Havuz

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

All-in-one local AI hub for Obsidian — LLM chat with vault tools, MCP servers, RAG, workflow automation, encryption, and edit history. Fully

Consent-first email on your existing IMAP mailboxes. Optional AI assistet screener with local or Cloud models. Full local Clients for MacOS,

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

Self-hosted personal AI agent with a WebUI, memory, tools, MCP, sub-agents and automations. Connect local or cloud LLMs.

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

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every g

🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs).

First LLM Studio: local-first LLM workbench for Apple Silicon + MLX. 本地优先 LLM 工作台，覆盖 Agent、对比、微调、评测与运行时遥测。

JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, M

fast rust coding agent, extensible in any language, multimodal inputs, deep provider integrations.

Benchmarking repository-borne prompt injection attacks and lightweight defenses for local coding agents. DL4C @ ICML 2026.

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline

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

A nightly newspaper that writes itself: an agent runs the desks, the figures come from code, and it refuses to publish an edition with marks

CPU-only, pure-Rust implementation of LiquidAI's LFM2.5-8B-A1B LLM

OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisi

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

The local AI app built for the Mac. Run LLMs like Qwen, Gemma and GPT-OSS on Apple Silicon, including models far bigger than your Mac's memo

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

ZeusHammer - AI Super Agent with Local Brain, Voice Interaction & Three-Tier Memory

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

Run Kimi K3 (2.8 T parameters,1.56 TB) on iPhone 16 Pro? Weights stream from your SSD through a memory budget you set. Free, local, on Mac a

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

ChatGPT-style generative UI for Open WebUI: photo galleries, live maps with real routes, multi-day trips, budgets, calculators, live weather

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

discover LLMs punching above their weight

🐱 Pixel art cats on your macOS dock — debate ideas with local AI

Open-source platform for creating, distributing and running sovereign EU-compliant LLMs. Verticalize any model for your domain, language and

An iPad IDE with local LLM inference on an AMD GPU over Thunderbolt: the upstream Linux amdgpu driver embedded as DriverKit, LemonSeed Engin

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

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

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

Turn one machine into a private ChatGPT for a whole room. One command sets up Ollama, Open WebUI, RAG and an OpenAI-compatible API sized to

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

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

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

Local LLM-maintained personal wiki, built on Karpathy's LLM-Wiki pattern. Runs on Ollama + Qwen3 + QMD.

Open source Agentic Development Environment

OpenAI-compatible inference server for Qwen3.8 on one RTX 5090 / RTX PRO 6000: the 27B at ~170 tok/s (peaks ~370), Flash-Next (125B MoE) at

Run and serve local models headlessly

Pools consumer laptops into one local runtime for Meta Llama models. Measures the free VRAM each machine reports, splits the model across CU

Free, open-source AI autocomplete for macOS — on-device ghost-text suggestions in every app. A private, local Cotypist alternative built wit

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

🚀 Multi-agent orchestration for Qwen Code CLI. 24 specialized AI agents and 82+ skills working as a professional dev department. Built for A

This project is for learning: it shows how an agent loop works underneath, in a way more intuitive and visual than reading about it. Behind

Delta-MFP: counterfactual-replay failure diagnosis for local tool-use agents (FAGEN @ ICML 2026)

Give any local LLM a billion-token memory. Open-source, local-first context + memory engine for Ollama and AI agents — runs on your own mach

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