Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL

by calebhwin • 5 months ago

48 33 5 months ago

Hi HN,

Been hacking on a simple way to run agents entirely inside of a Postgres database, "an agent per row".

Things you could build with this: * Your own agent orchestrator * A personal assistant with time travel * (more things I can't think of yet)

Not quite there yet but thought I'd share it in its current state.

tibbar5• 5 months ago

This is mind-bending. I can't imagine that it performs well enough to be particularly fit for production just yet but..... wow.

swyx3• 5 months ago

how exactly is adding a stored procedure as an agent mind bending

tibbar5• 5 months ago

I can only speak for my own mind ;) but the most advanced thing I'd seen prior in this regard was Google Sheets' =AI function, which is pretty convenient (if awkward) when you want to map values to LLM output.

What I specifically found "mind-bending" about this is that I don't have a clear concept of the limits of what an agent can do. In the limit case, it's basically like an independent employee, right?. So the concept of having a dedicated person sitting on each row of my database and transactionally performing any task I can describe is ... well, it IS a bit boggling to me.

Another way to look at it is: this is an extremely powerful construct for managing fleets of agents. I trust Postgres to execute all the stored procedures I ask it to. So with this tool I can easily spin up arbitrarily many agents. And state management is very simple, because they can directly edit their associated row!

IDK, the more I think about it the more fascinated I am. I'm sure there is some open source SAAS or something that has similar semantics and can do all this more efficiently, but now I know that this is a category of thing one could potentially build/use. Pretty nifty!

readme• 5 months ago

i love postgres and pgvector... this is exactly to my tastes

calebhwin3• 5 months ago

Same, it's in a similar vein as pgvector - probably not as performant as turbopuffer or chroma but you get the benefits of being in a really nice ecosystem.

tibbar5• 5 months ago

Is it? pgvector is primarily about indexing, I think? This feels more similar =AI in Google Sheets.

cpursley2• 5 months ago

Yes, and I imagine pgclaw would pair well with pgmq and pg_cron for scheduled work. Postgres really is enough: https://postgresisenough.dev

maxbond3• 5 months ago

Interesting to hear you say that, I was thinking (but hadn't said) that using WalEx to dispatch to some workers where the agent lived would be a better solution. The worker would then update the row (or more likely insert a new one in a different table with more constraints/different columns). I would be curious to hear what advantage you see in a `claw` type/`agent` column? I can't make heads or tails of it but I regard you as knowing a lot more about Postgres than me.

wwweston• 5 months ago

This... does not seem like separation of concerns.

Not to mention that the data layer seems like the one where you want to keep things most deterministic.

noupdates• 5 months ago

To decouple this the person would have to broadcast nearly every event and rebuild the observer layers elsewhere.

thatwasunusual2• 5 months ago

And IMO that's what should be done.

Don't get me wrong, I like the idea and all that, but this is another pgsql "solution" that is tied to the database layer, when it should be in the application layer.

I like to be database agnostic, and while I prefer PostgreSQL on production, I prefer SQLite on the dev layer. You should never have to HAVE TO use a specific database to make your APPLICATION work.

nkmnz2• 5 months ago

You could replicate and separate your llm-postgres from the system-of-record-postgres.

nkmnz2• 5 months ago

If you really want to run an agent on each created row, you could run this in a replica and stream the replies back to your system of record.

danr4• 5 months ago

this is fucking awesome

xnx• 5 months ago

It feels like we're a week away from the Claw hype supplanting AI hype. Companies will start renaming things ClawX to get on the hype bandwagon.

calebhwin3• 5 months ago

It's just an abstraction people are excited about at the moment. Langchain was an exciting abstraction at one point.

My bet is we converge on a super minimal model<>computer architecture.

maxbond3• 5 months ago

I think "claw" isn't appealing enough to be genericized and that "agent" will continue to be the generic term, but we'll see.

maxbond3• 5 months ago

What's the advantage in putting agents in the persistence layer rather than the application layer? This seems to me strictly less flexible, scalable, secure, easy to work with... I am having a hard time imagining why I would want to integrate with APIs or write an agentic harness in the database rather than in application code?

Maybe I'm behind the times but I don't understand.

4ndrewl• 5 months ago

It's similar to when we wrote all our business logic in eg pl/sql, stored procedures etc. Seems attractive at first, but it breaks separation of concerns, becomes difficult to test etc.

thatwasunusual2• 5 months ago

It's similar to when we wrote all our business logic in eg pl/sql [...]

What do you mean with "when"? /s

I dread companies who still have logic in their databases when it's not necessary. <insert sad face>

debugnik• 5 months ago

I don't understand why claw is a data type for columns in these examples, it doesn't seem to store any actual per-row state. Is it not possible to hook extensions onto "with" clauses or something similar?

ef2k• 5 months ago

Nice. These are the kind of boundary pushing projects I like to see. It challenges assumptions of where application logic should live. The implications around cost, latency, and recovery are going to be interesting.

rel_ic• 5 months ago

We need your help! Can you please use your creativity to build resilience to climate change in your community instead of experimenting with more ways to spend computing power?

brunoqc• 5 months ago

The solution is to tax the rich. But we won't.

worldsavior• 5 months ago

Until YOU get rich.

jmaw• 5 months ago

What does it mean to put an agent inside of a PG DB? Is PG doing the actual computing/inference (does it tie to GPU), or is PG just storing the state of the agents neural net (is that a thing, it seems like it would be).

Maybe I'm strictly too stupid to even parse the concept, but I don't understand what I'm looking at one bit.

Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL

Related Stories