic, enterprise-ai
一个让 Claude Code 调用 Codex 干活，并可以同时调用多个模型（GPT、Kimi、DeepSeek 等）的 MCP 工具。
GitHub repository with 42 stars and 0 forks.
Trending score: 0.92; stars gained: +8; forks gained: +0.
Language: Python
Topics: claude-code, codex, codex-cli, deepseek, fastmcp, kimi
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
GitHub repository with 9,336 stars and 832 forks.
Trending score: 0.92; stars gained: +6; forks gained: +1.
Language: Python
Topics: ggml, pytorch, chatglm, deployment, flan-t5, llm
Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.
GitHub repository with 250 stars and 32 forks.
Trending score: 0.81; stars gained: +5; forks gained: +0.
Language: Rust
Topics: agent, llm, qwen, rust, vllm
Proxy API OpenAI-compatible que usa automação com Playwright para rotear requisições para modelos do Qwen com suporte a múltiplas contas, tools e sessões persistentes.
GitHub repository with 106 stars and 50 forks.
Trending score: 0.76; stars gained: +5; forks gained: +0.
Language: TypeScript
Topics: docker, hono, llm, openai, playwright, proxy
Hermes Agent中文站- 中文实战入口：上手路径、国内落地、OpenClaw 共存迁移、排障参考与可下载方案包。
GitHub repository with 22 stars and 3 forks.
Trending score: 0.75; stars gained: +4; forks gained: +0.
Language: Python
Topics: agent, ai, ai-agent, ai-agents, ai-workflow, chinese-docs