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

vLLM and SGLang: LLM serving and batching explained

Ollama security: model downloads and agent permissions

Nemotron 3.5 Super VL: hardware and reasoning guide

Overview

Nemotron

Luminar preview: export, printing and AI editing tutorial

Luminar Neo

Pi Durable tutorial: local models and crash recovery

LangGraph and MCP: enterprise agent deployment overview

Overview

LangGraph

Nemotron and Pipecat: voice agent fine-tuning explained

Odysseus and llama.cpp: a local agent setup overview

rLLM and Qwen3: training a 4B finance agent versus 235B

Qwen3

BAML and Jev: building coding agent memory pipelines

BAML

OpenClaw, Hermes and more: agent comparison and setup

Codex App Server: custom clients and codex exec comparison

Overview

Codex CLI

Unsloth desktop setup: chat, media and OpenCode

LM Studio and Ollama: setup and model sizing

ComfyUI model tutorial: LoRA, CLIP, VAE and ControlNet

vLLM speculative decoding: Blackwell workload comparison

vLLM

Local AI alternatives: Odysseus, Vane and Upscayl

Langfuse: improving agents with traces and evals

Overview

Langfuse

Paperclip setup for Claude Code and Codex teams

Paperclip

SGLang and vLLM: how inference engines work

Sonible smart:chain: AI mixing setup and workflow

Overview
Tutorial

sonible smart:chain

Temporal, Google ADK and LangGraph: human approval tutorial

Claude Code mods vs n8n: customization and risks

n8n

VoiceStudio, Splash and OpenShell: local AI tools overview