zainhoda

Working on a web framework that provides some guardrails around what a coding agent can and can’t touch without human approval. Makes it easier to have confidence in 5000 line code changes without having to comb through the code.

https://ont-run.com

It would be amazing if the showcase was itself vibe coded. If so, you should showcase it!

Mobile app that lets you continue coding while you’re away from your computer.

The goal is to be a full mobile IDE that lets you use Claude Code, Gemini CLI, and other agentic code editors.

Has mobile-native file browsing and git integration.

https://remote-code.com

Oof… coincidentally my task for today is to implement Sign in with Apple.

If you were starting over what would you do differently?

What's The State Of Elm?

I love Elm but I think it's pretty clear that Evan is effectively declaring it as abandonware because he couldn't figure out a business model to sustain him.

What’s Evan Working On?

Sounds like he's talking to a handful of companies that he knows uses Elm and doing some tinkering without any defined objectives.

I’m waiting for the same signal. There are essentially 2 vastly different states of the world depending on whether GPT-5 is an incremental change vs a step change compared to GPT-4.

Would you be interested in merging with Vanna in some way?

You’re ahead of us in terms of interface but we’re ahead of you in terms of adoption (because of specific choices we’ve made and partnerships we’ve done).

Nice job getting something released! How does this compare to the other similar open source solutions like Vanna AI and DataHerald?

Looks really interesting! I saw something in the code about streaming. Could you explain that a bit more?

I've been looking for something like this! Does it optimize the prompt template for LangChain only or is there a way I can get it to generate a raw system prompt that I can pass to the OpenAI API directly?

I think of all the options for “carrots” and “sticks” that companies are offering for RTO, I like this one the best.

Very cool. Would the license allow for use with Vanna? https://github.com/vanna-ai/vanna

Founder of Vanna AI here -- appreciate the link and I agree, we're solving slightly different problems.

I’m trying to solve for this with my project using RAG and (at least based on what people say in Discord), it’s working really well for them: https://github.com/vanna-ai/vanna

That's a fair concern. In actual usage, however, the vast majority of hallucination (>90%) tends to be:

- phantom tables and columns, in which case the query will fail

- incorrect syntax for date functions (i.e. the wrong flavor of SQL)

And we tend to see less of this type of hallucination when there are lots of example SQL queries that have been "trained" into the RAG system.

Author of the package here. Apologies if this wasn't clear in the documentation, but what you're talking about is absolutely possible. Feel free to join our Discord -- we have other users who have this multi-tenant setup.

Yes, 100%! Can you turn this comment into a blog post so that I can send it to people who make this claim?

One added benefit of RAG is that it's more "pluggable." It's a lot easier to plug into newer LLMs that come out. If and when GPT-5 comes out, it'll be a one character change in your code to start using it and still maintain the same reference corpus.

I've noticed this as well. Do you have any theories as to why that is?

What would be missing from that is the ability to look up what tables are in the database, how they join together, what terminology the business uses, preferences around whether to exclude nulls from certain columns, etc.

This allows you to ask more of a “business question” like “who are the top 10 customers by sales?” and the LLM will be able to construct a query that joins the customers table to an orders table and get the results that you’re looking for.

With a simple NL to SQL, you’d have to say “join the customer table with the sales table, aggregate on the sales column from the orders table and limit the results to 10 rows” or something along those lines.

That's basically what happens but the power is that in Python, you can do this:

sql = vn.generate_sql(question=...)

Which means that now the SQL can be executed and you can get the table, chart, etc in any interface.

Flask: https://github.com/vanna-ai/vanna-flask

Streamlit: https://github.com/vanna-ai/vanna-streamlit

Chainlit: https://github.com/vanna-ai/vanna-chainlit

Slack: https://github.com/vanna-ai/vanna-slack

Super interesting! Why did you decide to shut down?

Author of the package here. Thank you! That's exactly what we've seen. Businesses spent millions of dollars getting all their structured data into a data warehouse and then it just sits there because the people who need the information don't know how to query the database.

100% -- in fact originally the package used to parse out SELECT statements and only execute SELECT statements. After some feedback, we decided that the permissions on the user should handle that level of detail.

Author of the package here. I think that it probably could handle that but may need more example SQL queries.

Author of the package here. Joining 5 tables is not a problem.

The training does not necessarily require you to write the queries by hand. A trick that we've seen people do is to just train with DDL statements and then ask "leading" questions if it can't answer on the first try.

I've been using the package myself for about 6 months and while I haven't forgotten SQL, what I have forgotten are the fully qualified table names and which tables live in which schemas etc since I never have to think about that.

Author of the package here. Yes, this is a very common use case.

This is a good idea. I think what you'd want to do is override the generate_sql function and store the question with the "related" metadata and the generated sql somewhere:

https://github.com/vanna-ai/vanna/blob/main/src/vanna/base/b...

We're going to be adding a generic logging function soon and fairly soon what you're talking about could just be a custom logger.

Author of the package here. It was originally because it's both a name and a finance term because I was originally using this to query a financial database.

https://www.thebalancemoney.com/vanna-explanation-of-the-opt...

Author of the package here. I would be open to alternative suggestions on terminology! The problem is that our typical user has never encountered RAG before.