Havuz

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

Offline LLM app for iPhone: run open models from Hugging Face on-device with llama.cpp, MLX, Core ML and Apple Foundation Models. No account

dgx-spark-qwen38 is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Ace

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。

Qwen 3.8 27B on a $1,400 Strix Halo: frozen optimal config, 262k needle-exact retrieval, vision fixed, delegation-card certified

给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH 插件）。

Self-hosted API-first AI call center: AI talks, code controls the call. AI agents answer every call; humans take over without dropping it. R

本机优先的 AI 办公工作台 · A local-first AI office workbench. Turn requests and source material into editable PPTX, DOCX, XLSX and HTML files. Choose

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

CCswitch的全面升级，专门优化codex体验。支持官方订阅和第三方模型混用，自动路由，支持v2subagent使用第三方模型

Use third-party and Chinese model APIs as bounded Codex subagents while keeping Codex as the main agent.

DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook

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

2026 年编程导航 AI 编程实战新项目，基于 Taro + React + FastAPI + DeepSeek 的 AI 闯关学习小程序，支持一句话 / 文本主题 AI 出题、闯关答题与即时讲解、联网搜索增强、RAG 私有知识库出题、AI 生图配图、微信登录与通关复盘报告。

Interactive AI avatar live streaming with Qwen SSE, CosyVoice3 voice cloning and MuseTalk 1.5 lip-sync. Chrome chat collection, autonomous h

On-device streaming speech-to-text for macOS, built on Qwen3-ASR via MLX

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

MAC, doğal dildeki tasarım brief’lerinden düzenlenebilir CAD parçaları ve deneysel olarak çok parçalı assembly’ler üretir.

Neden yükseliyor · 59 günde 1006 yıldıza ulaşması, doğal dilden CAD üretimine yönelik ilgiyi ve görsel olarak etkileyici parça/assembly demolarını yansıtıyor. Ancak README, assembly örneklerinin seçilmiş çıktılar olduğunu ve ölçülmüş prompt başarı oranı sunmadığını belirtiyor; 28 günde 22 commit olsa da farklı yazar sayısının 1 olması benimseme ve sürdürülebilirlik kanıtını sınırlıyor.

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

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the ha

Open-source local-first computer-use agent for Linux, Windows, and macOS, powered by local VLMs or compatible APIs.

hummingbird is a lightweight, zero dependency runtime for massive open source Mixture of Experts (MoE) language models. It unifies SSD, RAM,

Clone a voice from a few minutes of audio and generate speech locally: Qwen3-TTS fine-tuning pipeline with CLI and web UI

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

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

Tiny engine, immense models — run large MoE LLMs (gpt-oss, Mixtral, Qwen3-MoE) on ordinary machines by streaming experts from disk. OpenAI-c

Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimiz

Automatically resume Claude Code, Codex CLI, Grok, Qwen Code, Kimi CLI, OpenCode, and Antigravity sessions when 5-hour or weekly usage limit

Diktafon is a private, open-source voice memo app that transcribes and summarizes your recordings entirely on your device — organized like c

Fully local vulnerability research pipeline - 14B code-specialized LLM reviews every source file exhaustively.

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

Qwen3.6 vLLM Toolkit — Launcher + Templates, Optimized for 2×24 GB. vLLM launcher with an optimized hybrid chat template drawing from the be

To know what models don't say out loud.

CPU-first, eager-execution tensor/autograd runtime and LLM inference engine written in pure Zig

帮你的 Claude Science 一键接入你自己的 API：DeepSeek / 通义千问 / 智谱 GLM / Kimi / MiniMax / 小米 MiMo / 硅基流动 / OpenRouter / 任意 OpenAI·Anthropic 兼容端点

🧠 One LLM, split across a Mac (Apple MPS) + a Windows PC (NVIDIA CUDA) — heterogeneous pipeline inference over a framework-neutral wire, bit

WarMatrix 2026: Next-Gen Tactical Simulation & AI Command Console

A local-LLM privacy layer for anything you paste into a cloud model — detect, tokenize, restore. Zero deps, reversible, strong on Chinese.

Academic Commercialization Assessment Agent, araştırma makaleleri veya konularından kaynak bağlantılı ticarileştirme değerlendirme taslakları üretir.

Neden yükseliyor · 94 günde 770 yıldıza ve son 28 günde 267 commite ulaşması görünür ilgi ve yoğun geliştirme gösteriyor. Ancak commitlerin tek yazardan gelmesi, bu aktivitenin bağımsız katkıcı veya topluluk benimsemesiyle doğrulanmadığı anlamına geliyor; ilginin kaynağı verilen bilgilerden kesinleştirilemiyor.

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

Open Source Brain Platform | AI training and inference in Rust

Locally fine-tuned Russian RAG models: document splitter, query expansion, retrieval embedder. Teacher distillation → GGUF → llama.cpp on AM

Fastest MoE/LLM inference runtime for consumer and edge Blackwell GPUs. SN74 on Gittensor.

Private, offline AI coding agent for local Qwen models via Ollama — zero dependencies, real tools, multi-agent. Your code never leaves your

One ComfyUI skill for every AI coding agent (Claude Code, Codex, Gemini CLI, Qwen Code): drives a local ComfyUI end to end. 75 model prompt

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。

An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end using a single 7B open-source

Beastmode: MofA (Mixture of Agents) orchestration framework for Hermes/OpenClaw/Codex with MemroOS-style context continuity.

No longer developed. Use Speech Studio: https://github.com/timoncool/speech-studio. Portable Windows TTS — Higgs Audio v3 + AI text director