Show HN: Run LLMs in Docker for any language without prebuilding containers

Hacker News (score: 11)
Found: January 14, 2026
ID: 3047

Description

DevOps
Show HN: Run LLMs in Docker for any language without prebuilding containers I've been looking for a way to run LLMs safely without needing to approve every command. There are plenty of projects out there that run the agent in docker, but they don't always contain the dependencies that I need.

Then it struck me. I already define project dependencies with mise. What if we could build a container on the fly for any project by reading the mise config?

I've been using agent-en-place for a couple of weeks now, and it's working great! I'd love to hear what y'all think

More from Hacker

Poking holes into bytecode with peephole optimisations

Poking holes into bytecode with peephole optimisations

Bare metal programming with RISC-V guide (2023)

Bare metal programming with RISC-V guide (2023)

Fly's Sprites.dev addresses dev environment sandboxes and API sandboxes together

Fly's Sprites.dev addresses dev environment sandboxes and API sandboxes together

Show HN: FP-pack – Functional pipelines in TypeScript without monads

Show HN: FP-pack – Functional pipelines in TypeScript without monads Hi HN,<p>I built fp-pack, a small TypeScript functional utility library focused on pipe-first composition.<p>The goal is to keep pipelines simple and readable, while still supporting early exits and side effects — without introducing monads like Option or Either.<p>Most code uses plain pipe&#x2F;pipeAsync. For the few cases that need early termination, fp-pack provides a SideEffect-based pipeline that short-circuits safely.<p>I also wrote an “AI agent skills” document to help LLMs generate consistent fp-pack-style code.<p>Feedback, criticism, or questions are very welcome.

No other tools from this source yet.