n8n
Widely used tool for building AI automations and agents; free to self-host, cloud from 20 euros a month.
Should you use it?
Pick it if
People who want to connect apps and AI models into automations, and are happy to self-host or pay for the cloud.
Best for: Teams that want to self-host AI workflows and keep them on their servers (Automation and agents Top 20)
Skip it if
You only need a few simple automations inside Google Workspace; Workspace Studio is included there.
You give up: Licence limits commercial use; sends usage data to n8n until you turn it off
The short version
- What this is
- A visual workflow tool that connects hundreds of apps and AI models into automations and agents, self-hosted for free or in n8n's cloud.
- Why it matters
- It is widely used for building AI automations (206.9k GitHub stars), and self-hosting costs nothing but your own server.
- Free to self-host; cloud Starter 20 euros/month billed yearly s1.
- Latest release n8n@2.42.6 on 9 Oct 2026 s4.
- No independent test of automation tools yet, so no score yet.
Good at
Our take
n8n lets you draw a workflow, such as "when an email arrives, ask a model to sort it and post a summary to Slack", and run it on a schedule or trigger s2. It has 206.9k GitHub stars s2, and the Community Edition is free if you run it yourself s1.
Two things to know. It is fair-code, so you may self-host it for your own use but it is not standard open source s2. And a self-hosted copy sends some data to n8n by default unless you change a few settings s3. There is no independent test of automation tools yet, so we haven't scored it.
Not scored yet
This is a First look: the call above comes from the maker's own pages, so there is no score yet. When an independent test of automation or agent-building tools from the last 90 days is published.
AgentsData
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
Alternatives
Better or cheaper for agents, from our scores, then the ones we'd also look at. The same kind of product comes first.
- MakePlatformNot reviewed yet$12 a monthVisual automation builder with a free tier and paid plans from $12/month.
- ActivepiecesPlatformNot reviewed yetAn open-source automation tool you can also self-host.
- Claude Opus 5.5Top scoredText model#1$20 a monthRanked #1 on Arena's Agent board in agents, first in our ranking; $20 a month. Side by side
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 4
- s1n8n pricing
- s2GitHub: n8n-io/n8n
- s3n8n docs: isolate n8n (telemetry settings)
- s4n8n releases on GitHub
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 2 changes
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- First look. No independent test of automation tools, so not rated.
- Audit: replaced unsourced most-popular and most-starred claims with the sourced star count.
Use it well 4 guides on this site
Pages on this site that help with the jobs above.