Live data from Hacker News

Launch HN: Hyper (YC P26) – Company brain to power agentic development

news.ycombinator.com

71–80 of 88 posts

Re: Launch HN: Hyper (YC P26) – Company brain to power agentic development

#71
Congratulations on the launch! Really intriguing product.

How well would it work for a company that has the kinds of artifacts that you mentioned, but that lacks the quality/precision/accuracy that Hyper might need?

I'm especially thinking about mature companies that don't sell software and that have made a lot of mistakes and memorialized inconsistencies.

Is Hyper just a bad fit for them? Or could there be a path toward refinement and correction that eliminates ambiguities, etc.? For companies like this, Hyper could provide the clarity that such a company lacks day-to-day.

Re: Launch HN: Hyper (YC P26) – Company brain to power agentic development

#72

Hey HN! Kanyes here, one of the cofounders of Hyper. Here all day to answer any questions :)

As a person with a career in heavily regulated space who would very much like to try a product like this so we stop spending time on it in-house:

Hyper doesn't copy your Gmail inbox or Notion workspace onto our servers. We extract the meaningful signal — decisions, insights, key facts and context — and discard the rest.

This sentence does you no good, it just says we exfiltrate what matters.

Your data is hosted on managed AWS infrastructure with AES-256 encryption at rest at the storage layer and TLS in transit.

This sentence is like a code smell right up there with military grade. The first claim applies to effectively every hard drive these days, the second claim applies to every website with http"s". They do not differentiate you, instead they show you don't know what claims matter. These copy-pasta claims work only for buyers who don't actually have any regulations to comply with.

and we're blazing towards making our compliance fit your needs as quickly as possible

Again, this does you no good.

• • •

PS. Did you get rights for Jetsons footage? On the one hand, copyright might not apply as it's a short clip and the form seems unsuitable for uses that would compete with the commercial purpose of the original, but by using it in marketing you could open yourselves up to failure to license and compensate the content owner for the implied endorsement.

Re: Launch HN: Hyper (YC P26) – Company brain to power agentic development

#75
post #71

Congratulations on the launch! Really intriguing product. How well would it work for a company that has the kinds of artifacts that you mentioned, but that lacks the quality/precision/accuracy that Hyper might need? I'm especially thinking about mature companies that don't sell software and that have made a lot of mistakes and memorialized inconsistencies. Is Hyper just a bad fit for them? Or could there be a path to…

appreciate the congrats! This is a good question. The core thesis is that the brain is continually self improving. If your initial information is really bad or messy, then Hyper is going to only be able to start with that. But we provide manual refinement and correction options that will gradually make the brain strictly better. For example, we expose skills like `/correct` via MCP that make explicit, hard corrections against the brain. Over time, the longer Hyper is active, the more refined the knowledge will get. It's a very anti-entropy system :)

Re: Launch HN: Hyper (YC P26) – Company brain to power agentic development

#76

Hey HN! Kanyes here, one of the cofounders of Hyper. Here all day to answer any questions :)

As a person with a career in heavily regulated space who would very much like to try a product like this so we stop spending time on it in-house: Hyper doesn't copy your Gmail inbox or Notion workspace onto our servers. We extract the meaningful signal — decisions, insights, key facts and context — and discard the rest. This sentence does you no good, it just says we exfiltrate what matters . Your data is hosted on m…

Appreciate the feedback. We are not currently a good fit for highly-regulated industries like gov't or medical, though we are working to meet those requirements. We currently run Hyper on our (cloud) infra because it's far and away the lowest-friction option for teams that are comfortable with it. Understand that it's not for everyone, and our security and compliance posturing will mature with time and iteration (we are a very new company!).

Re: Launch HN: Hyper (YC P26) – Company brain to power agentic development

#77

How does this compare to gstack?

Hyper's focus is on the entire end-to-end experience from data coming in to agents performing work. We have made several distinct architectural decisions that we think make a significant difference, though we will be verifying this more officially with benchmarks in the near future. The bigger picture is that we see Hyper as a product that exists beyond the memory framework. Memory is a core technology to get right, but we are handling the full roadmap from data coming into the system to the actual agent orchestration out the other end. Hyper already supports a limited set of agentic operations.

Re: Launch HN: Hyper (YC P26) – Company brain to power agentic development

#78

Curious, does it connect to my claude code, or ChatGPT automatically and constantly inject some kind of context in it. Or do you have to connect to some kind of a MCP.

You are correct. In the onboarding process we install hooks to your machine (and also give an MCP option for unsupported agents that don't have a hook protocol). We do this because MCP is inherently unreliable -- you are at the whim of the calling agent to recognize the connection between the tool call description and the user's query. Hooks let you reliably run side effects as part of the lifecycle. All of this is configurable from our desktop UI.

Re: Launch HN: Hyper (YC P26) – Company brain to power agentic development

#79
post #24

Nice job! But here is my idea: why not build an agentic AI workflow that mimics the streamlined production methods of Ford in the early 20th century? We already have extremely powerful models and APIs, but we still tend to cram everything into one employee's workstation without giving out different tasks to different people.

Interestingly enough, this is how Hyper is structured under the hood. Rather than have one mega-agent whose job it is to go in and try to solve every problem simultaneously, we prefer a "production line" of narrowly scoped agents to make small decisions to keep the knowledge graph up to date. More broadly, agent orchestration is a problem tightly coupled to the "shared brain" problem. Definitely exploring what this m…

Yes! Wow, this definitely caught my attention!
Post reply on HN