Krish Dasgupta

Forever Learner | Building Reinforcement Learning Systems | Healthcare | Robots and Brains | Graph ML for Health | Privacy and Decentralized AI

[Krish Dasgupta @officialKrishD]

It was fun presenting at NODES 2025 ! Thanks @neo4j
@JulesHitz

[Krish Dasgupta @officialKrishD]

We believed in the intersection of Graphs and Language models , long before it was cool and graph RAG existed.
We created our own graph embeddings and used them to relate to better decision making process.
Join us on 6th Nov @neo4j and witness our work !
https://t.co/cw7Yzb8bzJ

[Krish Dasgupta @officialKrishD]

@sophiamyang Huge Congratulations!!!!! Sophia ! This is awesome !

[Krish Dasgupta @officialKrishD]

@MicrosoftAI @jm_alexia Open source ? Weights ? HF LINK !!!!!!

[Krish Dasgupta @officialKrishD]

@sundarpichai Start a hackathon :-)

[Krish Dasgupta @officialKrishD]

@GoogleIndia Honestly - just honestly tell me this - what was the count of query seeking Windows OS serial key 2003-2009

[Krish Dasgupta @officialKrishD]

@ariG23498 I have been using a coupled Gitlab self hosted in my local servers setup.

[Krish Dasgupta @officialKrishD]

@kaggle Hackathon soon ? Eh @Kaggle ?

[Krish Dasgupta @officialKrishD]

The scavengers of LinkedIn are at it again.
If you are in cybersecurity domain, you might have heard about the potential and disastrous leakage of answer sheets by one of the most critical examination bodies of India. [ CBSE ]
LinkedIn Scavengers - Talking about the leak without giving credit to the actual folks who found it. That’s why we have limited genuine raw talent. Since many are just trying to copy / paste known big facts without giving the due credit.
Credit Hogging is a skill that should be added on LinkedIn.

[Krish Dasgupta @officialKrishD]

@sampritibh The brilliant Sampriti.

[Krish Dasgupta @officialKrishD]

If your agent can do 1/2 of the jobs that it is doing now, but without internet and low resource compute - you built yourself a moat.
Else it will be still a glorified API call only this time instead of a wrapper - they call your agent a tad an empty suit.
TLDR : works on local models with low compute ? You built it right.

[Krish Dasgupta @officialKrishD]

AI OS.

Natively supports all inference types, memory swapping with base model - that inherently helps with all tools and action.
Completely local running STS pipeline.
Built with base 1B model for instruction following and tooling.
Natively supports robotics .
Fork of Linux .

Soon.

[Krish Dasgupta @officialKrishD]

@FactoryAI @FactoryAI : On local compute and efficient model tracing , want to work on a notch ahead ? Energy based efficient routing. After all, energy consumption is part of THE cost.
Check this out. Let’s chat sometimes soon. But do check LIQUIDATE.

https://t.co/5eATu4gFVP

[Krish Dasgupta @officialKrishD]

LIQUIDATE by @axonvertex_ai
Observability with Energy for Decentralized Compute & Connected GPUs
Better LLM Observability soon !
@natashamalpani @liquidai @ollama

@HazyResearch- THANKS for IPW .Shall reach out post holidays. Aligned research focus. [ IPW ]

😊OSS soon.

[Krish Dasgupta @officialKrishD]

What @FactoryAI built is truly amazing and is equally a true embodiment of people believing in them.
Flashback : year 2025 - prior to presenting at Linux Foundation in August 2025- I showed my work to a “certain well known VC” from India around June 2025.
The feedback was - “who will believe this or invest in this ? You are doing a side project. model routing through intelligence and self hosted compute is a big no. It will not make any difference as enterprise grade projects works on closed source models”.

I was completely disheartened and honestly felt demotivated. I felt it never would make sense. I doubted my intention with this project scope and idea.
Nevertheless , I presented my work at @linuxfoundation AI_Dev Summit 2025.

My lesson learnt : Arrogance and Ignorance has a face too.

Today : I now want to reopen the project and create the intended scale of impact it can have. Give this for free. OSS. As always intended. The 2025 demo and framework not just focused on model route intelligence , but also looked into compute intelligence. Local models do require compute and efficient computing is not a choice but a necessity when you use a private local model router.

