Havuz

A simpler self-hosted alternative to Open WebUI. Bring your own API keys or local models. Native Android and iOS clients.

Deterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→research→grill→compose→critique, with

A top for local LLMs: memory, paging, GPU and tokens/s for oMLX, Ollama, llama.cpp, vLLM and more

The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives you

Open-source local implementation of MiniMax H3 Context-IR. Turn simple prompts into structured, validated H3 video briefs.

Benchmark local LLM serving by replaying real agent trajectories

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

Open-source control panel for the real llama.cpp: see where a model lands in your VRAM before loading, every llama-server flag per model, on

Self-hosted health-data observatory: sync Apple Health, early wearable plugins, and Garmin/Samsung imports into a canonical TimescaleDB reco

A SillyTavern extension providing a multi-tier memory and narrative context system for AI roleplay. Tracks character facts, relationship his

Pool RAM across old PCs, Macs, and Android devices into a unified local AI cluster

A local-first AI control plane for orchestrating agents, models, tools, and machines from one desktop app.

Open WebUI tool port of Superpowers by Jesse Vincent — brainstorm → spec → plan → execute agentic dev workflow for local LLMs

An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harnes

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

llmBench is a high-depth benchmarking tool designed to measure the raw performance of local LLM runtimes (Ollama, llama.cpp) while providing

System-wide, on-device AI autocomplete for macOS — Copilot-style suggestions in every text field, fully offline and private.

MCP server for Git with local Ollama — zero tokens for git operations

为 JAV 日语视频生成日文、中文或双语 SRT 字幕。支持本地音视频识别、时间轴对齐及 API 或本地模型翻译；网页界面操作，视频与音频留在本机。适用于 Windows + NVIDIA 显卡。

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embe

Low-memory C++20 LLM inference runtime for quantized GGUF models on CPU — mmap-backed weights, paged KV cache, Q4/Q8 kernels, and reproducib

Native macOS workspace for Apple's container runtime. Browse, run, build and clean up Linux containers with live resource gauges, a built-in

Your own AI workspace on your own machines: chat, agents, coding, knowledge bases (RAG) and fine-tuning with local models. Open source (AGPL

YouTube 直播实时 AI 翻译字幕，支持本地 Ollama，英中双向。首次配置，日常双击启动。AI captions for YouTube livestreams with local Ollama. English ↔ Chinese. Windows/NVIDIA p

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b

Your AI company, in your device. Local-first AI platform: chat, agent crew, memory, and a model store sized to your hardware - from 4GB lapt

🥷 Give your codebase a black belt. Local code intelligence, security analysis, and compiler-backed facts for humans and AI.

Open-source Windows AI IDE built with .NET 10 WPF, featuring a fine-tuned local AI router (1.5B), live Blender & Unity copilots, self-healin

VRChat向けのAIエージェント実装です。音声認識、ローカルLLM、VOICEVOX系TTS、VRChat OSC、YOLO/Pose、VLM、長期記憶、感情/欲求モデル、自律行動を組み合わせ、会話だけでなくアバターの移動、視線、表情、エモート、Use/Grab、ピアノ演奏まで

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

A local-first language-learning app for the desktop. Lessons, stories and conversation practice are generated by an AI model running on your

A Visual Basic 6 clone for macOS, Windows and Linux: Windows 98 look, form designer, VB6 language, 59 classic controls, VB6 project import,

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

Slotstream, büyük bir MoE modelini SSD’den parça parça yükleyip yoğun kullanılan expert’leri bellekte önbelleğe alarak Apple Silicon Mac’lerde çalıştıran yerel bir inference engine’dir.

Neden yükseliyor · README, 48 GB M5 Pro üzerinde belirli koşullarda 15.86 tok/s ölçümü ve prompt işleme iyileştirmeleri yayımlıyor; son 28 günde 271 commit ve 5 farklı yazar da yoğun geliştirme faaliyetine işaret ediyor. Ancak proje yalnızca 30 günlük ve mevcut sürüm için nitelikli tam yanıt hızı ölçümünün hâlâ beklediği belirtiliyor.

SiliconScope, Apple Silicon Mac’lerde sistem kaynaklarını ve özel hızlandırıcıları izleyen, ayrıca uzaktaki makineleri aynı panele ekleyebilen bir macOS monitörüdür.

Neden yükseliyor · 111 günde 966 yıldıza ulaşması ve son 28 günde 48 commit alması dikkat çekiyor; README’deki ANE ve memory-bandwidth ölçümleriyle uzaktaki makineleri tek panelde toplama özellikleri de ayırt edici bir kullanım vaadi sunuyor. Üç farklı yazar aktiviteye işaret etse de ekip genişliği sınırlı; yıldızlar tek başına benimseme veya kalite kanıtı değil.

quackd, farklı robotları tek bir CLI üzerinden LLM tabanlı görevlerle yönetmeyi ve birlikte çalıştırmayı amaçlayan Python aracıdır.

Neden yükseliyor · 30 günlük bir repoda 505 commit ve 241 yıldız dikkat çekiyor; ancak son 28 günde yalnızca 2 farklı yazar görünmesi, hareketliliğin sınırlı sayıda katkıcıda toplandığını düşündürüyor. README yedi robot gövdesi desteği bildiriyor, fakat bunlardan yalnızca birinin gerçek donanımda çalıştığını; diğerlerinin simülasyon veya mock olduğunu belirtiyor.

本地优先的全栈 AI 创作工作站：AI对话 · AI漫画 · 漫剧创作 · 写作台 · 知识学习五大模块；vLLM / llama.cpp / Transformers 多引擎本地推理，显存智能调度、舱壁隔离自愈、仅供学习使用，欢迎交流指正。（最新进度（除插件系统）受到协议限制，

Downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac. Chat, vision, speech and generative models with per-model

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.

Open-source AI meeting notes for Mac. Records mic + system audio with no bot, transcribes on-device or via OpenAI / Deepgram / Groq, identif

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

Private on-device AI chat for Android - runs any GGUF model locally via llama.cpp with ARM-optimised SIMD. Zero network permissions, encry

Your AI intranet: network the computers you already own for inference and training.

A living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, delegate, learn & hold meetings. Per-agent swappabl

Turn your Win, Mac or DGX Spark into an AI hotspot. Nightshift races hundreds of attempts overnight and keeps what passes. Plus the open con

Turn your documents into a Markdown wiki you can read, that answers with citations. Works with any LLM provider, Ollama included. CROW class

Private AI on premise

Open Dungeon — the first easy-to-use, fully local AI roleplay app. Story and inline scene images generated 100% on your machine (Gemma 4 QAT