# Proof of concept LLM chatbot built with Julia: KeemenaLM.jl

**URL:** <https://discourse.julialang.org/t/proof-of-concept-llm-chatbot-built-with-julia-keemenalm-jl/137961>\
**Category:** Package Announcements\
**Created:** [July 5, 2026, 8:37pm UTC](https://discourse.julialang.org/t/proof-of-concept-llm-chatbot-built-with-julia-keemenalm-jl/137961 "2026-07-05T20:37:34Z")\
**Posts on this page:** 1\
**Showing post:** 44

<div class="post-metadata">

**Author:** ![Myar\_joyia](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/myar_joyia/32/223456_2.png) [@Myar\_joyia](https://discourse.julialang.org/u/Myar_joyia)\
**Post date:** [August 22, 2026, 5:21pm UTC](https://discourse.julialang.org/t/proof-of-concept-llm-chatbot-built-with-julia-keemenalm-jl/137961/44 "2026-08-22T17:21:58Z")

</div>

I agree that focusing on infrastructure first seems like a very practical direction. Beyond training a larger base model, I think it would be interesting to explore what a Julia-native stack for model development and inference could look like in practice. For example, having Julia-native tooling for efficient inference, context management, recursive workflows, and benchmarking could make it much easier to experiment with these newer architectures. It might also be useful to define a few concrete benchmarks so we can compare different approaches and see where Julia can offer real advantages rather than simply reproducing existing workflows.

---

_[View the full topic](https://discourse.julialang.org/t/proof-of-concept-llm-chatbot-built-with-julia-keemenalm-jl/137961)._