SnapQL
Data
natural language sql query tool
SHOW HN2025
104points
73comments
#709of 3,837 in 2025
Top 19%of 2025 by points
How HN took it
DebatedReal support and real criticism
11 positive, 15 neutral or asking, 0 mixed, 13 critical, out of 39 comments about the project. Thread score +0.07.
Idea: 8 for, 4 againstExecution: 0 for, 4 againstPrivacy: 0 for, 4 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Useful idea and clean prompting; interest in using it with Postgres
From 3 comments
Looks useful! And the system prompt didn't require too much finessing. I wonder how it would work with some later models than gpt-4o as in my own dabbling around gpt-4o wasn't…
jasonthorsness on HNThis is nice -- we're heavy users of postgresql and haven't found the right tool here yet. I could see this being incredible if it had a set of performance related queries or ran…
gabrielruttner on HNawesome work nick, literally been asking for a vibe coding SQL interface for months
jaimin888patel on HN
Objections
Schema-specific column names make LLM SQL unreliable
From 3 comments
I might test this out, but I worry that it suffers from the same problems that I ran into the last time I played with LLMs writing queries. Specifically not understanding your…
joshstrange on HNI did that the last time (again, only with 3.5, things have hopefully improved in this area). And I could potentially see LLMs being useful to generate the “bones” of a query for…
joshstrange on HNIt’s not a difficult problem to solve, I did it, last year, with 3.5, it didn’t help. That’s not to say that newer models wouldn’t do better, but I have tried this approach. It…
joshstrange on HN
Users cannot verify generated SQL without knowing SQL
From 1 comment
Mostly because you don’t know if it’s correct unless you know SQL. It’s entirely too easy to get results that look correct but aren’t, especially when using windowing functions…
sgarland on HN
Claim of running locally is misleading since it calls OpenAI
From 3 comments
Am I misunderstanding something? How is this "Everything runs locally" if it's talking to OpenAI's APIs?
GarrickDrgn on HNThis app is using OpenAI via the ai package[0][1], so "Everything runs locally" is definitely misleading. [0]:…
whilenot-dev on HNIt is a web app, though. You just aren't running the server, OpenAI is. And you're packaging the front end in electron instead of chrome to make it feel as if it all runs…
kokanee on HN
No license file, so not truly open source
From 2 comments
It is a web app, though. You just aren't running the server, OpenAI is. And you're packaging the front end in electron instead of chrome to make it feel as if it all runs…
kokanee on HNYour project is source-available, not open-source. Consider adding a license.
_9y71 on HN
Requests
Support local or Ollama models
From 3 comments
This is nice -- we're heavy users of postgresql and haven't found the right tool here yet. I could see this being incredible if it had a set of performance related queries or ran…
gabrielruttner on HNAre there plans to support other LLM sources, in particular ollama?
s1mplicissimus on HNWow, this looks really cool. What is the current support for OpenAI proxy or non-GPT models? For example, using locally deployed Qwen models or LLaMA models.
pescn on HN
Add column and enum descriptions to the prompt
From 2 comments
Can you please add support to add descriptions of each column and enumerated types? For example, if a column contains 0 or 1 encoding the absence of presence of something, LLMs…
pu_pu on HNThis is not a difficult problem to solve. We can add the schema, columns and column descriptions in the system prompt. It can significantly improve performance. All it will take…
pu_pu on HN
Graph generation
From 1 comment
I was looking for something like this that supports graphs.
kebsup on HN
Performance queries and EXPLAIN ANALYZE interpretation
From 1 comment
This is nice -- we're heavy users of postgresql and haven't found the right tool here yet. I could see this being incredible if it had a set of performance related queries or ran…
gabrielruttner on HN
Questions
Can it run fully locally with a local LLM?
From 1 comment
This is nice -- we're heavy users of postgresql and haven't found the right tool here yet. I could see this being incredible if it had a set of performance related queries or ran…
gabrielruttner on HN
How does it handle domain-specific schemas?
From 1 comment
Would love to contribute. I have made a fork, will try and raise a PR if contributions are welcome. Question, how are you testing this? Like doing it on dummy data is a bit too…
anshumankmr on HN
Alternatives named
SQLChat
From 1 comment
There are competitors with a GUI too, such as https://www.sqlchat.ai/ and https://www.jetbrains.com/datagrip/features/ai/ I wish you luck in refining your differentiation.
esafak on HN
DataGrip AI
From 1 comment
There are competitors with a GUI too, such as https://www.sqlchat.ai/ and https://www.jetbrains.com/datagrip/features/ai/ I wish you luck in refining your differentiation.
esafak on HN
DBeaver AI assistance
From 1 comment
https://dbeaver.com/docs/dbeaver/AI-Smart-Assistance/
ramoz on HN
Myriade
From 1 comment
Selfless plug, our own tool => https://www.myriade.ai > I wish you luck in refining your differentiation. Can't agree more with you. It's about distribution (which…
BenderV on HN
Postgres MCP servers
From 1 comment
If you can do this, can't you create a read-only user and use it with a database MCP like https://github.com/executeautomation/mcp-database-server ? Am I missing something?
esafak on HN