What if we replace the engine of BYOTA with your engine? Can we achieve a performance that can be used on even the low-end devices? It already rocks on a Raspberry Pi 5 well as showed in FediForum today.

At NexAI (NexQS) Engine, we're also prioritizing modularity, user agency, and real-time interaction in inference pipelines. Projects like BYOTA point toward a future where personalization doesn't have to come at the cost of transparency or privacy. Excited to see where this movement goes.

Really impressed by how BYOTA approaches decentralized AI customization. Letting users build their own timeline algorithms entirely on-device with full data ownership — using components like Llamafile for local embeddings and Marimo for browser-based UI — is both elegant and empowering.
+++

Davide Eynard is showing how to Build Your Own Timeline Algorithm (BYOTA)

https://github.com/mozilla-ai/byota

This is the last #fediforum speed demo for today. Next: unconference agenda making!

Davide Eynard is showing how to Build Your Own Timeline Algorithm (BYOTA)

github.com/mozilla-a...

This is the last #FediForum speed demo for today. Next: unconference agenda making!

Today I woke up then I used # BYOTA to build an algorithmic timeline on # Bluesky ... A good 8 hours before # FediForum starts 😅 so there's something more I can bring there! Nice facts: - everything runs on a # RaspberryPi 5 - the diff with the http...

| Details | Interest | Feed |

**Build Your Own Timeline Algorithm (byota)**
"Timeline algorithms should be useful for people, not for companies. Their quality should not be evaluated in terms of how much more time people spend on a platform, but rather in terms of how well they serve their users’ purposes. Objectives might […]

The demo is not local (which is what BYOTA is all about!), but I hope the message is still clear: we *can* run useful TL algorithms locally, without sharing our own data. We don’t need a lot of data and compute, if our goal is not to convince people to spend more time on a given platform.

I already talked about why we should own our timeline algorithms (fosstodon.org/@mala/113967...) and promised a blog post soon… Here’s the long awaited post AND a whole new @mozilla.ai Blueprint 🔥

Live demo: mozilla-ai-byota.hf.space

#BYOTA

📱🔒 Build your own timeline algorithm! BYOTA Blueprint creates a local feed for your goals, not engagement metrics. Powered by Mastodon.py, llamafile & marimo. Re-rank fediverse posts locally: github.com/mozilla-ai/b...