waleedlatif1

1) functionally, not that I'm aware of. the only thing right now is running from a specific block onwards, something that we are rolling out this week. you'll be able to run the workflow in debug mode and get really granular information about each node, the inputs and outputs, and resume from any point in the workflow with mock data

2) there is, we also have a code node that uses E2B to run code in isolated sandboxes. it supports python and ts/js

3) yes, in the code node you can use frameworks/libs since we do RCE

we built an execution engine ourselves https://github.com/simstudioai/sim/tree/main/apps/sim/execut... and for the infra for background jobs, we use https://trigger.dev/

thank you! hope you enjoy

the prebuilt images are in compose.prod file only, not in compose.local.

since the copilot is a managed service, you’d be setting those azure credentials in your .env and the copilot would call into your azure openai deployment.

afaik, there are actually a ton of unique IoT integrations that node-red has. a majority of their nodes/flows have accompanying physical devices and sensors

coming soon

We actually wrote our own serializer & execution engine and for long-running jobs, we defer to trigger.dev

You actually can, if you self-host there are environment variables to control what models are available to the copilot but it’s tuned to Azure for the time being. We can work on generalizing it further and documenting it better

Everything that’s available today in our repo will be Apache 2.0 forever, so you don’t have to worry about that :)

We keep all workflows running on Sim cloud backwards compatible always. The idea is that you build, deploy, and never have to make modifications again unless you want to.

If we release a breaking change that requires a migration for existing local workflows, we release notice at least a few weeks ahead of time/bake it into the db migrations.

Incase there are significant changes made, everything is versioned so you opt-in to upgrading.

hope you enjoy :)

sounds super cool! let me know how it goes

Copilot and a few modules are sim.ai-only, but self-hosters can access them with an API key. The core—execution engine, all integrations, deployment—is fully Apache 2.0.

We aimed for feature parity with n8n and improved much of the workflow building experience along the way. We also added what we think agentic workflows needed (mentioned above). Would love your feedback.

Node-RED is great for IoT/edge/data flows. Sim is built specifically for AI agents—native LLM support, tool-use control, structured outputs, token-level observability, etc.

1. we wanted to have full control over the agent orchestration and the execution since we didn't like the abstractions that many of the existing frameworks had built, and didn't want to have dependencies in places we didn't need them. so, we built the orchestration and execution engine from scratch, allowing us to do neat things like human in the loop, settings that run the same block 10 times concurrently, etc.

2. this would kind of serve as a drop-in replacement for langgraph. you could build a workflow with an agent and some tools, perhaps some form of memory. then, just deploy that as an API, call it from your frontend, and consume the streamed response on your chat client and without the need to maintain any infra at all.

3. we have a generic code block and an api block used to call APIs for integrations that we may not have, and you can use those to plug (langgraph) agents into the Sim ecosystem.

4. we are adding in the ability to deploy your workflow as an MCP server in the next week, stay tuned :) in the meantime, you can deploy the workflow as an API and have the agent call it as a tool. moreover, you can use the workflow block in sim to call other agents/worklows as well, so its easy to encapsulate a lot of complexity in a `parent` workflow that you call that dynamically routes and uses different tools based on the task at hand

the agents would be great in the instructions where we need to `do something`, but asides from that is sounds like a pure orchestration task.

now, handling an integration to something like google sheets myself for a task this small is a nightmare, not to mention the separate table I'd need to keep to store the access token & refresh token and the permissions I'd need to get from google. on top of that, hosting it somewhere and then monitoring it.

this is actually a perfect use case, mostly deterministic workflows that need LLMs to fill in the gaps or do the knowledge work. As you mentioned, you can either add it as a row in a CSV file (sheets), use the baked-in memory block and treat it as simple storage, store the row in supabase, or use the knowledgebase. Basically, there are a ton of ways that this can be done that don't require you to maintain the memory solution yourself. you can even detect the updated and deleted items by keeping some sort of version-controlled snapshot of each row in the csv and updating it as you go.

I can't tell you whether it got better in n8n, but I can definitively say that this sounds like a great candidate workflow to build in sim :)

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

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.

thanks for the feedback, I was actually thinking this the other day. we'll slow them down.

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.

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

i believe it stands for “nodemation”

imo, model regression might actually stem from more aggressive use of toolformer-style prompting, or even RLHF tuning optimizing for obedience over initiative. i bet if you ran comparable tasks across 3-5, 3-7, and 4-0 with consistent prompts and tool access disabled, the underlying model capabilities might be closer than it seems.

I really hope sonnet 4 is not obsessed with tool calls the way 3-7 is. 3-5 was sort of this magical experience where, for the first time, I felt the sense that models were going to master programming. It’s kind of been downhill from there.

thank you! appreciate the kind words

adding some examples and templates this week, and in our discord we are gonna maintain a showcase where ppl can post the cool workflows they've built.

appreciate it!

1) we are completely open source and you can self-host it if you so please. for the hosted platform, we have a free tier to let you tinker and get some free inference credits, and then we have a pro plan with is $20 worth of inference, team plan with $40. we only charge for inference, not to use the platform

2) we are planning on integrating with MCP servers, although hesitatn because its a newer protocol and may not be here to stay (might be a hot take). in the meantime, we have pre-built integrations for whatsapp & supabase, so you can definitely build this out today