Agree. Until then I will wait.

Still a welcome move that they finally added support from Python.

I use recall https://github.com/viggy28/recall for the following reasons:

1. It's tightly integrated with Pi 2. Creates context automatically from sessions 3. No external dependencies - sqlite and numpy

Interesting, I love pi too!

An analytics store for Postgres on S3 using DuckDB as the query engine

https://github.com/viggy28/streambed

More like the vulture PE for startups.

It's a solid business model though - get another team to take the risk and develop the app and user base, then when times are tough, buy them out, wring them dry and suck out all the value. In the meantime, don't do any extra feature development on the apps, just run them on maintenance mode with a lean dev team and zero support.

Yes. Buying companies at their actual value and then optimising the and extracting value they can. Considering lot of these startups and how they have acted I don't even consider them anyway evil.

Obviously welcome more tools for Postgres and sharding but it’s a tough hill to climb against the hyper clouds. Best wishes to the team.

The largest database to ever run on Aurora MySQL runs on PlanetScale, and the largest database to ever run on Aurora limitless also runs on PlanetScale.

What do you mean? Your comment reads like PlanetScale uses Aurora under the hood, you mean PlanetScale can handle bigger DB’s than Aurora?

He means that they moved from AWS to Planetscale and yes it handles much larger DBs.

We went as far as we could on GCP before PlanetScale. Spanner is amazing but also amazingly expensive. And CloudSQL, also amazing as long as you don’t need write scaling. PlanetScale (Vitess+MySQL plus their branching / deployment and monitoring tools) is just not a combination offered on GCP. And while I didn’t use Aurora, from talking to and exploring AWS it doesn’t really have this combination either.

It makes me so happy to hear you had a good experience. Thank you for being a customer.

Instead of managing skills as files, I have been using a simple utility which helps me create, update/attach skills and finally search it across sessions https://github.com/viggy28/recall/

I don’t see mention of pi. Does anyone whether it works? I am going to check out.

Yup https://github.com/docker/sbx-kits-contrib/tree/main/pi https://docs.docker.com/ai/sandboxes/customize/kits/

Reads like an add to Omnigent or whatever harness (wait it’s meta harness?.

Is that the core/tech behind Kitesurf?

TL;DR

Initial bet didn’t work out and it also became irrelevant.

Company is focusing on computer for agents. Founder CEO replaced with a new CEO.