Havuz

OpenAI-compatible inference server for Qwen3.8 on one RTX 5090 / RTX PRO 6000: the 27B at ~170 tok/s (peaks ~370), Flash-Next (125B MoE) at

Hybrid rule-based and context-aware LLM evaluation system for Chinese-to-Japanese game localization QA.

The models on your disk, put to work. A private desktop app for open models — chat, a coding agent built for small models, text-to-image, te

Git-Native Coding Agent for Mac

Local LLM-maintained personal wiki, built on Karpathy's LLM-Wiki pattern. Runs on Ollama + Qwen3 + QMD.

Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools

Serving Qwen3.8-27B-FP8 on a single DGX Spark (GB10): 7.88 to 58.5 tok/s single-stream from decode strategy alone, weights untouched. Specul

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

Inference engine for large language models on consumer GPUs, with deep optimization for older hardware

Free, open-source AI autocomplete for macOS — on-device ghost-text suggestions in every app. A private, local Cotypist alternative built wit

AI 厂商动态别挨家追：每天巡检 OpenAI、Claude、Gemini、DeepSeek、通义、Kimi 等的官方博客与更新页，生成可订阅的 RSS，英文原文逐段精译为中文，并附 70 家免费额度 / 限时活动总表（实时抓自官方页、带官方链接可复核）

DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

基于 Spring Boot、微信 iLink SDK 与阿里云百炼的多模态微信机器人，支持文本、图片、语音、Function Calling、Skill 编排和本地 RAG。

🚀 Multi-agent orchestration for Qwen Code CLI. 24 specialized AI agents and 82+ skills working as a professional dev department. Built for A

Serving 4-bit Qwen3.8-27B on a single DGX Spark (GB10): 75 tok/s single-stream, 246 tok/s aggregate at 8-way concurrency. NVFP4 vs MixedInt4

A lightweight, general-purpose harness for tool-using LLM agents, fair benchmark evaluation, harness baselines, and personal assistant workf

We have caveman system prompts and skills for AI models to reduce token use, why not try bake it into the model itself with fine-tuning?

Durable local inference for Oh My Pi: NInfer + Qwen3.8 27B on one RTX 3090/4090/5090, with restart-resumable OpenAI Responses state.

The most powerful open-source TradingView AI agent. 50 tools, 15 models (Claude, GPT, Gemini, Qwen, DeepSeek, MiniMax), Pine Script v6, quan

Windows 版 Codex Desktop 简体中文语言包，一键安装汉化；支持 codex汉化、Codex 中文菜单、国产模型接入、DeepSeek/千问/智谱、多账号切换、跳过官方登录。

Pure-Rust, memory-safe, CPU-only runtime for Qwen3-TTS zero-shot voice cloning: no Python, no ML framework, no GPU. Verified seam-by-seam ag

Give the agent "this" and he gets a real PC.

The official Qwen Studio app only supports Windows and macOS. This project brings the same desktop experience to Linux.

Hemmingway-1: a 27B model that writes the way a person writes. Open weights, free for non-commercial use (CC BY-NC 4.0); commercial use by a

Local LLM inference engine written from scratch in Rust — hand-written AVX-512 assembly kernels, Metal & Vulkan compute shaders. Supports Qw

Transformers for decision models: fine-tune, load and serve calibrated decsion-model on any Hugging Face model.

Free, open-source AI coding agent for terminal and browser. A Claude Code / Cursor alternative that runs offline with Ollama or with your ow

Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent

High-performance OpenAI & Anthropic compatible API gateway for Qwen with multi-account rotation, interactive TUI dashboard, and resilient to

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflo

Crow — a local AI agent, not a chat box: 30 tools, MCP, memory, skills, goals, subagents, vision, and image generation and editing with Qwen

Ultra cost-effective terminal AI coding assistant with excellent token cache hit rate. Built in ~10K lines of Go, it uses DeepSeek by defaul

Ollama-compatible LLM server on a tuned llama.cpp fork. Beats vllm by 40% on single stream decode, and by 20% on multi stream decode, and be

qMLX: Custom inference engine for Qwen 3.5 122B on Apple Silicon, extending MLX with hybrid attention support, SSD-backed KV cache, and RYS

llama.cpp speculative decoding measured on one RTX 3090, Qwen3.6-35B-A3B UD-Q4_K_XL, commit 3737e4137. Published figures are re-derived from

UI-UX: a 4B multimodal LLM for mobile UX defect diagnosis, with UXBench — the first vision–language benchmark for UX reasoning (CVPR 2026 Fi

Any Model for VS Code Copilot

Self-hosted decision model (selfjev-4b) with a Jev-compatible API: Python SDK, server, fine-tuning and RLCD.

Qwen3.8-Flash-Next (180B MoE) on one 12-16 GB NVIDIA GPU, Linux or Windows. Own engine, own compression.

A powerful, lightweight agentic desktop agent built for engineers and work.

Pixel-Pets: A local, open-source virtual pet ecosystem on M5Stack. 100% AI-authored C++ (Claude) by a 10yo maker. Includes Muffin (LLM), Vis

Native AI assistant for macOS, built with SwiftUI and llama.cpp. Run local LLMs offline, work with PDFs, and create custom AI assistants. Op

AI coding agent in your terminal. Works with any LLM - DeepSeek, Qwen, GPT-5, Claude, Gemini, Kimi, Ollama. 100+ models via litellm. ~1300 l

Run Qwen Code as a coding agent through an OpenAI-compatible API.

Run LLMs and Ollama Qwen across AMD XDNA1 NPU, CPU, and GPU on Ryzen AI Linux systems.

Can't find subtitles? Generate SRT/ASS subtitles from any video with local AI and auto-translate them — no internet, free. macOS & Windows.

阿亮开源的 Skills 合集：短剧成片 / 电商详情图 / 儿童故事 / 有声绘本 / 配音 / 多人播客。一句话触发，AI 走完整 AIGC 流程。

让 Codex 白嫖 NVIDIA 免费顶级模型，一键接入 | Transparent proxy between Codex and NVIDIA NIM — use NVIDIA's free hosted top-tier models with Codex

A web-based memory usage and performance calculator for Huggingface GGUF models

一键配置各类 AI Agent 工具的 MCP、Skills 和规则；支持 Claude Code、Codex、DeepSeek Harness、OpenCode、Cursor、Gemini CLI、Qwen Code 等。 One-click local setup for M