Hacker News: msradam

New comment by msradam in "Fable 5 Is Back"

msradam — Wed, 01 Jul 2026 21:40:07 +0000

I have yet to run into a project where I felt like I needed this and was worth justifying the latent worry about it disappearing or micromanaging quota usage. Heard about massive refactors or ports that were compressed into days but I'm wondering if it's really worth the inference cost.

Show HN: Ocarina – Automate and test MCP servers from YAML, no LLM

msradam — Sat, 27 Jun 2026 15:33:22 +0000

Hi all. As someone who has spent years working with Ansible and other automation frameworks, the recent MCP boom has me fascinated. People are creating nice, typed, LLM-readable (and thus human-readable) interfaces for their servers, over a standardized protocol that exposes both tools and resources. I wanted to see if I could create a way to run scripts against these servers directly, with no AI in the loop.

Ocarina lets you inspect MCP server characteristics and write Rondos (the equivalent of Ansible playbooks) that express tool calls in yaml so you can play them step-by-step without needing to drive with an LLM.

Here's what a Rondo looks like:

  keys:
    owner: acme
    repo: api
  server:
    command: npx
    args: [-y, "@modelcontextprotocol/server-github"]
  rondo:
    - name: recent commits
      tool: list_commits
      args:
        owner: "{{owner}}"
        repo: "{{repo}}"
      grab: ".0.sha"
      echo: latest_sha
    - name: commit detail
      tool: get_commit
      args:
        owner: "{{owner}}"
        repo: "{{repo}}"
        sha: "{{latest_sha}}"
      expect:
        contains: "feat"

I have started using Ocarina myself to test and validate the MCP servers I am creating at my job, and I am interested in the broader field of how we can maximize the use of the massive MCP ecosystem. The README includes links to repos you can clone and try right away (and a little Blender demo ;])

Happy Saturday!

Comments URL: https://news.ycombinator.com/item?id=48699141

Points: 2

# Comments: 1

Show HN: Rocannon – Any Ansible module to MCP Tool, record sessions as playbooks

msradam — Sun, 21 Jun 2026 00:40:38 +0000

I've been using Ansible for IT automation for a while, and the process of writing imperative playbooks in something that looks closer to English I felt was a good fit to design MCP tooling around. I specifically wanted to have a process of running Ansible modules directly as tools from an LLM and record it so my exploratory sessions can become runnable playbooks. The ansible-doc command already emits the schema for each module, so tool calling is nice and structured, and it feels nice to have this available ad-hoc with all the existing Ansible collections that are out there.

Comments URL: https://news.ycombinator.com/item?id=48614526

Points: 3

# Comments: 0

New comment by msradam in "Why isn't the external link symbol in Unicode? (2018)"

msradam — Sun, 14 Jun 2026 19:16:34 +0000

This led me down a bit of a rabbit hole and today I've learned of the ⎘ symbol. I feel like there has been a bit of a terminal / TUI renaissance and I'm now on the huntdown for more aesthetic looking non-emoji Unicode symbols to use in my projects.

New comment by msradam in "Datatype – variable font that turns text into charts"

msradam — Fri, 12 Jun 2026 20:47:57 +0000

This is awesome! I had no idea you could do this sort of thing, thanks for sharing. I've incorporated into my design system because of how well it fits: https://msradam.github.io/lokta/

New comment by msradam in "Running Claude Code Offline on an M3 Pro with Qwen3.6"

msradam — Thu, 11 Jun 2026 17:22:13 +0000

The inertia of switching. At least for me, being able to maintain the same UX and configuration for agentic coding is a benefit. I have access to internal models at work where I use a LiteLLM proxy with Claude Code, so no Anthropic models, but I can maintain the same .claude between personal and work machines. Though I'm definitely open to a non-Anthropic harness if it's a clear win.

New comment by msradam in "The First 100 Wikipedia Pages"

msradam — Thu, 11 Jun 2026 01:02:45 +0000

Very fitting that philosophy is one of the top 5. All roads really do lead back.

New comment by msradam in "Apache Burr: Build reliable AI agents and applications"

msradam — Wed, 10 Jun 2026 22:19:49 +0000

I have enjoyed using this framework in my personal and work projects, having a reliable stateful workflow for AI models while getting free observability. I stitched a tool that allows mounting a Burr state machine as an MCP, giving agents a rail to follow, and no matter how complex the state machine gets the MCP tools are constrained to state machine navigation: https://github.com/msradam/theodosia

I am currently working on skills-to-state-machine conversions, since a lot of popular skills out there are already written as phases for an AI model to follow, so it would be great to leverage the explicit functionality of Burr to make that more reliable. Thank you for this amazing project.

New comment by msradam in "Show HN: Documenting an Obscure Japanese Wii Game – and-Kensaku"

msradam — Sat, 06 Jun 2026 01:47:29 +0000

I love lost art, I feel like this would be really fun to port to DS.

New comment by msradam in "A Brief History of Reviewing Things on the Internet, Vol. I"

msradam — Sat, 06 Jun 2026 01:42:56 +0000

At least BZPower, the Bionicle / Lego review fansite, is still going strong. Same exact site layout too. I really needed their consult before a Toys R Us visit.

New comment by msradam in "Why Do Asian Brands Pretend to Be Japanese?"

msradam — Sat, 06 Jun 2026 01:38:34 +0000

The line "Miniso publicly apologized for pretending to be Japanese" made me giggle. It reminds me of how Häagen-Dazs is not even any particular Danish / Scandinavian word, just completely made up to sound exotic and premium. It worked though, had no clue it was made up til very recently.