HN

Launch HN: Captain (YC W26) – Automated RAG for Files (runcaptain.com)
1d ago by CMLewis 54 points 35 comments
mchusma 1d ago
Having tried this a bit I do really like the single api call for all of it.

I also appreciate transparent pricing but I am not 100% sure the sense of scale of costs. It could be helpful to give some ballparks on things for each of the plans. I'm not sure exactly what i could get out of a plan. My guess, trying hard to figure it out, was if i had about 1,000 pages of new/updated content per month, I would pay $295/month for unlimited queries on top of it. Is that roughly correct?

edgarbabajanyan 1d ago
Yes, we don't charge for queries. For $295, you're able to index up to 1000 pages of new content per month into a fully queryable pipeline.

Advanced and Basic do play a difference though. Advanced is for complex graphics or charts in the documents submitted. Basic is sufficient for most document workloads.

vg_head 1d ago
Good looking! I didn't get to watch the video or look at docs in depth, but do the results trace back to the location of the answers in a document? Let's say it finds an answer in a PDF, and I'd like to know where in that PDF the citation is. Is that possible or intended?
CMLewis 1d ago
Great question, we have deterministic page # citations for PDF results and exact bounding box citations coming very soon.

If you want to check out the Query API response example, here's a link: https://docs.runcaptain.com/api-reference/query/collection-v...

jzig 1d ago
This is an interesting product, thanks for sharing. Can you elaborate on some of your competitors in this landscape and what you might do differently compared to each one?
CMLewis 20h ago
Thanks! The largest alternative to Captain is folks trying to build file search themselves. As mentioned in the post, it is a lot to manage.

The most similar product I've seen is Vertex File Search. They're hosted inside of GCP which can fit nicely into existing cloud deployments. Captain indexes from more sources (like R2 for example) and anecdotally provides faster indexing.

freakynit 14h ago
Hey, congrats on the launch..

How do you compare to kapa.ai ? I have tried them.. and on search quality, they are really impressive.

jzig 19h ago
What about OpenSearch, Onyx, Glean Search, Kore.AI, Sana Labs?
CMLewis 15h ago
OpenSearch provides general search infrastructure and they recently added vector search. It's a low level engine so users would still need to build their own ingestion, parsing, chunking, embeddings, re-ranking, permissions, etc.

Onyx, Sana, and Glean are closer to application-layer enterprise AI products. Their internal knowledge assistants can search across SaaS tools but the interface is more graphical and seats are purchased as end-user software.

Captain sits in between because it's an API-first retrieval system to fully-manage file workloads. This adds search capabilities to existing AI agents but the agents are managed by the developers, outside of Captain.

Kore.ai however is more of an agent platform. Their focus is building and orchestrating agent workflows (which can include document retrieval, but that's not their main focus).

sjkoelle 20h ago
Great name - Captain Hook recently hit public domain - would be a sick logo! (Disney stuff like red jacket still copywrited)
CMLewis 20h ago
No way, that's awesome!
jamiequint 1d ago
This is cool, like qmd as a service with real-time integrations where it matters?

How do you handle more structured data like csv/xlsx/json? Would be cool if it were possible to auto-process links to markdown (e.g. youtube, podcast, arbitrary websites, etc) a la https://github.com/steipete/summarize (which can pull full text in addition to summarizing).

CMLewis 1d ago
Thanks, we're just starting to optimize more for the semi-structured data. So far, we've been parsing tables into Markdown and running them through the contextualized embedding model with no overlap, taking advantage of how it strings together chunks. This isn't great for big files so we're exploring agentic exploration (slow but good for more structured numerical data) and automated graph creation (promising for more relational data).

Love the auto-process markdown idea, we'll add it to our roadmap :D

bfeynman 17h ago
I think I've lost count of how many of these start ups I've seen. But what I really cant fathom is that pricing which is completely out of band. You can already talk to files directly with gemini, just wrapping other apis etc makes no sense. This is even stuff now you can easily codegen entire solutions for esp object storage based ones. Don't see actual any value add or differentiators here. It's obviously not that secure, and ingestion pipeline/connectors are also commodity.
CMLewis 15h ago
You're right that you can chat with files using Gemini or a codegen'd RAG pipeline, and that does work well for a lot of teams.

The problem that Captain really addresses comes when production pipelines need to run continuously over large file corpora with fast, incremental indexing, and reliable latency. The maintenance required in these situations is often quite significant.

Captain focuses specifically on making sure the retrieval layer can operate smoothly so folks don't have to scale & maintain the infrastructure themselves.

edmundsauto 14h ago
For use cases where the increased value ~= 20%, the cost of the distraction with that low of a margin is a hard sell. (Just based on your intro, that was my read)

No disputation of the core idea, I think you are on the right track, but the pitch isn't compelling. People looking for these kinds of AI solutions tend to favor simplicity and ~80% is fine, because the overall perceived productivity improvement is 5-10x, with such wide error bars that the approximate gain is just not worth maximizing for right now.

