Havuz

Local-first agent harness (Windows + Ollama) for 2–9B models. Same 2B model: 0.017 → 0.821 across four agent harnesses — 48×. 288-cell bench

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

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

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

Let idle local LLMs sleep and get your Mac's memory back. A native macOS menu bar app to turn Ollama on and off and auto-free idle model RAM

Local-first desktop app for AI agent teams. Runs with Ollama or cloud models. Mac + Windows.

Qwen3.8-Flash-Next 177B MoE (IQ3_S 3.44bpw) on RTX 5090 Laptop 24GB: full-model quality @ 97.7 tok/s · dual-lane 256K full-context unlocked

A free, open-source AI agent that runs entirely on your machine — controls your computer like you would, works across any app, and handles a

Your own digital life form — local AI companion with persistent memory, IDE workspace, MCP support, and 30+ tools. Companion-first alternati

Fully local AI companion with Long-Term Memory RAG, branch-isolated worldlines, Live2D/VRM 3D avatars, and real-time TTS for consumer GPUs (

Local AI chat and personal agents for macOS. Ollama-powered conversations, customizable characters, controllable memory, and a browser-based

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

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

Run and serve local models headlessly

Portable multi-agent AI developer setup for Claude Code + Ollama. Role-based local LLM orchestration via Bash — plan, code, review, commit.

Vyact is an open-source, local-first personal AI workspace for llama.cpp, RAG, AI agents, document intelligence, and Google Workspace.

Model Dispatch and Memory Allocator: an LLM inference engine for the hardware you own. Custom CPU, ROCm, Vulkan, CUDA, Metal and Level Zero

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

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

Local-first, model-agnostic LLM agent-harness research. Restart planned after a hiatus; existing code and historical claims await revalidati

Local OCR, metadata automation and RAG document chat for Paperless-ngx using PaddleOCR and Ollama, designed for CPU-only self-hosted servers

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

Grux AI: open source AI agent for macOS (MIT). One Command Panel for your mail, calendar, meetings, files and a shell it can undo. Runs on a

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

Run Qwen3.8-Flash-Next on ONE RTX 3090 (24 GB) + 64 GB RAM: 128K context, up to 2,100 tok/s prefill, 43–51 tok/s decode. vLLM runtime with h

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。

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

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

Qwen3.8-27B on RTX 5090 Laptop 24GB — TWIN-TURBO NVFP4 (native llama.cpp) vs Coder390 Q3 LynnStyle (.ninfer + NInfer engine in WSL2/Docker):

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

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

Package an app into one self-extracting Linux ELF. CLI on Linux/macOS/Windows; artifact runs on Linux.

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

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

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

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

Evaan — a fully local, offline-capable AI companion chatbot built with Python & Hugging Face Transformers, running on Qwen2.5-0.5B-Instruct

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

Agentic Runtime

Winning Qwen and DeepSeek setups for AMD Strix Halo: pinned Ansible recipes and matched benchmarks on a 128 GiB Ryzen AI Max+ 395 / Radeon 8

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

A full-screen terminal environment for writing fiction with language models.

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;

Ollama Model Test - Figure out the best model for the task

Raise your own dragon: fine-tune a language model on your own documents, from R. Writes the training data, trains on your laptop, RAG built

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

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

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

Local desktop coding assistant you can run with any local model. No API key required. It can read your project, edit files, run commands, ve