Qwen: open-source projects on GitHub
106 repositories on Qwen, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
SLOTSTREAM LAUNCHES QWEN3.8 ON MAC
Run Qwen3.8‑Flash‑Next (125B MoE, 104 GB at 4‑bit) on Mac by streaming experts from SSD on demand. Implemented with MLX + Swift, it offers an Ollama‑compatible API.
★ 673 · SwiftHarvester: GitHub Data Collection
An intelligent Python framework for automated data collection from GitHub and web sources. Ideal for researchers and AI developers.
★ 612 · PythonMCO — Multi-Agent Orchestration
A neutral orchestration layer for Claude Code, Codex CLI, Gemini CLI, and other AI agents. 375 stars on GitHub.
★ 557 · PythonMEMT-1.0: LONG-TERM MEMORY FOR LLM
Official MemT-1.0 repository. Implements long-term memory for LLM agents. Supports long context and DeepSeek integration.
★ 537 · PythonRUNNING DEEPSEEK-V4.1 552B ON A SINGLE PC
Xolotl is an engine for running large MoE models (DeepSeek-V4.1-Flash 552B, GLM-5.3-Flash, Qwen3.8, LFM3-Omni) on a single PC with RTX 4090. It delivers 33 tok/s on agent
★ 534 · C++LLM Serving in Kubernetes
OME is an operator for running LLMs in Kubernetes with smart GPU scheduling and support for SGLang, vLLM, TensorRT-LLM, and Triton.
★ 527 · GoFLIDE: INSTANT DECISION INFERENCE
Flide is a decision model inference engine with CUDA support. Provides deterministic inference for Gemma and other models in microseconds. Ideal for AI agents requiring s
★ 501 · PythonQWEN3.6-27B ULTIMATE VERSION
Fully uncensored, enhanced version of Qwen3.6-27B with NVFP4 and DFlash speculative decoding.
★ 495 · PythonMAESTRO ORCHESTRATE: MULTI-AGENT PLATFORM
The platform orchestrates 39 AI agents for Gemini CLI, Claude Code, Codex and Qwen Code. It provides parallel sub‑agents, persistent sessions and built‑in tools for code
★ 490 · JavaScriptCore AI Model Collection
A model zoo for Apple Core AI with Qwen3.5 and Gemma 4 conversion, custom Metal kernels, and a Swift runner.
★ 465 · SwiftOPEN SOURCE AI OFFICE AGENT
Openworkbuddy — local AI office agent: turns one request into ready PPTX, DOCX, XLSX, HTML. Supports DeepSeek, Qwen, Doubao, Claude, Ollama (BYOK), MCP and drives Claude
★ 413 · JavaScriptLLAMAMPERE: LLM ACCELERATION ON RTX 3090
llama.cpp fork optimized for Ampere GPUs. Delivers 110+ tok/s on Qwen 3.8 at 100K context. Runs on 12 GB VRAM with 200K+ context.
★ 380 · C++XINFER - FAST LLM INFERENCE
Xinfer — ultrafast LLM inference in pure Rust, without PyTorch and Python. Enables running models with minimal latency.
★ 354 · RustCLAUDE NIGHT MARKET – 23 AI PLUGINS
A collection of 23 Claude Code plugins for TDD, PR workflow, and development automation.
★ 350 · PythonVERL-OMNI: REINFORCEMENT LEARNING
Framework for RL training of diffusion and multimodal models. 347 stars on GitHub.
★ 347 · PythonDEVO — Agent for Any Models
Open-source runtime agent in Rust for private and corporate environments. Supports DeepSeek, Qwen, Kimi, MCP and local code search.
★ 347 · RustOBSIDIAN TARS: AI TEXT BY TAGS
The Obsidian plugin generates text from tags using models DeepSeek, Claude, OpenAI, Gemini, Ollama and other LLM providers. It works entirely in TypeScript and integrates
★ 338 · TypeScriptTHE PAIR: AUTOMATIC PROGRAMMER PAIR
Two AI agents work as a pair, reviewing each other's code while you sip coffee. Automated pair programming in TypeScript.
★ 337 · TypeScriptHUD-Python RL Evaluation
An OSS environment for RL with ready‑to‑use agent evaluation tools. Run, configure, and get results.
★ 329 · PythonDELPHIOPENAI – API FOR DELPHI
A wrapper for multiple LLM APIs (OpenAI, DeepSeek, Azure, YandexGPT, etc.) for Delphi, enabling easy integration of ChatGPT, DALL‑E, Whisper and other services.
★ 320 · PascalMini-Verl on One GPU
The project allows running a documented subset of verl-style OPD on a single consumer GPU, using typed configuration, Parquet prompts, and PEFT scaling artifacts.
★ 311 · PythonCARWATCH AI AGENT CAR
CarWatch turns Raspberry Pi 5, a dashcam, and local AI into a chat agent for your car. Talk to the vehicle, get data, and control functions in real time. This is a CodeWa
★ 305 · PythonInvincat: AI Agent for Coding
A native Python CLI agent with an autonomous memory system that helps you write code more efficiently thanks to hierarchical learning organization.