You might be a few months-years early, or target people who have maxxed out because they cannot retrieve from their second brain effectively. Most folks I've talked to are just trying to keep up, optimization/efficiency is not on their radar.

desmondwillow 17h ago
Congratulations on the launch, Edgar and Lewis! I tried out https://pg.runcaptain.com/ --- 1. I can't seem to select the text during text generation without it being deselected as soon as more text is generated.

2. It seems like it tries to emit citations, but doesn't emit proper links and instead just wrote [filename].

> one of the most common pieces of advice Y Combinator gives to startups [153_do_things_that_dont_scale.pdf].

CMLewis 15h ago
Thanks for trying it out!

Yeah good catch on the demo. If this were a production deployment, the citations would be hyperlinked to object storage. Captain is just the index, so the real files would be wherever they were indexed from.

Perenti 19h ago
Just a note on the website, I thought at first my browser had been hijacked by a shipping or travel agent. The first impression is how AI has improved ship tracking, so you can now track ships with 98% accuracy, with little to no hint this is AI infrastructure until you scroll down.

If you know what Captain is, this is not an issue. I closed the browser tab at first, thinking "what the hell is this, I don't give a damn about shipping forecasts"

CMLewis 15h ago
I see what you're saying, we may tweak the hero to make it a bit clearer. Thanks for the note!
Perenti 14h ago
You're welcome. By the way, as an AIdiot, anything that makes RAG less brittle is good.
alexhans 22h ago
Congrats on the launch. Very quick feedback on the site, since I usually try to check out the blog section, https://www.runcaptain.com/blog layout is broken in mobile, I tried brave/chrome/Firefox.
CMLewis 17h ago
Thanks, just shipped a fix ;)
macieman 19h ago
Its a nice thought & the outcome as a product. Why would an organization pay for such product, as they can very well build a RAG these days tuning to their business needs. I see that Captain API does everything in one shot without rebuilding the RAG, but why would an organization to pay for this solution as this entire chain of activity can be automated and run at non business hours as a batch with the fraction of a cost. What's the delta efficiency that captain would bring it to the table , have you done any benchmarks, if its negligible, i see no reason for any organization to use the captain
cleansy 1d ago
Just some unfiltered feedback after checking out the website: from what I understand this is an SaaS only? So basically I’m asked to upload ALL company docs to a company that existed for basically a minute with some questionable SOC2 report. Soc2 is basically dead as a security artefact and the data asked to upload is sensitive by nature. I don’t see that working.
piker 1d ago
> Soc2 is basically dead as a security artefact

can you expand on that?

bfeynman 17h ago
not to mention they are using 3p apis for everything.. gemini, reranking etc...
jzig 1d ago
> spotty RAG

:O

BoorishBears 1d ago
Are you writing the integrations listed there, or is are you using something that manages the data connections?
edgarbabajanyan 1d ago
We've built these integrations ourselves.

For larger enterprises that require governance and additional compliance, we've been relying on trusted partners to help establish a connection to Captain

saberience 20h ago
The problem with these kind of tools now is that Codex is so good you can basically build something which is good for 99% of cases in a single day, and it's free...

Look at Tobi vibe-coding QMD, he's not a full-time engineer and vibed that up and now it's used as the defacto RAG engine for OpenClaw.

CMLewis 20h ago
Yeah QMD is quite impressive! The main difference between us and them is the scale folks would be looking at indexing. The serverless ingestion engine I described in the post is optimized for processing large batch jobs with high concurrency. We depend on a lot of cloud compute for this which isn't something QMD's local-first environment is optimized for. That said, it's a great option for OpenClaw!
eckesicle 20h ago
Funny you say that.

I spent the last two days building this exact thing for our internal use.

Managed to get a full RAG pipeline integrated and running with all of our company documents in less than two days work.

Chunking, embedding and querying, connected to S3 and Google Drive, and running on our own hardware (and scaling on AWS too if needed).

maxperience 1d ago
Interesting to see still solutions being developed for RAG. We developed a solution similar to yours: Automatic indexing from GDrive, SharePoint etc. and then advanced hierarchical chunking, context header based markdown conversion etc... All the tricks that were published last year while RAG was still the "new" kid in town. We finally open sourced everything as the competition from the big players (Notion AI, Google etc.) was daunting. If anyone is interested, this blog post about all the techniques we tried and what actually works is still relevant and up2date: https://bytevagabond.com/post/how-to-build-enterprise-ai-rag...
macmac_mac 23h ago
Thank you so much for this, started reading it a few min ago and already learnt quite a lot!

I like how clean and compressed the info is

BrianFHearn 1d ago
[flagged]