kimchi.dev

@getkimchi

A CLI coding agent, inference layer, and spend console all in one. Powered by open-source models.

United States

kimchi.dev

Joined April 2026

kimchi.dev
@getkimchi
Jun 18
Big news for Kimchi Coding - picked up by @techday_uk today! Our autonomous coding agent now routes most coding work to MiniMax M3, after it hit 59% on SWE-bench Pro and outperformed several frontier models.
kimchi.dev
@getkimchi
Jun 15
We're among the first platforms in the world to offer MiniMax M3 access! We're opening up access to Early Adopters over the coming weeks, so make sure you're on the list and we'll reach out the moment it's ready for you. Join Early Access → kimchi.dev/minimax-m3
kimchi.dev
@getkimchi
Jun 3
🍜 KIMCHI COOKOFF - Build. Ship. Cook. We're officially launching the first ever Kimchi Cookoff 🔥 From now until June 15th, build literally anything using Kimchi and deploy it anywhere publicly accessible. We just want to see what you cook 👀
kimchi.dev
@getkimchi
Jun 3
Paying $20/month for a coding assistant only to get rate-limited after just 3 prompts is a massive flow-state killer. You’re in the middle of a complex refactor, you ask a couple of follow-ups, and boom: “You've reached your usage limit. Try again in 5 hours.”
kimchi.dev
@getkimchi
Jun 3
We built Kimchi to solve this exact gap between models and silicon. By continuously routing developer tasks to highly optimized open-source models and reserving top-tier hardware strictly for milestone evaluation, we help you maximize every compute cycle.
Cast AI
@cast_ai
Jun 3
Even OpenAI’s Sam Altman admits there is a ton of waste in current AI spending. As organizations pour billions into infrastructure, the critical question is how to get these costs under control. Our 2026 State of Kubernetes Optimization Report provides the hard data behind this