Havuz

Local-first MCP server for Obsidian vaults — no plugins, no API keys, with schema-validated Bases (.base) support.

一键本地 AI 工作站：模型市场（多源测速+断点续传）、llama.cpp+MNN 双引擎、多芯片检测（NVIDIA/AMD ROCm/华为昇腾）、LLM/TTS/图像/视频/3D/超分、Agent 助手；Electron + 原生 JS + Python sidecar，数据默

Open-source local AI server configs, GFX906 runtime maintenance, reproducible benchmarks, and QC methods for affordable AI research infrastr

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

Local and cloud GPU interference model orchestrator exposing OpenAI-compatible API from different engines

Verified multi-source distribution for local LLM weights

Build your own personal AI agent, one mission at a time. Mission 01: your AI learns who it's working for.

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

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

《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。

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

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

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

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

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

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

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

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

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。Apple Silicon Mac 2.3.0，Windows/Linux 2.2.9；Drama 3 本人克隆、长稿配音与分段修改，按平台维护运行环境。

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

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

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

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

Make your own private AI bot on your own computer. Say what bot you want; BuildBot finds apps, books and live info, shows one plan, and buil

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

Advanced local AI prompt generator for image & video models — reference images, dataset creation, prompt refinement, model-specific outputs

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

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

Local-first personal AI voice assistant for web, Windows, Telegram, Discord, Slack & WhatsApp — Ollama + MCP tools, Fluid Motion audio visua