Havuz

Fully local voice AI for iOS

AI agents and workflows for Kotlin Multiplatform, as small typed graphs: loops, parallel steps, streaming, save points and human approval. I

Reproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the

The best model under 200B at near 10 token/s exact batch throughput on a single laptop CPU, with an automatic 8 GB RAM path. Native C, no GP

Run the native 284B-A13B DeepSeek-V4-Flash-0731 LLM locally on one laptop CPU: pure C, 8 GB RAM minimum, no GPU, best TPOT 0.892 s/token, re

Fast, private, on-device dictation for Apple silicon Macs

edge-dit.cpp — a native C/C++ inference engine for Diffusion Transformers (DiT), designed for local and resource-constrained devices with au

Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tools;

Introducing Muse Glimmer: open-weight 30B agentic multimodal model that runs on your device (Meta). Interactive local agent lab + guide. Apa

Provider-neutral bounded agent runtime for Android/JVM: controlled context (trust/priority/budgets), profile-scoped tools, OpenAI-compatible

The local-first AI knowledge workspace — an infinite canvas for research, learning, and creation (Tauri 2 + Vue 3)

Local, real-time system-audio captioner + translator for macOS — Whisper + a local LLM + a glass overlay. Fully offline.

Intents is a native macOS workbench for evaluating Apple's on-device Foundation Models.

CubicLM is a unified cross-platform AI workspace with local GPU acceleration (GGUF, LiteRT-LM). Supports on-device image generation, 23+ clo

Relic is the open-source, end-to-end encrypted clipboard manager. Everything you ever copy, indexed by local AI, synced across Windows, macO

Electron + Next.js desktop AI assistant that runs GGUF models locally using llama.cpp. Designed for offline use, portability, and zero-insta

Private, fully offline photo search for Android. Find photos with words in English, Arabic, French, Russian or Spanish, or with another phot

Run GPT-OSS-120B on a 16 GB Mac. Streams mixture-of-experts weights from SSD so only the 2 GiB trunk stays resident. Swift + Metal, no depen

Mobile-native agent SDK for building on-device AI agents with sandboxed execution, extensible tools, and x-app / x-agent / x-channel connect

Translate and rewrite without switching apps. Free, open-source, on-device writing for Mac. No account or API key.

Free, open-source Mac dictation built for accessibility. Press a key, speak, and it types in any app. Whisper and AI cleanup run fully on yo

Fast WebGPU runtime for 1-bit (binary-weight) LLMs in the browser. Bit-exact, zero runtime dependencies.

Custom converter: open-weight Hugging Face LLMs/VLMs -> on-device LiteRT-LM (.litertlm), with one-command reproduction

A free, fully local, minimal-setup voice dictation app for macOS - built specifically for developers.

Faraday — the local private voice agent for your phone.

Hands-free on-device voice loop for macOS: Apple SFSpeechRecognizer + cloned-voice TTS, continuous listening, zero cloud. Originally built t

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

On-device shell command generator for macOS Tahoe. Uses Apple's 3B model with dynamic few-shot retrieval from 21k tldr examples.

A local-first second brain for scientists, researchers, coders, and nerds.

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

Android SDK and MCP server: 157 tools for calendar, contacts, SMS, files, camera, sensors, notifications and UI automation, for on-device LL

Native iOS DeepSeek Harness port: BYOK inference, on-device Agent tools, iSH sandbox, Cordis plugins, and trajectory.

Fault injection framework for on-device AI. Pure Dart core (sate_core) + Flutter package (sate_ai). Android, iOS, Web, and CLI targets.

SDK for building on-device AI applications on Arm with reusable building blocks across inference runtimes.

Fast KV-cache quantization for Apple Silicon (MLX) — 43 research-adapted compression methods with Metal kernels

A local-first macOS app to catalog, organize, and clone the open-source repos you actually use. No account, no cloud.

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

Free, open-source AI coding agent & multi-agent teams for macOS — runs 100% on-device via Ollama or LM Studio. Autovisor, an autonomous Supe

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

Android 16 fork. AI as a platform primitive. Twelve capabilities, one shared runtime, every app. OEM-pluggable. Apache 2.0.

Native macOS image generator for FLUX.2 Klein — fully on-device on Apple Silicon via MLX. No Python, no ComfyUI, no server.

web-ai-sdk: TypeScript SDK for the Web AI surface (Prompt, Writer, Rewriter, Proofreader, Translator, Summarizer, Language Detector, WebMCP)

Pi agent for Android — sideload the APK and run a Pi coding agent on your phone. Single-APK, on-device Termux runtime, Claude Pro/Max OAuth,

[Archived] AAOSP, predecessor to JibarOS. Early experiment in OS-level on-device AI (MCP + local LLM on Android 15). See JibarOS for the act

100% offline voice dictation for macOS, Windows & Linux — Whisper & Parakeet on-device, no cloud, open source.

macOS-Port von kimi-k3-in-c: Patch, Installer und Validierung für Apple Silicon. Ohne Modellgewichte.

The first native Swift inference engine for Gemma 4 on Apple Silicon / iOS

Use many on device and cloud models with Apple's Foundation Models framework in iOS and macOS with a full chat experience.

P2P semantic matching for on-device AI agents. No server, no cloud.

Your own voice + text AI assistant, embedded with one script tag, running 100% in the visitor's browser.