← All harnesses

Local AI tool

Ollama

Run open models locally with one command.

The easiest way to run open-weight models on your own computer; most open-source harnesses can use it as their model.

Where it runsLocal or cloud
CostFree

Free and open source for local use; optional cloud models.

Good for: Content, Support triage, Bookkeeping

Visit Ollama · Source: github.com

Works with

Local AI tools

Local AI tool

AnythingLLM

On-device, private AI workspace for your documents.

Local or cloudFree
Local AI tool

Open WebUI

Self-hosted ChatGPT-style interface for local models.

Runs locallyFree

Harnesss

Harness

n8n

Visual workflow automation with native AI agent nodes.

Local or cloudFree tier
Harness

OpenClaw

Open-source personal AI assistant that runs on your own machine.

Runs locallyFree
Harness

Dify

Open-source platform for agentic workflows and RAG apps.

Local or cloudFree tier
Harness

Flowise

Build AI agents visually, open source.

Local or cloudFree tier
Harness

Langflow

Low-code builder for agents and RAG, open source.

Local or cloudFree
Harness

Activepieces

Open-source automation with AI agents and ~400 MCP servers.

Local or cloudFree tier
Harness

CrewAI

Python framework for teams of role-playing AI agents.

Local or cloudFree tier
Harness

LangGraph

Low-level orchestration framework for reliable agents.

Local or cloudFree tier
Harness

goose

Open-source, extensible agent that runs on your machine.

Runs locallyFree