Kilo Code for JetBrains - Fully native, open-source coding agent built for JetBrains
by•
Kilo Code for JetBrains is a fully native, open-source coding agent for IntelliJ IDEA, WebStorm, PyCharm, GoLand, Rider, PhpStorm, CLion, RubyMine — any JetBrains IDE. Designed for both local and remote dev, with parallel agents in isolated worktrees, GitHub PRs and diffs inline, and 500+ models.
Replies
Mastra
@Kilo Code is so back on @Product Hunt.
Four months ago, the team launched a new @VS Code extension. #1 Product of the Month, the community loved it.
Today, we’re shipping a native plugin for @JetBrains. Rebuilt from the ground up in Kotlin with Swift UI, designed for both local and remote dev, the plugin brings first-class AI coding assistance to IntelliJ IDEA, WebStorm, PyCharm, and other JetBrains IDEs: parallel agents, GitHub PRs and diffs inline, 500+ models...
View source code on GitHub: github.com/kilo-org/kilocode
Looking forward to seeing what you're building with @Kilo Code.
I like the idea of seeing PRs and diffs right inside the IDE. It should make checking AI changes much less annoying.
Kilo Code
@landon_matthew It's really helpful to see what changed, especially if you're using agent manager to change things on separate worktrees.
Mastra
yes, and to learn more about the agent manager, see docs: kilo.ai/docs/automate/agent-manager
Buffup.AI
For me, the BYOK option is a valuable feature that giving developers greater control over their preferred models and API providers.
Mastra
spot on - some tools want to lock you into one editor, one workflow, one way of doing things. @Kilo Code is different. the mission is to build an all-in-one, agentic AI platform that supports you wherever you are.
Buffup.AI
@fmerian Exactly. I think BYOK makes a big difference when you already have a preferred model or API provider and do not want to be tied to one option.
Metabase
Open source + BYOK = freedom to build your way
Kilo Code
@ramiro__nd Amen to that!
Mastra
@ramiro__nd oss ftw!!1
Wao! you build an amazing platfoam, as i have used AI coding assistants before but the ability to work directly within a jetbrains IDE is a significant advantage.
Kilo Code
Mastra
@ashley_james thank you! make sure to add your review here: producthunt.com/products/kilocode/reviews
@fmerian sure why not
How well does it handle agents needing different models for different tasks? For example, one model for planning and another for implementation could be useful.
Are most of your users relying on local models or cloud-based setups?
Promomix
surprisingly good! i also like that it supports local models through Ollama and LM Studio. not everyone wants to rely only on hosted AI.
Mastra
exactly - @Kilo Code is building an all-in-one, agentic AI platform that supports you wherever you are. you should get to choose how you work: your GUI, your model, your workflow.
enjoy! kilo.ai/install
Promomix
@fmerian Yeah, having local model support is useful, especially for people who want more control over their setup. Ollama and LM Studio make that option much easier to use.
How do you keep the agent aligned with the overall architecture instead of just solving individual tasks?
Congrats @jobrietbergen & team!
Thanks @fmerian for hunting another germ.
Mastra
@hamza_afzal_butt thank you for your continuous support, you're the legend
Native is the key word here. I've tried extensions that just wrap a web view inside JetBrains and they always feel bolted on.
Kilo Code
@puja_sharma13 yes, this current native UX is smooth and it's not limited by the space of a tool window
Mastra
@puja_sharma13 thanks for the support! anything @Kilo Code should build/improve/fix from your pov?