Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing
11–20 of 20 posts
how does it compare to sakana?
Re: Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing
#12Re: Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing
#13Foreman is too well known imo
Noted!
Re: Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing
#14I have something simmilar brewed in my multi-agent system, showing and saving cost data on every agent flow run.
That's awesome! I'd love to check it out and give it a try
Re: Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing
#15Nice
Thanks for checking it out!
Re: Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing
#16how does it compare to sakana?
I assume you're referencing Sakana Fugu? Similar in the sense that there's multiple models involved, but from what I understand Fugu is kind of a black box in terms of what model is used for what. This project is more deterministic, you can pick and choose which model to assign/use for certain tasks, plus this project is open source which Fugu isn't.
Re: Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing
#17Re: Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing
#18Interesting project. Most of what I read appears to deal well with a linear agent session.
How does it handle concurrent agent/subagent spawning?
Do they fall under the same sessionId (where they're potentially fighting over the warm route breaking it with every task-type change) or get their own individual sessionIds (where you must rewrite the shared prefix for each agent)?
Re: Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing
#19Re: Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing
#20[flagged]