[Krish Dasgupta @officialKrishD]

Brilliant work -

That’s amazing.
I had the same work done in August 2025 and presented at the AI_Dev Summit @linuxfoundation in Amsterdam.
Agents of S.E.A.L.E.D - this model routed process encapsulated the way to achieve agentic actions using 7 different models of different sizes and parameters hosted in distributed manner and calls an effective way to handle without letting the user know.
Please Watch this :

https://t.co/P42mfqeDtw

@FactoryAI - you might like this. It is timed - watch for 5 mins and you will see the work 🤗

[Krish Dasgupta @officialKrishD]

@FactoryAI You guys are awesome. Honestly. Sometimes I wish there are folks in my circle who would believe and understand the scale of impact that I try to put in the work.
Long live @FactoryAI for this.

[Krish Dasgupta @officialKrishD]

@FactoryAI @linuxfoundation Thank you for acknowledging the work too 😊

[Krish Dasgupta @officialKrishD]

Brilliant work -

That’s amazing.
I had the same work done in August 2025 and presented at the AI_Dev Summit @linuxfoundation in Amsterdam.
Agents of S.E.A.L.E.D - this model routed process encapsulated the way to achieve agentic actions using 7 different models of different sizes and parameters hosted in distributed manner and calls an effective way to handle without letting the user know.
Please Watch this :

https://t.co/P42mfqeDtw

@FactoryAI - you might like this. It is timed - watch for 5 mins and you will see the work 🤗

[Krish Dasgupta @officialKrishD]

Model routing and Intelligence routing - One thing that I always believed in and also built upon.
Check this out - https://t.co/NPOuYztXJR

Watch this too. Task based model routing. This was built and presented in August 2025 - at the @linuxfoundation AI Dev Summit .
Glad companies like @FactoryAI are shaping on similar lines.
P.S : This work in 2025 also uses the Pareto analysis.

Next big thing is routing not just by task or model - it is energy. And yes , I created another project which basically uses energy as a base for Pareto based routing too.

[Factory @FactoryAI]

Introducing model routing to Factory.

Factory Router picks the right model for every task, automatically.

Maintain frontier performance while cutting costs by 25%.

[Krish Dasgupta @officialKrishD]

@0xSero Agree - check this out.

[Krish Dasgupta @officialKrishD]

Brilliant work -

That’s amazing.
I had the same work done in August 2025 and presented at the AI_Dev Summit @linuxfoundation in Amsterdam.
Agents of S.E.A.L.E.D - this model routed process encapsulated the way to achieve agentic actions using 7 different models of different sizes and parameters hosted in distributed manner and calls an effective way to handle without letting the user know.
Please Watch this :

https://t.co/P42mfqeDtw

@FactoryAI - you might like this. It is timed - watch for 5 mins and you will see the work 🤗

[Krish Dasgupta @officialKrishD]

@tereza_tizkova @FactoryAI Check this @tereza_tizkova 😊

[Krish Dasgupta @officialKrishD]

Brilliant work -

That’s amazing.
I had the same work done in August 2025 and presented at the AI_Dev Summit @linuxfoundation in Amsterdam.
Agents of S.E.A.L.E.D - this model routed process encapsulated the way to achieve agentic actions using 7 different models of different sizes and parameters hosted in distributed manner and calls an effective way to handle without letting the user know.
Please Watch this :

https://t.co/P42mfqeDtw

@FactoryAI - you might like this. It is timed - watch for 5 mins and you will see the work 🤗

[Krish Dasgupta @officialKrishD]

@gregisenberg had I a dollar for every tweet that I have bookmarked and had not visited since, I would be able to sponsor myself a 24 GB VRAM GPU.

[Krish Dasgupta @officialKrishD]

That’s amazing.
I had the same work done in August 2025 and presented at the AI_Dev Summit @linuxfoundation in Amsterdam.
Agents of S.E.A.L.E.D - this model routed process encapsulated the way to achieve agentic actions using 7 different models of different sizes and parameters hosted in distributed manner and calls an effective way to handle without letting the user know. All happens via Pareto based router.

Please Watch this :

https://t.co/wY37kp3KK2

@_AbhaySinghal - please do watch this - it is already timed where you can see the entire demo in action.
Let me know if you want to speak sometimes if this seems interesting ! Great work.