Havuz

Hosomaki, the intelligence layer for Linux

为 DeepSeek V4.0 等单模态大模型装上眼睛和耳朵 —— 本地视觉+音频 MCP 服务器，基于 Ollama + MiniCPM-V 4.6 + faster-whisper，图片描述·视频分析·语音转文字

I Ran Qwen 3.8 27B on Just 4GB VRAM! (FreeToken Tutorial) - Edge-native MoE serving engine for local LLMs on low VRAM GPUs

RenderCaption - Offline AI Speech to Text & Subtitles Generator.

A 100% private, in-browser AI Study Companion. ByteBrain runs powerful Large Language Models directly on your local PC—no API keys, no serve

HK NPU STUDIO — Local AI for Snapdragon® PCs. NPU-accelerated image generation for Windows 11 ARM64. Featuring Phoenix Boost.

Local-first personal knowledge base CLI — hybrid FTS + pgvector search, a GraphRAG entity graph, and LLM enrichment over your notes, transcr

A high-performance, private, on-device AI chat client built with Flutter. AstraLM runs Large Language Models (LLMs) and Vision models 100% l

Local AI chat and personal agents for macOS. Ollama-powered conversations, customizable characters, controllable memory, and a browser-based

Self-hosted AI workspace for job applications, resumes, cover letters, company research, and interview preparation.

Sync & tag your ChatGPT/Claude exports into Obsidian using a local LLM. No cloud, no API keys.

Windows 线上会议面试助手：多会议平台路由、本地流式语音识别、可选领域模块，并针对金融与会计场景做专项优化。

Weekly WordPress trend summaries with local AI review

Your AI. Your machine. Always on. A personal assistant in one pure-Swift binary.

墨境 Novel Workspace MCP — Local Web + MCP Server + Codex Skill for long-form AI writing; LM Studio and OpenAI-compatible API.

OnDevice Local AI Studio — run LLMs on iPhone offline. SwiftUI workbench with MLX, llama.cpp, whisper.cpp, RAG, and authenticated OpenAI/Ant

NOW AVAILABLE on MICROSOFT STORE - Bulk-delete or move IMAP emails by AI Cleanup (NEW), sender, domain, or nested rules - CLI + Web GUI, std

Local AI Voice Studio for macOS

The last agentic harness you'll ever need. Bring any model; Pennant does the rest on your Mac and iPhone, and asks before anything is sent,

AI-powered GitHub repository assistant with local Ollama models, repository analysis, grounded chat, and GitHub OAuth.

Run stock llama.cpp with the stock Unsloth Qwen3.6-35B-A3B 4-bit on a 16 GB Mac.

Portable offline AI assistant powered by llama.cpp and GGUF models. Run a private local chatbot directly from a USB drive on Windows with no

Open-source ESP32-S3 desktop assistant for LILYGO T-Display-S3: firmware, Windows Bridge, notifications, widgets, games and optional local A

KamehaDB is a cross-platform database GUI - AI. Support query via human language

Qwen Image 2.1 in Frosty Studio: create and edit with 10 references, official prompt enhancement, RGBA and recoverable galleries. Includes F

Local-first Chinese voice typing for macOS — offline ASR, local polishing model, hotwords, and Self-Evolution.

《BSide: Olivia Lin》的本地功能复原与扩展项目：恢复信件、MIDI 演奏、音频/视频回信，并为 3D 演奏保留扩展接口。

Native Mac dictation in a 12 MB download. Free Local mode with Whisper + Parakeet, reproducible benchmarks, optional Cloud. MIT-licensed cli

ИИ под названием Vortex для любых задач. Сейчас уже доступна рабочая версия проекта, которая ежедневно улучшается

A structured agent runtime for LLMs. Structured context, multi-stage workflows, and ECS-based orchestration in a single binary

方寸智匣 LocalBrain：本地大模型、文件与媒体工作台。Windows/Linux 2.2.8，Apple Silicon Mac 2.2.7；按平台维护运行环境，支持本地工具与 MCP 接入。

A lightweight single file AI chat UI for local and cloud models. No backend, no build, just open the HTML file and start chatting

Learn languages by reading and listening, just like LingQ, with a local AI. Free. Forever.

ComfyUI deployment kit for Qwen-Image-2.1 Uncensored (GGUF): ready-to-use t2i & image-edit workflows, ComfyUI-GGUF architecture patches, and

Real-time speech translation with transparent on-screen subtitles. 100% local, no cloud

JEV-guided context compaction for OpenCode. Prune stale tool history instead of rewriting conversations with an LLM.

Self-hosted, local-LLM news reader that ranks, de-duplicates, and summarizes your RSS/Atom feeds privately, on your own hardware.

grep for meaning: ask a question about lines, logs, diffs or JSON and explore the answers live. Runs locally on CPU, one Rust binary.

Native SwiftUI voice client for Hermes Agent — private, self-hosted STT/TTS with iPhone & iPad push-to-talk

MiniMax H3: 4.9x faster local generation and seam-free 4K via synchronized tiles (SyncTile). Benchmarks included.

Open-source local meeting transcription for Discord and Google Meet with real speaker attribution.

Rust bindings for Qualcomm GenieX SDK - Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of

Local, offline text-to-speech and voice cloning on audio.cpp — multi-voice narration, voice design, sound/music generation, and a real-time

Run open AI models on your own computer — a friendly desktop app and local gateway for llama.cpp and more. Private, free, open source.

Published: 2026-10-18

Published: 2026-10-18

Desktop app for browsing and filtering the Xbox Game Pass catalog with on-device AI genre classification

Published: 2026-10-18

The honest Windows companion: cleaning, repair, network & power tuning, disk analysis, app installer and a 100% local AI assistant. No place

Serve DeepSeek and Qwen, run an on-demand model library, and fine-tune with Unsloth QLoRA on 2x NVIDIA DGX Spark. TP=2 vLLM lanes behind one