2,000+ AI tools you can run locally Add tool

Local AI Tool Overviews

Explore what local and self-hosted AI tools do, how they work and which tasks they can help with.

500+ videos

GPT Researcher and local AI alternatives: costs and limits

LLM Compressor: quantization and GPU cost reduction

Overview

LLM Compressor

NVIDIA Dynamo and Gcore: distributed inference explained

Overview

Open WebUI + Ollama: self-hosted subscription alternatives

Odysseus, DeerFlow and 8 more tools: paid alternatives

Comparison
Overview

Nemotron 3 Ultra: architecture and training explained

Overview

Nemotron

ppt-master: generate editable PowerPoint presentations

Overview

PPT Master

Open-LLM-VTuber setup and local voice AI overview

MoneyPrinterTurbo: AI video pipeline explained

Overview

Open Notebook vs NotebookLM: Docker and Ollama setup

llama.cpp, Ollama and MLX: local model runners compared

PEFT and LoRA: GPT-2 adapter configuration and checkpoints

Claw-Empire setup with Gemini CLI and agent office tour

AgentScope 2.0 overview: retries, permissions and Docker

AgentScope

PandasAI + Streamlit: local analytics app walkthrough

Overview
Tutorial

PandasAI

Zep and Graphiti: agent memory architecture vs RAG

Graphiti

Kubernetes and Kubeflow: AI platform stack explained

Overview

Lemonade and ROCm integration in Ubuntu 26.04

Mastra walkthrough: TypeScript agents and deployment

Overview

Mastra

Vibe-Trading: research agents and setup overview

Overview

Vibe-Trading

Headroom: context compression for Claude Code and Codex

Overview

Hunyuan3D workflows: image-to-3D and API options in ComfyUI

Hunyuan3D

llama.cpp and DeepSeek V4: quantization explained

Overview

Hermes Agent with OpenShell: skills and sandbox demo

Overview