Havuz

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

One AI workspace for your models, agents, tools and computer.

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

PosterChan AI is a Nostr-powered personal cloud and a self-hosted AI powerhouse, running on one box you own.

Started as a €70 used mini PC running an always-on AI agent (Hermes, n8n, Pi-hole, monitoring, Tailscale, encrypted backups). Now with a sec

Auto-tuning de modelos locais: TPS e contexto sob limite de PPL, com busca finita, protecoes de recursos e evidencias em SQLite.

Local AI workstation: chat by voice or text, transcribe, generate images and video (with sound on Apple Silicon), benchmark and serve open-w

Drop-in ggml backend for Rockchip NPUs: offloads llama.cpp/whisper.cpp prefill to the RK3588 NPU

A beautifully crafted desktop client for running and managing local LLMs via llama.cpp.

Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.

Rivo Agent is a private, local-first mobile AI assistant that runs compact GGUF language models directly on your phone. It lets users downlo

A NPC AI Framework , based on character personalities, can be used for game NPC (extendable for Godot / Unity)

MCP server that delegates Claude Code subagents to local models (LiteLLM/llama.cpp/Ollama), DeepSeek, AWS Bedrock, or any OpenAI/Anthropic-c

Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.

A memory system for AI agents modeled on human memory: episodic, affective, reconstructive.

Local AI video dubbing studio with voice cloning, speech translation, speaker diarization and audio separation. Edit, preview and export dub

Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.

面向内存受限端侧设备的 MoE 大模型推理运行时优化系统

AI-assisted rescue boot USB — a Ventoy multi-boot drive on Ubuntu 24.04 with offline LLM inference (Ollama + llama.cpp), pre-installed agent

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。

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

Turn any document or a whole zip into an interactive knowledge graph, using a self-hosted Qwen3.6-35B-A3B-MTP on a single NVIDIA L4

A local LLM server built for concurrent work. Drop-in replacement for Ollama and/or OpenAI and Ollama APIs on one port. Requests that share

Open-source desktop AI agent: built-in free model, local GGUF models via llama.cpp, dispatch tasks from WeChat/Feishu/DingTalk. Files, brows

AI, fully local on your computer.

CPU-first LLM inference server on llama.cpp. Runs useful models on free-tier ARM boxes; rewriting the input made it ~6x faster and more accu

Fully local voice AI for iOS

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

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

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

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

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

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

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

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.

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.

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

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

One GPU. Full LLM workflow. Real benchmarks. No cloud required.

Reproduce Lium's LocalMaxxing leaderboard runs (7 boards, 20 Verified) on a rented Lium GPU in one script — vLLM/llama.cpp recipes, measured

llama.cpp speculative decoding measured on one RTX 3090, Qwen3.6-35B-A3B UD-Q4_K_XL, commit 3737e4137. Published figures are re-derived from

Native AI assistant for macOS, built with SwiftUI and llama.cpp. Run local LLMs offline, work with PDFs, and create custom AI assistants. Op

Impulse by Velocity: run AI models on your own computer, on Windows and Linux. Load any GGUF model and chat with web search, files, charts a

A TUI around llama.cpp for running, managing, and benchmarking local GGUF models and launching the pi coding agent against your local server

Can't find subtitles? Generate SRT/ASS subtitles from any video with local AI and auto-translate them — no internet, free. macOS & Windows.

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simula