Qwen

An open-source Cotypist with macOS system wide AI autocomplete

Claude Code 零基础入门教程，claude code 大陆如何使用教程

Offline, local-only context migration skills across 9 coding-agent sources × 9 destination hosts (registry-derived 81 cells). Stdlib-only; inert handoff for fresh sessions, not live restore.

Free AI models in VS Code Copilot Chat via browser auth. No API keys required.

Offline Cantonese/Chinese voice dictation for Windows & Linux — press a hotkey, speak, and the text is typed at your cursor. CPU-only, powered by Qwen3-ASR via llama.cpp.

Implemented and benchmarked KV cache compression methods for LLM inference in Triton. Optimized kernels for KIVI and TurboQuant with Flash Attention integration - up to 7.11× compression on GPT-2 and 7.31× on Qwen3.5 9B.

1200+ AI models in your GitHub Copilot Chat — free & forever free. VS Code extension powered by OmniRoute: 330+ providers (90+ free) — Kimi, Claude, GPT, Gemini, GLM, DeepSeek, Qwen — with agent mode, tool calling, vision and quota-aware auto-fallback. MIT.

PriorTR (ECCV 2026): training-free, prior-corrected visual token reduction for accelerating multimodal LLMs — image & video.

AI Testing Agent Framework · 16 experts + 32 skills + 49 utils · Multi-LLM (Claude/OpenAI/Qwen/etc) · MCP-native · Open-source · Learn-while-using

基于 llama.cpp 的本地大模型桌面客户端：可视化配置 Qwen3.8-27B 等 GGUF 模型参数，一键启动 OpenAI 兼容 API，内置模型下载与实时监控 | A user-friendly desktop GUI for llama.cpp — visually configure GGUF models like Qwen3.8-27B, launch a local OpenAI-compatible API in one click, with built-in model downloads and real-time monitoring.

DeepSeek Harness plugin: describe_image — give a text-only model vision through an OpenAI-compatible VLM endpoint

ClinePass provider plugin for Opencode — authenticate via Cline Pass (Cline CLI subscription or static API key) and use 10 curated open-weight coding models through Cline OpenAI-compatible API

OpenAI compatible API on top of the free web clients

📡 AI 资讯飞书通知机器人 - 抓取 OpenAI/Anthropic/Google/DeepSeek/Qwen 等 23 个源，通过飞书 Webhook 推送

RTX 5090 decode megakernel adapted as the Qwen3-TTS talker backend, streamed into a Pipecat voice agent

Desktop/OS-Level autonomous agent that observes human-computer interactions to discover and automate repetitive workflows using AI-powered pattern mining.

Claude Code、Codex、Qwen Code、Kimi Code、Qoder CLI 能力矩阵

Powerful AI software runs with Qwen/Quark S1/G1.

A simple text summarization project built with LangChain and Groq. It uses the Qwen model to summarize long text into clear paragraphs. The project also shows how to use system and human messages, load API keys safely from .env, and work with LLMs in Python.

Local Qwen 3.6-27B as a supervised MCP coprocessor for Claude Code (no OAuth interception, no ToS surface).

OpenAI Codex 国内配置工具 —— 支持 DeepSeek/GLM-4/通义千问/Ollama 国产模型，无需翻墙

便捷使用的，使用agnes和qwen的免费api的AI视频输出工作流

基于Ollama本地qwen3:8B模型的数仓数据分析助手-仅作为学习用途

Private, offline multimodal AI for Android using Qwen3-VL, llama.rn, and Whisper.

Text2STL Agent converts natural language prompts into STL files for 3D printing. It runs locally with Ollama/Qwen3, uses Streamlit for the UI, and CadQuery for 3D model generation, with STL preview, validation, and download support.

Multi-platform prompt engine для DeepSeek, Grok, Kimi, Qwen, Gemini и других AI

Autonomous Bitget trading agent with Qwen reasoning, risk-governed receipts, and GetAgent Playbook proof

AI Arena is a dual-model evaluation platform that compares OSS models like Qwen2.5 with frontier models like Claude Sonnet across hallucination detection, bias evaluation, jailbreak resistance, and safety benchmarking. Built for transparent LLM testing, reliability analysis, and AI alignment experimentation.

Local-first threat detection agent for Windows. Runs a 4B-parameter LLM (Qwen3.5-4B) on-device via KoboldCpp. ReAct FSM, MITRE ATT&CK, YARA, OSINT, 15 skills, 4000+ tests.