Havuz

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

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

🤖 Full-stack AI agent app built with React, TypeScript and LangGraph JS. Streaming, multimodal input, human-in-the-loop, native + MCP tools,

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。

Local LLM Server Manager + LlaMA.cpp + Chat

SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A

An inference framework customized for AI MAX 395, compatible with both Linux and Windows, and supports deploying only qwen3.8-flash-next. Th

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

Small enough to run on your Mac. Smart enough to ask. An open-source computer use agent for macOS, with local models (MLX) that see, decide

Source code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Python, Node.js and a shell built

Swift SDK for running chat, vision and speech models on iPhone and Mac with Apple's Core AI. Model download and caching, FoundationModels in

Pure-Rust MoE inference engine for Qwen3.5/3.6/3.8 GGUF. CPU+GPU hybrid experts, NVRTC CUDA kernels, OpenAI-compatible server. 2x llama.cpp

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

多模态检索实战：意图识别、Prompt 工程、Qwen LoRA、EmbeddingGemma 2 与 InfoNCE 对比学习。含真实演示、自有数据接入、训练评测及 RAG 检索组件学习指南。

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

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。

A native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and deliver

A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-device. MLX-native, Ollama/OpenAI

ApocData · AI-native financial database for China A-share market. Drop-in Skill / MCP for Claude,ChatGPT, Qwen, Kimi, DeepSeek agents.

OpenClaw Companion / OpenClaw 中文助手：中英双语、安全编排官方 OpenClaw 安装、配置、检查、升级、备份与诊断。社区项目，非官方。

collabosm, kullanıcının Google Colab hesabında GPU başlatıp Qwen3.8 modellerini yerel uygulama ve OpenAI uyumlu API üzerinden kullanmasını sağlar.

Neden yükseliyor · 3 günlük bir repoda 87 yıldız dikkat çekici bir başlangıç; ancak yıldızların neden geldiği ve kullanıcıların uygulamayı gerçekten çalıştırıp çalıştırmadığı mevcut verilerden anlaşılamıyor. Son 28 günlük commit ve farklı yazar ölçümleri de yok.

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

Curated list of open-weight AI models with commercially exploitable licenses, verified benchmarks, and no EU restrictions.

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

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

A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-tea

A 4B decision model: calibrated probabilities for yes/no, choice and score questions over long inputs.

Continuum — the agent runtime by ShyftLabs. Build, orchestrate, ship.

Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option.

Free, open-source connector agent chatbot AI browser to many App via MCP.

ACE (AI Chat Exporter) · Privacy-focused opensource browser extension to export AI chats from ChatGPT, Claude, Gemini, DeepSeek, and more to

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM i

An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine that d

OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisi

The local AI app built for the Mac. Run LLMs like Qwen, Gemma and GPT-OSS on Apple Silicon, including models far bigger than your Mac's memo

Multi-Agent AI Desktop Client — 20 specialists auto-collaborate on your tasks. Visual Skill Store, PM orchestrator, streaming chat. Works wi

Self-hosted voice gateway in Go that speaks the OpenAI Realtime (GA) WebSocket protocol and runs a cascaded ASR → LLM → TTS pipeline behind

AI-assisted text editor for Windows with local LLM support, text rewriting, style improvement and Unicode cleanup.

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

Open Source Brain Platform | AI training and inference in Rust

ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, verifi

Hybrid GPU + CPU inference for mixture-of-experts models, written in Rust down to the CUDA kernels. A drop-in llama-server.

The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, con

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）。

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.

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

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