
Founder @Hydra_DB | graphs x agents
San Francisco
Joined August 2020
- Tweets2.7K
- Following2.1K
- Followers9.1K
- Likes4.4K
Pinned Tweet
Introducing HydraDB.
The graph native context infrastructure for agents. Purpose built to deliver precise context & observability into why agents act the way they do.
We've always believed graphs are the best way to manage AI context, but they've been too expensive to scale or impractical for storing full context. Until now.
@hydra_db combines in memory, NVMe, and object storage into a single graph layer, making context delivery faster, cheaper, and more precise.
We want context delivery to be extremely fast, 1000x cheap, and highly precise. Give your agents a brain.
Nishkarsh retweeted
Most databases store data in tables. But what if your data is all about connections?
That's where @hydra_db gets interesting.
HydraDB is a distributed graph database built to handle large networks of connected data.
Think of users, wallets, transactions, or social networks. Instead of repeatedly joining tables to find relationships, a graph database represents them as nodes and edges.
The interesting part is how HydraDB handles scale.
It uses object storage like S3 for durable data, separates storage from compute, and distributes work across machines.
This means the system can scale without every machine needing to hold the entire graph.
The goal is simple: make querying massive connected datasets faster, more scalable, and cheaper.
There's a lot of interesting distributed-systems engineering happening underneath.
Netflix built a knowledge graph so engineers and agents can see what depends on what.
Their take: observability is "a data modelling problem."
Agent context is too. HydraDB builds that graph from your docs, Slack and tickets as you ingest.
What would you model first?
So glad to have met @zkevinbai & @mathemagic1an! GOATED engineers solving goated problems
Replying to @contextkingceo
@contextkingceo is one of the clearest thinkers I've met on context for agents. We went past how to engineer context and into how to engineer the platform that makes context engineering possible!! Shoutout @mathemagic1an for the connect!
Next week, we are hosting a coworking night with our friends at @vorfluxai and @Tiny_Fish
Bring your laptop and what you're building: a side project, a startup, or an agent that's only half done.
See what others are building, and meet the teams behind the tools.
Space is limited so register below!
@contextkingceo @lilyyang169
We're running our Database discussion session tomorrow. 4:00 PM IST (10:30 AM UTC), on Discord.
This week: Consensus - Paxos & Raft.
How distributed systems agree on one truth when nodes crash and messages drop.
Come hang, bring questions. Link in the reply.
New community session today: Index 0.
7:00 PM IST (1:30 PM UTC) on Discord.
Chill intro hang, zero-indexed. Come say hi, meet the folks, see what we're building and where it's headed. No prep, no prior context needed.
Everyone's welcome. Link in the reply.
We're running our Database discussion session today. 4:00 PM IST (10:30 AM UTC), on Discord.
This week is a refresher on the fundamentals: replication, partitioning, transactions, consistency, and consensus.
Come hang, bring questions. Link in the reply.
make soemthing more powerful than meta glasses and show the world how hardware is done
excited to share that @kyra_interface is now backed by @AforeVC
we’re building smart glasses to proactively handle your work and communications.
thanks to @nathanqyu @gjain @anamitra for believing in the team and vision.
🔥@buzzy_bit and @jaywyawhare are MASTERMINDS
Your AI is a genius with amnesia.
It finds anything. It remembers nothing. Not your work, not your people, not what changed last week.
HydraDB is the context layer it's missing. A knowledge graph of everything your company knows. Time-aware, always in sync.
Vector databases store. HydraDB remembers!
Your AI is a genius with amnesia.
It finds anything. It remembers nothing. Not your work, not your people, not what changed last week.
HydraDB is the context layer it's missing. A knowledge graph of everything your company knows. Time-aware, always in sync.
Vector databases store. HydraDB remembers!
Nishkarsh retweeted
today we launch @morphic_io: the sovereign AI platform around one core principle.
human knowledge is our most precious asset and needs to compound for the people contributing it.
we unlock our potential only when experience does not walk out the door every time someone leaves
thanks a LOT @simranrambles for helping out. i would fight a horse for you.
i'm back buttercups. this lowkey felt like a hostage situation lmao
thanks a LOT @michaelo for helping out. i would fight a horse for you
I remember when I Snehil and I met for the first met and he told me about how they literally meet their customers and potential users every single day. Easy to say success was an eventuality for them
Update: Overlayy is now a part of Monaco 🚀
Elated to officially announce that @MonacoGTM has acquired @OverlayyAI, and our entire team is joining them
In early 2024, @AnmolChaman and I started Overlayy with a belief that AI would fundamentally change how sales teams work. Over the last two years, we rebuilt systems, workflows, and processes from first principles to make sales reps' lives easier
At Monaco, that thesis becomes part of a much bigger vision
Monaco is building the first AI-native revenue platform - replacing the fragmented stack of CRM + point solutions with one system that can understand what is happening across your entire go-to-market motion and actually act on it
Everything we learned building Overlayy now gets to operate at a completely different scale
Huge thanks to @samdblond, @malay_desai, and especially @abishekv for the conversations, conviction, and ambition that brought us together. We couldn't be more excited to build alongside them and the exceptional team at Monaco
Extremely thankful to our team, customers, investors, advisors, and everyone who helped us along the way
Read more at: overlayy.com/acquisition-pr
@msuraj025 @Panthini_7 @thepurpledoe @madmax_anushank @srijanshetty @vaibhavbetter @amitp42 @abhinavjain @AR_Bits @shivadhawan119 @shubg @pratyush_r8 @kshitijjaggi @GauravPiyush2 @ArkidMitra @mukundjha @madhavjha @abhaysinghal @gokulr @thechangj @deepanshu_edu
Nishkarsh retweeted
Learn what ontologies are, how they are created and used across organizations, and why they are becoming a key layer for giving AI agents structured context.
👏👏
You have absolutely no idea what you’re capable of
Just completed my first ever full marathon In Helsinki , it was few years ago I ended up falling In love with this thing called Running & never gave up
I’ll keep going , you question yourself every time you run why I’m doing this because it’s not easy - if it all it’s more riskier & a crazy thing to attempt to
Like Phil knight described
“ Every runner knows this. You run and run, mile after mile, and you never quite know why. You tell yourself that you’re running toward some goal, chasing some rush, but really you run because the alternative, stopping, scares you to death.”
Thanks to lot of folks here on X who’s Running journey have inspired me a lot & pushed me when I didn’t feel like doing it especially @zachpogrob @SahilBloom @HankFrank @_nicolealonso
Not the result I was expecting but absolutely enjoyed the run , cried many times along the way 🥲 & it’s truly an humbling & character building experience
Especially the last 2Km stretch when the entire crowd is cheering for you it’s an experience ill never forget
Nishkarsh retweeted
Started thinking in graphs @hydra_db @contextkingceo





























