800+ AI tools you can run locally

Local AI Tool Overviews

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

73 videos

CrewAI vs OpenAI Agents SDK vs LangGraph in Python

Obsidian Copilot V4: workflows and multi-agent review

Overview

Obsidian Copilot

Langfuse walkthrough: tracing, evals and self-hosting

Langfuse

ECC for Claude Code: setup, hooks and security review

Overview
Review

ECC

RAGAS and RAG evaluation: metrics and workflow

Overview
Tutorial

Ragas

Reef and local AI tools: GitHub project roundup

News
Overview

Reef

Ollama, llama.cpp, LM Studio and vLLM compared

Comparison
Overview

Slotstream: Qwen 3.8 Flash Next on a 48 GB Mac explained

Overview

Slotstream

Context7, GitHub and browser MCP servers compared

LM Studio, Ollama and Docker Model Runner setup

Docker Model Runner
+3 more

NVIDIA Dynamo: Distributed LLM Serving and KV Cache Reuse

Overview

NVIDIA Dynamo

Jan, Vane, OpenCode and FLUX.2: local AI setup guide

FastAPI and LangGraph: production AI agent architecture

Overview
Tutorial

Ollama, Tabby and n8n vs paid AI tools

Ollama, Open WebUI and 8 more tools compared with SaaS

vLLM and LLM-D: GPU serving and Kubernetes setup

Nextcloud Assistant: Office sidebar and spreadsheet fixes

Nextcloud Assistant

Unsloth desktop vs LM Studio: first impressions

Comparison
Overview
Review

Lemonade
+3 more

Frigate 0.18 beta: UI setup, profiles and GenAI chat

Overview
Tutorial

Frigate

Phone Harness and local agents: GitHub project roundup

News
Overview

Phone Harness

Open Notebook, Meetily and 8 more: self-hosted comparisons

Comparison
Overview

Project AIRI, T3 Code and CapRover: developer tool overview

AIRI

Langfuse tutorial: tracing Pi, Hermes and Claude Code

Comparison
Overview
Tutorial

LangChain explained: concepts and when to use an SDK

LangChain