G
Show HN
Show HN: Sim – Apache-2.0 n8n alternative
Hey HN, Waleed here. We're building Sim (https://sim.ai/), an open-source visual editor to build agentic workflows. Repo here: https://github.com/simstudioai/sim/. Docs here: https://docs.sim.ai.

You can run Sim locally using Docker, with no execution limits or other restrictions.

We started building Sim almost a year ago after repeatedly troubleshooting why our agents failed in production. Code-first frameworks felt hard to debug because of implicit control flow, and workflow platforms added more overhead than they removed. We wanted granular control and easy observability without piecing everything together ourselves.

We launched Sim [1][2] as a drag-and-drop canvas around 6 months ago. Since then, we've added:

- 138 blocks: Slack, GitHub, Linear, Notion, Supabase, SSH, TTS, SFTP, MongoDB, S3, Pinecone, ...

- Tool calling with granular control: forced, auto

- Agent memory: conversation memory with sliding window support (by last n messages or tokens)

- Trace spans: detailed logging and observability for nested workflows and tool calling

- Native RAG: upload documents, we chunk, embed with pgvector, and expose vector search to agents

- Workflow deployment versioning with rollbacks

- MCP support, Human-in-the-loop block

- Copilot to build workflows using natural language (just shipped a new version that also acts as a superagent and can call into any of your connected services directly, not just build workflows)

Under the hood, the workflow is a DAG with concurrent execution by default. Nodes run as soon as their dependencies (upstream blocks) are satisfied. Loops (for, forEach, while, do-while) and parallel fan-out/join are also first-class primitives.

Agent blocks are pass-through to the provider. You pick your model (OpenAI, Anthropic, Gemini, Ollama, vLLM), and and we pass through prompts, tools, and response format directly to the provider API. We normalize response shapes for block interoperability, but we're not adding layers that obscure what's happening.

We're currently working on our own MCP server and the ability to deploy workflows as MCP servers. Would love to hear your thoughts and where we should take it next :)

[1] https://news.ycombinator.com/item?id=43823096

[2] https://news.ycombinator.com/item?id=44052766

So here is a case that I wanted to implement in n8n a few years ago and it required quite heavy JS blocks:

- I want to check some input - pick one of your 138 blocks

- I want to extract a list of items from that input

- I want to check which items did I encounter before <- that's the key bit

- Do something for the items that have not been encountered before; bonus point for detecting updated and deleted items

It could be a row added to a CSV file, a new file dropped into a Nextcloud folder, a list of issues pulled from a repo, or an RSS feed (Yahoo! Pipes, what a sweet memory).

How good is the support for such a case in Sim? And did it get better in n8n?

I wonder how the free open-source in this stacks up to the free open-source in n8n.
n8n uses a "Sustainable Use License"—source available, but not OSI-approved open source. This means you can only use it for internal business purposes or non-commercial use. Sim is Apache 2.0.
A bit of feedback, the readme gifs are a little too fast, it's hard to tell what exactly is happening.
thanks for the feedback, I was actually thinking this the other day. we'll slow them down.
  • brene
  • ·
  • 3 hours ago
  • ·
  • [ - ]
How does it deal with loops? I’ve often see workflow builders struggle at that?
for loops we use two sentinel nodes with a backwards edge, and before each iteration, we check the condition and update loop variables.

  sentinel -> body -> sentinel (condition with backwards edge to first sentinel)
in the UI, this is just represented as another block, and depending on the varying types of loops you can either define a collection or the number of iterations
and specifically nested loops. if you're spinning up full runtime copies for each loop, you're gonna have a hard time
at the moment, we don't support 'loops in loops' on the client-side, but not for any other reason asides from it becoming confusing for users. since we don't actually make copies for each loop, it wouldn't be a performance issue.
Looks interesting. The 12GB minimum RAM requirements seem quite steep though. Why so much?
its a conservative estimate, but primarily because there's a socket server that runs alongside the main container, so you never have to manually save because changes are debounced, broadcasted to any other users on the canvas, and sent to the socket server which persists it to the DB
What does “n8n” stand for? I’m assuming it’s a shortening of a longer word, like k8s.
i believe it stands for “nodemation”
Correct, check the "Our name" section at: https://n8n.io/press/
naaathaaan
Is that intoned like Ricardo Montalbán's "Khaaaan!" ?
[dead]