Hey HN! I got inspired, locked in, and built this yesterday.

Those are tricky! We've found https://www.datalab.to/ to be good for this @ thesynthesis.company

I used to, that's their whole vibe

Is it tongue in cheek?

I'm not sure what you mean by "same amount of time"

You can check out the full prompt here, maybe this answers your question: https://github.com/zenbase-ai/context42/blob/main/src/lib/ge...

This prompt is used to synthesize subdirectories

Congrats on the launch!

Thank you!

You should check out https://x.com/lateinteraction's DSPy — which is like an optimizer for prompts — https://github.com/stanfordnlp/dspy

This is cool! Learned about JigsawStack.

Curious, can you share your decision making for adding Hasura on top of Supabase? I used Hasura a couple of years ago, recently started using Supabase and it seems to cover my Hasura use case in a simpler way.

Yeah! I'm the founder of JigsawStack, happy to help if you have any feedback or questions.

I've been using Hasura generally with vanilla Postgres DBs and I've mainly used it for three real reason: Client side permission management, DB dashboard and GraphQL.

Supabase has done an amazing job trying cover all those aspects with their own solutions but I still find Hasura really found the sweet spots for those aspects a little better and more fine tuned.

Client side permission: Hasura has an amazing UI to build permissions compared to Supabase sql based row level permissions where I still need to right code and then verify it

DB dashboard: managing the db, adding/removing columns, changing types, creating triggers, index etc, works/feels a lot better to me on hasura or maybe its just something I've gotten use to

GraphQL - I love writing in GraphQL, and Supabase Graphql layer isn't production standard at this stage.

Again, a lot of this is preferences and my personal opinion. You can build amazing products with just Supabase for sure, just a lot faster for me with Hasura right now :)

Super cool! Great work on making it fast and having clear benchmarks.

I had some fun looking through them and seeing how comma-separated-values — a package I authored ~9 years ago and posted to Show HN as well fared.

ha, you win the longest package name!

I was also thinking about how they could've integrated this into every app, but I figured that simple tasks would be more reliable across all apps if they did AI-recognition on screenshots of the desktop + injecting data like "Installed Apps", then by the end of it output virtual keyboard event or a virtual click at an X/Y coordinate.

Just some afternoon postulating haha

I found modelling them as humans made it easier to imagine how to structure them, but there's nothing saying that's it's a better way to model your agent tree. Would be curious for somebody to use this to run some experiments with different names/traits for the fractal agent tree.