mogili

These are essentially zero-shot classifiers; they don't need to be trained for a specific classification task. You could include some natural language context on the rules for classification and it should get good enough accuracy.

I've found Gemini to be better at writing. Claude has gotten worse while it gets better at coding / agentic use cases.

Wasn't just a review, it failed the task I gave and Opus completed the task

It's not a good model tbh, got a bunch of things wrong that Opus corrected in my codebase.

It uses the word load bearing a bit so I'm guessing either Anthropic or Claude distilled model.

3d printing is great for low volume parts that have challenging geometries. The aerospace industry has been talking about 3d printed parts for a long time now.

They do have an ambient mode you can enable.

It means it'll use tool calls to search slack and get context not that it's some sort of ambient always running loop.

Token consumption on this is not a huge issue, I built this a few months ago for our company slack using claude agent sdk and most of the conversations/sessions were short lived. You don't generally tend to have long sessions with agents in Slack like you would if using in the terminal.

It was very useful to delegate things like create a ticket based on a discussion to Claude.

This is a solved problem, there are many that do this. Can't believe YC would fund this in 2026.

Not sure what problem it solves on top of Claude Code. I tried it a while back when this was posted but didn't find it very useful. This being a desktop app didn't make sense to me.

Same.

However, I think Cerebras first needs to get the APIs to be more openAI compliant. I tried their existing models with a bunch of coding agents (include Cline which they did a PR for) and they all failed to work either due to a 400 error or tool calls not being formatted correctly. Very disappointed.

I'm waiting on this to be released on Groq or Cerebras for high speed vibe coding.

You need to use better coding agents and workflows.

Long term software engineers very much have a horse in the AI race. It threatens their jobs and importance.

I used Cline and Claude Code extensively for a project. Claude code is much better.

I use with the Max plan ($100 per mo) and its well worth the money and only hit the limit once so far.

There's also flogo https://github.com/TIBCOSoftware/flogo

n8n has even more restrictive license.

I am not saying there isn't value for this, just saying what it does. I might actually use this if they don't tie the fine tuned models to only be used within their platform.

Essentially this is a frontend to automate the process of converting a csv file into jsonl and pass through a fine-tuning service.

I use roo code with Gemini to get similar results for free

This is a good problem to solve for. But making this closed source makes it a bad choice for us to use.

And the other aspect as someone already specified is it seems to only work with single agent workflows.

Yes. I am using a mcp that provides Claude desktop file editing and terminal tools to work like Claude code but using my pro subscription instead of pay per use expensive API

Absolutely! I assumed they had open sourced it and was searching for the Github link :(