★ 303 · PythonPY-IDP: AI FOR DOCUMENT PROCESSING
py-idp — AI-powered IDP platform for Python: 12+ LLM backends, Pydantic schemas, OCR Nanonets‑OCR2‑3B, auto schema and HITL. Includes a FastAPI server, AGPL‑3.0 + commerc
★ 298 · PythonVESTI – MEMORY FOR AI CHATS
Local memory hub for AI conversations: saves, searches, summarizes, and exports chats from all popular platforms.
★ 288 · TypeScriptMULTIMODAL DECISION MODEL
OneJev — multimodal System One model for calibrated answers to questions about screens, photos, video and text in one forward pass.
★ 272 · PythonCOLLECTION OF FREE AI MODELS
Daily‑updated list of free AI models (LLM API), ranked by quality with live status. A single OpenAI‑compatible endpoint automatically routes requests to the best availabl
★ 267 · JavaScriptCONTROL AI AGENTS COMMAND CENTER NOW
The control panel for AI agents: launch, coordinate, and monitor numerous agents in real time. It supports integration with Anthropic Claude and workflow automation via p
★ 250 · JavaScriptSUBTEXT: BEHIND THE MODEL
A tool for analyzing hidden representations of AI models, revealing their internal logic.
★ 248 · HTMLTINYBOT - PERSONAL AI AGENT
Tinybot is a lightweight personal AI agent in Python, constantly improving and ready to help with everyday tasks.
★ 247 · PythonAUTORESUME AI SESSIONS
unsnooze automatically resumes Claude Code, Codex, Grok, Qwen, Kimi, OpenCode, and Antigravity sessions after 5-hour and weekly limits reset. Works in tmux, Zellij, VS Co
★ 231 · JavaScriptPURE-RUST ENGINE FOR QWEN GGUF
RustingStrata is a pure-Rust inference engine for Qwen GGUF (Qwen3–3.8, MoE up to 770B+). Supports CUDA/Vulkan, hybrid CPU+GPU experts, MTP speculative decoding. Up to 1.
★ 231 · RustAI AGENT COST CONTROL
Fast, cross-platform, real-time token usage tracker and cost monitor for Gemini CLI / Claude Code / Codex CLI / Qwen Code / Cline / Roo Code / Kilo Co
★ 229 · RustBROWSER EXTENSION TO CONNECT AI TO VS CODE VIA MCP
Browser extension and local bridge connecting AI chats in browser to VS Code via MCP. Allows controlling code from chat without API keys and terminal.
★ 218 · JavaScriptOPENCODE COPILOT CHAT AI
opencode-copilot-chat gives access to 30+ AI models in GitHub Copilot Chat free via your own API key (BYOK). No Copilot Pro needed — everything works straight from your e
★ 213 · TypeScriptAUTOSHORTS AI CLIPS GAMEPLAY
Automatically creates vertical short clips from long gameplay recordings, analyzing scenes with AI. GPU‑accelerated rendering and optional AI voiceovers make virus‑ready
★ 207 · PythonSPOTTER EMBODIED AI AGENT
Spotter — official codebase for embodied-ai agent that lets LLM drive the robot while VLM corrects its actions. It interacts with RoboCasa and RoboDojo, applying Qwen and
★ 206 · PythonJOANIUM - YOUR SMART AI ASSISTANT
Joanium — a smart and friendly AI assistant built with JavaScript. It answers questions, helps with tasks, and adapts to your style.
★ 169 · JavaScriptTyped Decisions With Probabilities
Open-weight Python model that outputs typed decisions with probabilities in one forward pass. Apache-2.0 licensed weights and code.
★ 168 · PythonAI Learning Mini-Project
The project shows how to build an AI-driven mini-project in a week using Taro, React, and FastAPI, with question generation, instant explanations, web search, RAG base, A
★ 148 · PythonAgentic RL Tutorial & Benchmark
33-chapter Chinese tutorial from RL concepts to GRPO with TRL examples, plus reproducible discriminative-model benchmark comparing encoder, LLM-LoRA, and rule baselines.
★ 146 · PythonMultimodal Image Retrieval System
Practical multimodal image retrieval with intent recognition, prompt engineering, Qwen LoRA, EmbeddingGemma 2, InfoNCE contrastive learning, and RAG components.
★ 129 · Python125B MoE Inference on RTX
Run Qwen3.8-Flash-Next (125B MoE) with 1M context on one or two RTX 3080 10GB cards. Tuned, benchmarked fork of Strata.
★ 71 · C++Self-Hosted Jev Decision Model
Run the selfjev-4b decision model locally with a Jev-compatible API, Python SDK, and tools for fine-tuning and RLCD training.
★ 34 · PythonOpen Decision Model API
Provides an open decision model exposing Jev's API for typed answers (yes/no, choice, score, multi) with probabilities from forward passes, using Qwen3.5-4B fine‑tuned wi
★ 25 · PythonSparkDuet: on-demand model library
The project provides a single OpenAI‑compatible endpoint for running DeepSeek and Qwen models. It serves them via two vLLM lanes (TP=2) on an NVIDIA DGX Spark cluster and
★ 0 · PythonNew projects on this topic in Telegram
Telegram →