I can highly recommend n8n. I prefer it over Make.com, Pipedream, Zapier, etc. for automations and AI agent tasks. Basically, anything you want to automate but don't want to spin up a custom code server each time.
The main reasons I switched to n8n are it's open source, meaning I can run it locally without limits, and it supports code nodes in javascript and python. Make.com used to drive me bonkers when it took 10+ minutes to create all the nodes in the UI to handle loops, errors, etc. when I could normally just write a few lines of code to handle it.
Only downside to n8n vs other platforms is it's polling based vs instant trigger unlike Zapier's and Make.com's connectors. So if you're processing email, Google Sheets data, etc. you'll have more latency with n8n unless you add some custom middleware to handle instant triggers. But polling is actually a benefit in my case since I mostly run n8n locally through docker. Whenever I spin it up, it auto catches up on new data it hasn't yet processed.
n8n's AI nodes are first rate and more intuitive IMO than others. You can easily extend it with custom LangChain nodes as well if you're self hosting.
If you want to play around with n8n locally, this tool makes it easy: https://github.com/LLemonStack/llemonstack/ I created it to make it easier for me to spin up and down project stacks on the same machine.
It's dual licensed in a way, but neither license is open source. The OSI messed up in not coming up with an answer to the SSPL, and now ambitious projects that would have traditionally gone with an open source license like AGPL are now foregoing open source entirely and just slapping a sustainable use license on it.
So yeah, you can use n8n for free, but that doesn't make it open source. It is a source available license.
The main reasons I switched to n8n are it's open source, meaning I can run it locally without limits, and it supports code nodes in javascript and python. Make.com used to drive me bonkers when it took 10+ minutes to create all the nodes in the UI to handle loops, errors, etc. when I could normally just write a few lines of code to handle it.
Only downside to n8n vs other platforms is it's polling based vs instant trigger unlike Zapier's and Make.com's connectors. So if you're processing email, Google Sheets data, etc. you'll have more latency with n8n unless you add some custom middleware to handle instant triggers. But polling is actually a benefit in my case since I mostly run n8n locally through docker. Whenever I spin it up, it auto catches up on new data it hasn't yet processed.
n8n's AI nodes are first rate and more intuitive IMO than others. You can easily extend it with custom LangChain nodes as well if you're self hosting.
If you want to play around with n8n locally, this tool makes it easy: https://github.com/LLemonStack/llemonstack/ I created it to make it easier for me to spin up and down project stacks on the same machine.
Or see n8n's official repo for instructions on running locally: https://github.com/n8n-io/n8n