--- title: JetBrains open sources KotlinLLM, a runtime LLM code... description: JetBrains Research has open sourced KotlinLLM, a research IntelliJ IDEA plugin that uses LLMs as a code generator rather than a runtime dependency. The... canonical: https://daily.dev/posts/jetbrains-open-sources-kotlinllm-a-runtime-llm-code-generator-that-saves-output-as-plain-kotlin-76vderime twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: JetBrains open sources KotlinLLM, a runtime LLM code generator that saves output as plain Kotlin | daily.dev og:description: JetBrains Research has open sourced KotlinLLM, a research IntelliJ IDEA plugin that uses LLMs as a code generator rather than a runtime dependency. The... og:url: https://daily.dev/posts/jetbrains-open-sources-kotlinllm-a-runtime-llm-code-generator-that-saves-output-as-plain-kotlin-76vderime og:image: https://api.daily.dev/og/posts/76VDeriMe.png og:image:alt: JetBrains open sources KotlinLLM, a runtime LLM code generator that saves output as plain Kotlin og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # JetBrains open sources KotlinLLM, a runtime LLM code generator that saves output as plain Kotlin **[Trends](https://daily.dev/sources/trends)** · 2 min read · 5 upvotes · 0 comments ## Summary JetBrains Research has open sourced KotlinLLM, a research IntelliJ IDEA plugin that uses LLMs as a code generator rather than a runtime dependency. The concept, called 'Smart macros,' fills in function bodies with LLM-generated Kotlin source the first time a new scenario is encountered, then saves the output as plain `.kt` files. After generation, the code runs as ordinary Kotlin with no further LLM calls, eliminating per-request latency and API costs. Two APIs are included: `asLlm()` for converting unstructured data to typed Kotlin values, and `mockLlm()` for generating stateful interface implementations. Benchmarks on Spring Petclinic Kotlin showed 100% hot-reload success across 24 scenarios with ~1% overhead. The plugin is released under Apache License 2.0 and is explicitly a research prototype, not a production tool. ## Content JetBrains Research just open-sourced KotlinLLM, and the core idea is genuinely different from how most teams are using LLMs in production today. The pitch: instead of calling an LLM on every request (slow, expensive, non-deterministic), or hiding AI usage inside agents nobody can audit, KotlinLLM generates real Kotlin source code the first time it hits a new scenario, saves it as a normal `.kt` file, and reuses it forever after. No model at runtime. No latency hit. Just code you can read, commit, and test. The plugin introduces two APIs. `asLlm()` converts unstructured input into typed Kotlin values. `mockLlm()` generates stateful interface implementations. Both are explicit call sites in your codebase, which means they show up in code review like any other function call. That's the point — JetBrains is betting that visibility is the thing most AI-in-production approaches get wrong. The numbers from their Spring Petclinic Kotlin evaluation are decent: 100% hot-reload success across 24 scenarios, roughly 1% runtime overhead, and ~0.89 recall on a GitHub issue parser. Not production-hardened, but enough to show the concept isn't purely theoretical. The honest framing here matters: JetBrains is calling this a research prototype explicitly, and they're asking for community feedback rather than claiming it's ready to ship. That's a refreshingly low-hype posture for a tool in this space. What's interesting is the problem it's actually solving. The complaint about LLM-backed features in production usually comes down to three things: you can't review what the model decided, you can't test it reliably, and you're paying inference costs on every request. KotlinLLM takes a swing at all three by treating generated code as an artifact rather than a live call. Whether the tradeoff — generated code that might go stale as your app evolves — is worth it depends heavily on your use case. But as a research direction, it's more interesting than another wrapper around the OpenAI API. Available under Apache 2.0 on GitHub. ## Questions this post answers ### What is KotlinLLM and how does it avoid calling an LLM at runtime? KotlinLLM is a JetBrains Research open-source tool that generates real Kotlin source code the first time it encounters a new scenario, saves it as a plain .kt file, and reuses that generated code afterward instead of calling a