Havuz

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or clo

Honest local LLM deployment planning and benchmarking for high unified-memory Macs and future Linux/NVIDIA rigs.

Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any GGU

Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI + sy

Your personal context engine for macOS, with Windows and Linux in alpha: on-device meeting notes, screen recall, dictation, and autocomplete

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

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

OpenVitamin is a local-first AI execution platform that unifies Agents, Workflows, and multi-model inference into a single programmable syst

Local LLM inference on Xbox Series S in Developer Mode: llama.cpp (GGUF) + ONNX Runtime GenAI, an OpenAI-compatible LAN endpoint (off by def

Raspberry Pi 5 home NAS: CasaOS apps, Nur Hub and the Nur app (local AI, Fish Audio voice), a 3D-printed case and an ESP32-S3 touch screen

Clonación de voz y texto a voz 100% local con Qwen3-TTS y llama.cpp. Funciona en CPU y GPU, 10 idiomas, interfaz web en español.

Hermes Agent (NousResearch) sandboxed by NVIDIA OpenShell — hardware-enforced network/filesystem/syscall policy, full memory + gateway stack

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

Turn an old Android phone into a home server: SSH, web hosting, Jellyfin with hardware transcoding, Immich, qBittorrent, Home Assistant and

♟️ llama-modchip v2.1: Run 30B Sparse MoE LLMs on Pure CPU (0 GPUs) at 20–60.4 tok/s with a 256K Context Window via a 1.64MB Stockfish-PVS +

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

🔒 Your private AI assistant, 100% local on Windows: chat, vision, documents (RAG), web search, images, videos with sound, voice, code projec

AI work that doesn't evaporate. A workspace for building, tuning, and publishing governed AI products.

NeveAI é uma plataforma de IA local privacy-first, desenvolvida para oferecer uma experiência de alta performance na execução de LLMs, reduz

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

Your coding agents forget. Graft doesn't. Persistent local memory that brings back fixes, decisions and project knowledge when they matter —

A terminal AI agent you can fully undo - every file and shell action is snapshotted and reversible. Model-agnostic (any LLM), and connects t

Benchmark your local LLMs: speed, memory, and quality, in one command. TUI leaderboard for Ollama, LM Studio, llama.cpp, and vLLM.

Android keyboard with local AI (Ollama, Whisper, MCP) or cloud (Gemini, Groq, OpenAI)

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

llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 3080.

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

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

llama.cpp performance patches developed and measured on Tesla P100 (GP100, sm_60). Most are not Pascal-specific.

Serving Qwen3.8-27B-FP8 on a single DGX Spark (GB10): 7.88 to 58.5 tok/s single-stream from decode strategy alone, weights untouched. Specul

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

AI commit messages from your local LLM - Ollama / llama-cpp backed, offline, Conventional Commits, with review + changelog modes.

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

Covert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.

A personal AI agent to help you think, create, and get things done. Powered by open models, on your computer or in the cloud.

Context management proxy for AI coding agents: verbatim archive, on-demand recall, and saved engine state on supported backends.

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable

Community benchmark database for running LLMs on Apple Silicon Macs

Can my GPU run this? Pick a GPU to get 3 fitting AI models, quantization, VRAM, speed ranges, and run commands. 한국어·English.

Lightweight proxy for LLM

Free, open-source AI coding agent for terminal and browser. A Claude Code / Cursor alternative that runs offline with Ollama or with your ow

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。

An assistant that lives next to your cursor on Windows. It sees your screen, talks with you, draws on things, solves the math you write, and

Desktop email client with AI that runs on your computer. Chat with your inbox, draft replies and extract data from Gmail, Outlook and IMAP,

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

Private, local-first AI meeting assistant for transcription, speaker diarization and meeting notes. Open-source, self-hosted alternative to

Crow — a local AI agent, not a chat box: 30 tools, MCP, memory, skills, goals, subagents, vision, and image generation and editing with Qwen

AI coding agent harness for any hardware, local or cloud (OpenAI-compatible engines). Tuned for AMD Strix Halo: Qwen3.8 125B on the iGPU, NP

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

Ollama-compatible LLM server on a tuned llama.cpp fork. Beats vllm by 40% on single stream decode, and by 20% on multi stream decode, and be