Hacker News

Show HN: DeepSQL – A self-hostable DBA agent for Postgres and MySQL

32 points by venkat971 ago | 19 comments
Hi HN - I'm Venkat, founder of Stayflexi (YC), CMU CS grad and Ex-Oracle Query Engine team (patents in core databases)

DeepSQL started as an internal tool to stop our own databases from becoming the bottleneck they were becoming (13,000+ hotels in production). It worked well enough that we're releasing it.

DeepSQL is an AI agent that operates a database the way a senior DBA and Data Engineer would

1. Fixes slow queries (we cutdown DB spend by 4x) 2. Fixes DB bloat (blocks unnecessary schema changes, in vibecoded setup) 2. BI dashboards(we removed spend on tableau, retool and appsmith) 3. Security (We could redact access to sensitive, PII data to our employees) while engaging everyone in the org to interact with our database

How it works 1. Deepsql learns your data and relationships from your code base, rules and query logs 2. Deepsql agent has 20 background jobs that continuously monitor the schema changes, bottlenecks, and come up with solutions before the problem arises. (Schema bloat issues are irreversible) 3. Deepsql Brain has CLI and MCP surfaces that can directly work with Claude / Codex and Cursor. 4. Deepsql digest delivers the daily database health report. 5. Your team can connect to deepsql with their favourate surface areas - Web UI, CLI, MCP or Slack.

One line install: curl -fsSL https://install.deepsql.ai/install.sh | bash

For community support: https://discord.gg/duEJq7AeeG

Or just email me for expert level setup guidance venkat@deepsql.ai

quard8 |next [-]

inside install.sh file i found this:

printf " ${DIM}This install is using DeepSQL's shared managed Azure OpenAI key, so your${RESET}\n" printf " ${DIM}schema and queries are processed through DeepSQL's shared LLM resource.${RESET}\n"

also, it requires docker.

venkat971 |root |parent [-]

Hi, yes. Right now we are bundling our key to maintain the consistency of DeepSQL agent performance. We will lift this key bundling very soon, for enterprise deployment we might allow BYOK (bring your own key)

Yes, this requires docker. Here is more technical documentation on prerequisites and suggested setup (including AWS CFT)

https://docs.deepsql.ai/quickstart/

docheinestages |next |previous [-]

The landing page doesn't show a link to your GitHub. Despite mentioning "self-hostable", I genuinely thought it was closed-sourced. I doubt first-time users will trust a random tool and grant it database-level access with a curl command.

venkat971 |root |parent [-]

Great point and thanks for the feedback. We made it self-hostable so that data doesn't leave the premises. We haven't open sourced the code yet, but most likely we will head in that direction very soon.

venkat971 |next |previous [-]

Deepsql doesn't replace your DBA, it gives your DBA super powers. In my org, when we had to decide on hiring a DBA, we chose building deepsql and empowered our senior engineer to handle the database tasks like a senior DBA.

For deployment help, pl email me at venkat@deepsql.ai

sehw |root |parent [-]

[dead]

vector_spaces |next |previous [-]

> 2. BI dashboards(we removed spend on tableau, retool and appsmith)

Can you explain this in more detail? You saying that DeepSQL can create BI dashboards that makes Tableau and friends redundant -- are you talking about analytics dashboards consumed by business teams or more like db ops dashboards used by backend teams? Does the user prompt the agent for them, or does it build dashboards that it infers are needed?

venkat971 |root |parent [-]

Deepsql has built in BI dashboards server - You can ask agent to build any BI dashboard from the connected data sources (this can be used by your internal teams or you can even share the dashboard link with customers with password protection, just like how we would share the retool links).

mdasen |next |previous [-]

Is this an open source tool? Is it something we have to pay for? The site really doesn't tell me what I should be expecting.

venkat971 |root |parent [-]

Sorry for the confusion. It's not opensource. For first few installs, we are offering free 3 months and free consulting service to setup the tool end to end at your org. Post that pricing will be based on AI tokens consumption with some standard monthly pricing (we are also exploring the pricing sweet spot)

I am happy to get connected over email venkat@deepsql.ai and share more details on pricing and deployment help.

|next |previous [-]

evanelias |next |previous [-]

> cut database costs by 40%

Where does this number come from? It feels completely arbitrary.

venkat971 |root |parent [-]

We did cut our overall DB spend by more than 3x. Our $9K spend drops to $3k - indexes not kicking in, rapid growth of log tables and schema bloat were the culprits. Also, we removed the retool and appsmith licenses, another $2k savings.

We worked with 6 YC companies who are running on Aurora postgres and worked through the inefficiencies of workloads - too many indexes (in some cases almost every column is indexed), over indexing significantly increases I/O ops (writes), this hidden costs are enormous for fully managed services like Aurora. In all these cases, we could safely come up with a plan to cut down their DB spend by more than 40%.

evanelias |root |parent [-]

My point is that the number will entirely vary for each user, depending on how many poor DB-related infra decisions they've made. Some users may save 99%, others may save almost nothing, right? So why say 40% here? Where did this number come from?

Personally, I will instantly distrust a new product claiming an exact number of 40% savings -- not even "up to 40%" or "over 40%", which would still be misleading, but less weird than claiming exactly 40%. Especially in the second line of the homepage, without any supporting link or information.

> we removed the retool and appsmith licenses, another $2k savings.

These aren't DB-specific tools though? Why would this count towards the savings?

> 6 YC companies [...] in some cases almost every column is indexed

If your savings math is based on very early-stage startups who made horrendously bad indexing mistakes, honestly that would reduce my trust even further. That said, I'm definitely not the audience for your product.

venkat971 |root |parent [-]

removed that metric.

Our goal was to tell a convincing story with case studies. However, you are right on many dimensions that this number means nothing for many optimized scenarios.

shenli3514 |next |previous [-]

This is an interesting product. Any comparison with other DBA tools? There are many tools can fix the slow queries, based on rule+statistics.

venkat971 |root |parent [-]

Deepsql doesn't require any predefined rules + stats, nor you need a DBA to operate it. It's an autonomous agent, that learns your business context, schema, join relationships and creates a mental map of everything (just like a DBA who joined your team). This we call it deepsql brain init stage. Once the init is done, it will then look at all slow queries workload, comes up with comprehensive suggestions of indexes, MVs etc. Other DBA tools might look at one query at a time, if we try to optimize one query at a time, we might over index.

Also, deepsql is intelligent in understanding the deployment type. Postgres standalone deployment is very different than Aurora postgres. Cost factors are quite different. Other DBA tools might ignore these factors - Hence they need well trained DBA to use them.

shenli3514 |root |parent [-]

I think most of the slow queries can be identified and fixed by simple rules with a proper tool. Like https://docs.percona.com/percona-toolkit/pt-query-digest.htm... . Have you done any benchmark about the accuracy of your tool?

venkat971 |root |parent [-]

We have cross checked with industry standard tools like pganalyze. Most them analyze the workloads in isolation. There are no continuous evaluations and context carry forward across the runs.

DeepSQL does continuous evaluation of queries, we maintain performance life cycle of a query by customer.

A dashboard query for customer A might run for 2s, but for customer B it would take 50s. Here data clustering is the problem, skewness of distinct join keys … various factors. If query fix has to happen by looking at that query alone, one would make wrong decision (probably creating index). But a holistic decision would be partitioning here.

that_dba_guy |previous [-]

So, does it help with context management or so called MemoryBank setup?

venkat971 |root |parent [-]

Yes, it has built in storage layer(Postgres and PGVector)