model on every request. It exposes two APIs: asLlm() for typed conversion of unstructured input, and mockLlm() for generating stateful interface implementations, both explicit and reviewable in code. _Developers weighing whether to bake LLM calls into production code can follow research like KotlinLLM on daily.dev._ ### How well did KotlinLLM perform in JetBrains' Spring Petclinic Kotlin evaluation? KotlinLLM achieved 100% hot-reload success across 24 scenarios, roughly 1% runtime overhead, and about 0.89 recall on a GitHub issue parser task in a Spring Petclinic Kotlin evaluation. JetBrains describes these results as promising but not production-hardened, framing the project explicitly as a research prototype rather than a shipped tool. _Teams evaluating LLM code-generation tradeoffs can track early benchmarks like this via daily.dev._ ## Similar posts on daily.dev - [adam bien's blog](https://daily.dev/posts/adam-bien-s-blog-1kfev7sch) · Jakarta EE · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#devtools](https://daily.dev/tags/devtools), [#kotlin](https://daily.dev/tags/kotlin), [#jetbrains](https://daily.dev/tags/jetbrains) [View this post on daily.dev](https://daily.dev/posts/jetbrains-open-sources-kotlinllm-a-runtime-llm-code-generator-that-saves-output-as-plain-kotlin-76vderime) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"JetBrains open sources KotlinLLM, a runtime LLM code generator that saves output as plain Kotlin","url":"https://daily.dev/posts/jetbrains-open-sources-kotlinllm-a-runtime-llm-code-generator-that-saves-output-as-plain-kotlin-76vderime","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/jetbrains-open-sources-kotlinllm-a-runtime-llm-code-generator-that-saves-output-as-plain-kotlin-76vderime"},"datePublished":"2026-07-30T23:28:57.115Z","dateModified":"2026-09-13T19:19:33.033Z","description":"JetBrains Research has open sourced KotlinLLM, a research IntelliJ IDEA plugin that uses LLMs as a code generator rather than a runtime dependency. The...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f13051ea0df7408e65450d32d6a1e3cc?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f13051ea0df7408e65450d32d6a1e3cc?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Trends","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Trends","logo":"https://media.daily.dev/image/upload/s--ZfSp3asX--/f_auto,q_auto/v1780996004/logos/trends?_a=BAMAMiWQ0","url":"https://daily.dev/sources/trends"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/jetbrains-open-sources-kotlinllm-a-runtime-llm-code-generator-that-saves-output-as-plain-kotlin-76vderime","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":5},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,devtools,kotlin,jetbrains","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Trends","item":"https://daily.dev/sources/trends"},{"@type":"ListItem","position":3,"name":"JetBrains open sources KotlinLLM, a runtime LLM code generator that saves output as plain Kotlin"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/jetbrains-open-sources-kotlinllm-a-runtime-llm-code-generator-that-saves-output-as-plain-kotlin-76vderime#faq","mainEntity":[{"@type":"Question","name":"What is KotlinLLM and how does it avoid calling an LLM at runtime?","acceptedAnswer":{"@type":"Answer","text":"KotlinLLM is a JetBrains Research open-source tool that generates real Kotlin source code the first time it encounters a new scenario, saves it as a plain .kt file, and reuses that generated code afterward instead of calling a model on every request. It exposes two APIs: asLlm() for typed conversion of unstructured input, and mockLlm() for generating stateful interface implementations, both explicit and reviewable in code. Developers weighing whether to bake LLM calls into production code can follow research like KotlinLLM on daily.dev."}},{"@type":"Question","name":"How well did KotlinLLM perform in JetBrains' Spring Petclinic Kotlin evaluation?","acceptedAnswer":{"@type":"Answer","text":"KotlinLLM achieved 100% hot-reload success across 24 scenarios, roughly 1% runtime overhead, and about 0.89 recall on a GitHub issue parser task in a Spring Petclinic Kotlin evaluation. JetBrains describes these results as promising but not production-hardened, framing the project explicitly as a research prototype rather than a shipped tool. Teams evaluating LLM code-generation tradeoffs can track early benchmarks like this via daily.dev."}}]} ```