Nishkarsh

We've raised $6.5M to kill vector databases. Every system today retrieves context the same way: vector search that stores everything as flat embeddings and returns whatever "feels" closest. Similar, sure. Relevant? Almost never. Embeddings can’t tell a Q3 renewal clause from a Q1 termination notice if the language is close enough. A friend of mine asked his AI about a contract last week, and it returned a detailed, perfectly crafted answer pulled from a completely different client’s file. Once you’re dealing with 10M+ documents, these mix-ups happen all the time. VectorDB accuracy goes to shit. We built @hydra_db for exactly this. HydraDB builds an ontology-first context graph over your data, maps relationships between entities, understands the 'why' behind documents, and tracks how information evolves over time. So when you ask about 'Apple,' it knows you mean the company you're serving as a customer. Not the fruit. Even when a vector DB's similarity score says 0.94. More below ⬇️

Your AI agent is only as good as the tools it can actually reach. "If you're building a deep research agent that needs to pull from Notion, we want to make sure all your integrations are sorted first. We loop in the Composio team directly. Shared channels between the customer, us, and Composio." @contextkingceo (founder of @hydra_db) on why the integration layer has to come before the retrieval layer and why @Composio is the first call they make. Full conversation below + on YT and Spotify!

@juliafedorin Best interviewer I’ve come across!

Vector databases are a scam. Not technically, they do exactly what they say. Return the most cosine-similar string to your query. The scam is the entire industry pretending that's the same thing as relevance. It isn't. Search "Apple." You get the fruit, the company, the watch, and a recipe blog. Your agent picks one at random and calls it retrieval. Your customer calls it broken. Most AI agents shipping right now are duct-taped on top of this. They demo well because demos are easy. They die in production because production is real. @Hydra_db's Founder Nish (@contextkingceo) said the quiet part out loud — "vector databases suck, similarity is not relevance" — and the demo signups haven't stopped since. He raised $6.5M because he was the first to name what everyone in the room already knew. If your retrieval layer is a flat embedding index, you're not building infrastructure. You're building a liability with a prettier name. 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) AI Needs Context (01:30) HydraDB Explained (07:41) Vector Search Breaks (09:32) Messaging That Converts (13:41) Writing the Viral Tweet (16:07) Similarity Not Relevance (20:46) POC to Production Gap (35:35) Raising 6.5 Million Fast (39:33) Founder Lesson on Messaging This is a @Composio "Agents at Work" podcast, where I chat with founders building the next leap of AI. Follow for more:)

@iHarnoorSingh @lilyyang169 LOL

@lilyyang169 @contextkingceo yes cuz he always has the right context of everything

something is cooking when scammers keep spinning up new numbers to impersonate @contextkingceo and DM me on repeat. who's spending this much effort and why?

Insanely great guide!

Founder Angel fit @contextkingceo @kamath_sutra

@iHarnoorSingh @mytechceo @iHarnoorSingh 🔥

this is why @mytechceo hires just Forward Deployed Engineer!! Palantir coined the term FDE to give customer, engineering, end to end ownership of the product now, this is industry standard haha!!

@kirat_tw @100xSchool @tereza_tizkova @utpalnadiger @Aiswarya_Sankar @nischal @shirsenh @ShubhamKukretii Wtf is that photo

Releasing an SF pod series on the @100xSchool channel. Featuring @tereza_tizkova @utpalnadiger @contextkingceo @Aiswarya_Sankar @nischal @shirsenh @ShubhamKukretii

If you want to fix your agent context. Try @hydra_db

@interface4AGI for AGI is practically one of the only founders for whom I can say that they have the capacity to pull off something so cutting edge that it will genuinely surprise all of us

Welcoming the VP of SoftBank Vision Fund and Arm! He came through with swag built from his own startup @SpiritStAI We talked about the moats he actually looks for in AI startups, hacker houses or waiting in boardrooms! Thanks @byte721 for the incredible insights and for pulling up to @hydra_db.

@JayanthSanku01 Hi chief, we’re expanding across multiple roles - can’t seem to DM you. Open to chatting?

KV Cache Explained

@ragsgups Amazing!

Grateful to everyone who showed up and made it special. And we’ll have a lot more of these so you all can experience Posha!

@interface4AGI @agi_interfaces Locked in

interfacin’ for the past month @agi_interfaces dropping tmrw!

@RounakLenka @Devanshpawan1 @StalwartCoder amazing

POV: you start talking to your computer and it actually does what you mean.

inside Smallest AI office, @kamath_sutra on what's the missing piece for voice agents!! why Lightning TTS, ultra-low latency voice models needs @hydra_db the knowledge and context layer for AI Agents!!

the hackathon SF deserves! / build matcha / build code best matcha wins best code wins upto $1000 to be won lots of fun creating matcha art!!

@danwintermeyer @getclera Congratulations on the launch!

We raised $3M pre-seed and moved to SF. AI is coming for your job. Maybe in 5 years. Maybe in 15. Nobody knows. But we know this: no great career move ever came from a job board. They came from someone saying “you two should meet.” That’s what @getclera does.

@iHarnoorSingh can i also join?

build matcha or build code? why not both.? this Saturday!!