Mastodawn

#Linux #Podman #RHEL #SelfHosting #Fediverse #Python

Weekend project that turned into infra I actually run daily: MastoSum.

The stack: RHEL host, 100% rootless Podman. Web on FastAPI, Celery worker/beat/flower, PostgreSQL 16, Valkey. All on userspace networking (pasta), images built & shipped by a self-hosted Forgejo runner. No root daemon, no privileged anything.

What it does: tracks technical hashtags all day and produces one daily briefing, every point linked to the original post + author. It reads only public hashtag timelines, credits every source, and trains on nothing.

And yes, an LLM writes the prose: a local Ministral model from French lab Mistral AI, running on my own hardware. No cloud, nothing leaving the box. Saying that plainly, not burying it. The whole design goal was to point readers *back* at the authors, not replace reading them.

Example output:
https://mastosum.linuxserver.pro/s/OGuLC5whmCS1ET9jAe9leg

Frank Jun 6

@Larvitz
What type of hardware do you use to run the mistral model and what kind of performance do you get?

@fvbever It runs on a old geforce 2080 TI that I used for gaming several years ago. With the small Ministral 14B model, I get aroun 25 tok/s (roughly 20-25 words per second) out of the local LLM. For async data crunching like that, it's totally fine.

Dave Jun 6

@Larvitz Interesting project! Did you publish the source code somewhere?

@itg_dave I plan that. But the current version is not mature enough for anyone to look at 😂

Dave Jun 6

@Larvitz I see 😬 I had some ideas in the same direction but never found the time to actually implement them. Thanks for sharing anyway!

bbₜᵤₓᵢ Jun 6

@Larvitz

Could you also implement this as a bot? So that one can message it, name the hashtags, and receive a daily private message. That might fit better into the Fediverse.

@tux @Larvitz feel free to fork the source code (I’ll release it on codeberg soon) and make a bot out of it. Markdown files via email fits my personal use-case better.