Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Rowboat – AI coworker that turns your work into a knowledge graph (OSS)

github.com

Post reply on HN
Print view View original

21–30 of 60 posts

Re: Show HN: Rowboat – AI coworker that turns your work into a knowledge graph (OSS)

#21

Post by delichon »

segmenta wrote: post #20
delichon wrote: post #18

How do you handle entity clustering/deduplication?

We use a two-layer approach. The raw sync layer (Gmail, calendar, transcripts, etc.) is idempotent and file-based. Each thread, event, or transcript is stored as its own Markdown file keyed by the source ID, and we track sync state to avoid re-ingesting the same item. That layer is append-only and not deduplicated. Entity consolidation happens in a separate graph-building step. An LLM processes batches of those raw f…

> the model decides whether a mention like “Sarah” maps to an existing “Sarah Chen” node or represents a new entity, and then either updates the existing note or creates a new one.

Thanks! How much context does the model get for the consolidation step? Just the immediate file? Related files? The existing knowledge graph? If the graph, does it need to be multi-pass?

Re: Show HN: Rowboat – AI coworker that turns your work into a knowledge graph (OSS)

#22

Post by segmenta »

delichon wrote: post #21
segmenta wrote: post #20

Earlier quoted context omitted.

We use a two-layer approach. The raw sync layer (Gmail, calendar, transcripts, etc.) is idempotent and file-based. Each thread, event, or transcript is stored as its own Markdown file keyed by the source ID, and we track sync state to avoid re-ingesting the same item. That layer is append-only and not deduplicated. Entity consolidation happens in a separate graph-building step. An LLM processes batches of those raw f…

> the model decides whether a mention like “Sarah” maps to an existing “Sarah Chen” node or represents a new entity, and then either updates the existing note or creates a new one. Thanks! How much context does the model get for the consolidation step? Just the immediate file? Related files? The existing knowledge graph? If the graph, does it need to be multi-pass?

The graph building agent processes the raw files (like emails) in a batch. It gets two things: a lightweight index of the entire knowledge graph, and the raw source files for the current batch being processed.

Before each batch, we rebuild an index of all existing entities (people, orgs, projects, topics) including aliases and key metadata. That index plus the batch’s raw content goes into the prompt. The agent also has tool access to read full notes or search for entity mentions in existing knowledge if it needs more detail than what’s in the index.

It’s effectively multi-pass: we process in batches and rebuild the index between batches, so later batches see entities created earlier. That keeps context manageable while still letting the graph converge over time.

Re: Show HN: Rowboat – AI coworker that turns your work into a knowledge graph (OSS)

#23

Post by asciii »

wyattjoh wrote: post #14

It would be fantastic if this supported email and calendar providers that weren't Google. Supporting protocols like IMAP or JMAP alongside CalDav would be a fantastic step, as well as open source note-taking apps like Hyprnote would be neat.

I second this, as a big Fastmail user

Re: Show HN: Rowboat – AI coworker that turns your work into a knowledge graph (OSS)

#24

Post by einpoklum »

> We’d love to hear your thoughts

Google Mail should not be used, nor its use encouraged. Nor should you encourage the use of LLMs of large corporations which suck in user data for mining, analysis, and surveillance purposes.

I would also be worried about energy use, and would not trust an "agent" to have shell access, that sounds rather unsafe.

Re: Show HN: Rowboat – AI coworker that turns your work into a knowledge graph (OSS)

#25

Post by delichon »

segmenta wrote: post #11
btbuildem wrote: post #9

How do you manage scope creep (ie, context size), and contradictory information in the context?

Good question. We don’t pass the entire graph into the model. The graph acts as an index over structured notes. The assistant retrieves only the relevant notes by following the graph. That keeps context size bounded and avoids dumping raw history into the model. For contradictory or stale information, since these are based on emails and conversations, we use the timestamp of the conversation to determine the latest i…

> That said, handling contradictions more explicitly is something we’re thinking about.

That's a great idea. The inconsistencies in a given graph are just where attention is needed. Like an internal semantic diff. If you aim it at values it becomes a hypocrisy or moral complexity detector.

Re: Show HN: Rowboat – AI coworker that turns your work into a knowledge graph (OSS)

#26

Post by delichon »

Curiositiy wrote: post #19

Fucking hate software dorks turning simple web searches into a polluted, unrelated results list, thanks to their stupid, unimaginative & completely unrelated one-word "product" names.

Dear software dorks turning raw text searches into meaningful, relevant linked data: rock on and thank you for your service.

Re: Show HN: Rowboat – AI coworker that turns your work into a knowledge graph (OSS)

#27

Post by segmenta »

delichon wrote: post #25
segmenta wrote: post #11

Earlier quoted context omitted.

Good question. We don’t pass the entire graph into the model. The graph acts as an index over structured notes. The assistant retrieves only the relevant notes by following the graph. That keeps context size bounded and avoids dumping raw history into the model. For contradictory or stale information, since these are based on emails and conversations, we use the timestamp of the conversation to determine the latest i…

> That said, handling contradictions more explicitly is something we’re thinking about. That's a great idea. The inconsistencies in a given graph are just where attention is needed. Like an internal semantic diff. If you aim it at values it becomes a hypocrisy or moral complexity detector.

Interesting framing! We’ve mostly been thinking of inconsistencies as signals that something was missed by the system, but treating them as attention points makes sense and could actually help build trust.

Re: Show HN: Rowboat – AI coworker that turns your work into a knowledge graph (OSS)

#28

Post by iugtmkbdfil834 »

I think this is a good example of what a good landing page can do.. I can immediately tell what it can do and the visualization makes me want to try it. And I don't think it is particularly refreshing or anything.. it just seems cool.

Re: Show HN: Rowboat – AI coworker that turns your work into a knowledge graph (OSS)

#29

Post by iugtmkbdfil834 »

segmenta wrote: post #27
delichon wrote: post #25

Earlier quoted context omitted.

> That said, handling contradictions more explicitly is something we’re thinking about. That's a great idea. The inconsistencies in a given graph are just where attention is needed. Like an internal semantic diff. If you aim it at values it becomes a hypocrisy or moral complexity detector.

Interesting framing! We’ve mostly been thinking of inconsistencies as signals that something was missed by the system, but treating them as attention points makes sense and could actually help build trust.

This was something that I was working on for a personal solution ( flagging various contradictory threads ). I suspect it is a common use case.
Post reply on HN