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

Local AI Tool Comparisons

Compare local and self-hosted AI tools through videos that show how their features, workflows and results differ.

500+ videos

llama.cpp vs vLLM: choosing a local inference engine

Qwen 3.6 and Ollama setup vs Claude Code

Opus 5 vs Fable: coding tradeoffs and T3 Code

Codebase-Memory-MCP vs Graphify, GitNexus and CodeGraph

Codebase Memory MCP

Ollama and OpenCode: Windows VM setup and Qwen comparison

top, htop, btop and nvtop: Linux monitoring compared

nvtop

Nativ vs LM Studio and Ollama on Apple Silicon

Comparison
Review

LibreChat vs Open WebUI: local models or cloud APIs?

Comparison

LibreChat
Open WebUI

Gemma 4 in LM Studio: setup and 12B vs E4B

Crawl4AI, LocalAI and RAGFlow: an AI agent stack overview

LTX 2.3 MSR V2 vs V1: ComfyUI workflow and review

ComfyUI

RVC 2.3.260718: AI covers and live voice setup

RVC WebUI

Headroom review: token savings with Claude Code and Codex

Comparison
Review

Headroom

Mem0 tutorial: local memory with Ollama and Qdrant

llama.cpp: CPU and H100 tests with Kimi, GLM and MiMo

Comparison

Hermes Agent routing: local models and spending limits

Hermes Agent

ha-mcp and OpenCode: Home Assistant setup and comparison

OpenCode

Continue and twinny: Ollama setup in VS Code

llama.cpp, vLLM and ODS: inference stack comparison

Topaz Video: Starlight Precise 2.5 vs Astra 2 settings

Topaz Video

Pi vs OpenCode: setup and extension tutorial

LobeHub overview: Multi-agent workspaces and self-hosting

llama.cpp on a 4 GB PC: Gemma and Qwen performance

Kimi Code CLI vs Claude Code: setup and hosting limits

Kimi Code CLI