Claritty vs n8n
n8n hands you the runtime to operate. Claritty runs it for you, and still runs on your own machine when you want that.
How n8n works
n8n is a source-available, node-based automation tool you host yourself, on your own infrastructure or on their cloud. You assemble nodes on a canvas and drop into code nodes for logic the built-in ones do not cover, and you own the instance: its upgrades, its backups and its credential store.
n8n gives you the runtime and the nodes to operate. Claritty composes the automation from a description and runs it for you, and Claritty Studio covers the local case without asking you to run a server.
Where they differ
What you operate
Nothing. Managed by default. Claritty Studio runs automations on your machine with your own API keys, no account and no telemetry.
The instance itself: hosting, upgrades, backups and the credential store, unless you use their cloud.
How it gets built
You describe the task and it writes the automation. Developers can build the same thing with Claude Code or Codex and ship it through the CLI.
You assemble nodes on a canvas, and drop into code nodes when the built-in ones run out.
Steps that need judgment
An agent reads the content and decides, with the reasoning kept in the run record.
AI and LLM nodes are available and well supported. You design the chain and write the prompts.
Before it does something real
A dry run shows you what it would have sent. Nothing writes, sends or pays until you approve it.
You add your own guard, a filter step, a manual approval step, or a test run before you switch it on.
Credentials
Brokered server-side on the managed platform, so keys never reach the automation code. In Studio they stay on your machine.
Stored in your own instance, which you secure and back up.
Why Claritty instead
Each of these is something the product does today, not a direction of travel.
There is no server in your life
No container to run, no upgrade to schedule, no backup of a credential store to worry about. The automation runs and you did not have to become its operator to get there.
Local is still an option, and it is free
Claritty Studio is a free MIT-licensed desktop app. It runs automations on your own machine with your own API keys, with no account and no telemetry, so wanting things local does not mean taking on hosting.
You describe the task instead of building it
No node graph to assemble and no code node to fall back into for ordinary logic. Developers who want that control still have it, through Claude Code or Codex and the Claritty CLI.
Your keys never reach automation code
Credentials are brokered server-side, so the automation calls a tool and the platform holds the secret. There is no key pasted into a step for someone to read later.
Nothing irreversible happens without you
A dry run shows you what it would have sent before it sends it, and a real action waits for your approval. The failure mode of a bad run is a draft you delete rather than an email your customer reads.
Questions people ask
Is Claritty open source?
Claritty Studio, the desktop app, is MIT-licensed and free, and the app template is public on GitHub. The managed platform itself is not open source.
Can I self-host Claritty?
You can run automations locally with Claritty Studio using your own API keys, and apps built from the template are self-hostable anywhere you can run Docker. The hosted platform is managed rather than something you deploy yourself.
Is Claritty an n8n alternative?
Yes, especially if you chose a self-hosted tool to avoid per-task pricing and have ended up maintaining a server as a side effect. Claritty runs the automation for you, and Claritty Studio covers the case where you want it on your own machine with your own keys.
Describe the job. Watch it run.
Building an automation is free, and it runs on your real data so you can see whether it actually works before you pay for anything.
Start freeOr read how it works first.