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

Odysseus vs Claude: local AI workspace review

Odysseus setup with Ollama, Gemma and hosted APIs

LangWatch Scenario: voice agent testing demo

LangWatch

NVIDIA Cosmos 3 overview and Nano inference demo

NVIDIA Cosmos

Hermes Agent Kanban: multi-agent workflow walkthrough

Hermes Agent

LangChain4j tutorial: Java prompts and document RAG

LangChain4j

NVIDIA Dynamo explained: distributed LLM serving

Overview

PaddleOCR-VL-1.6: document parsing demo and architecture

PaddleOCR

ComfyUI: Rebels Prompt Enhancer and audio nodes tutorial

ComfyUI

NVIDIA Triton: inference serving and deployment overview

Overview

Triton Inference Server

AionUI review: Ollama, Claude Cowork and Open WebUI

Langfuse tutorial: agent traces, datasets and human review

Transformers.js tutorial: ONNX and browser AI pipelines

EXO and GLM 5.1: Mac clusters and Spark inference

AMD local AI setup: LM Studio, ROCm and ComfyUI

Mem0 vs OpenAI memory: pipeline and benchmark review

Mem0

Hermes Agent overview: skills, memory and server setup

Hermes Agent

ON1 Photo RAW 2026.4: Standard vs Max buying guide

ON1 Photo RAW

OpenRig overview: organizing Claude Code and Codex agents

Overview

vLLM, Tunix and MaxText: Google TPU setup and demos

Graphiti and GraphRAG: choosing retrieval for AI agents

ON1 Photo RAW 2026.4: Home and Restore AI tutorial

ON1 Photo RAW

Dyad v1 overview: Neon databases and migration previews

Dyad

Archestra setup: MCP agents, security and cost controls