Shiva Saini

Building @axoncrew — AI agents that do real work.
Creator of

[Shiva Saini @shivasainix]

Why I Built NanoCrew

Today's AI agents generally fall into one of two categories:

General-purpose agents like Hermes or OpenClaw that can handle a wide variety of tasks.
Specialized agents like coding assistants that are built for one specific domain.

But what if you don't want either?

What if your business has a unique workflow that no existing AI agent is designed to solve?

Today, you have two choices:

Use a general-purpose agent and hope it adapts to your workflow.
Hire a team to build a custom AI agent for your business.

The second option is expensive, time-consuming, and repetitive. Every new business problem usually requires building another specialized agent from scratch. If you need 10 different agents, you're likely paying to build 10 different systems—with no guarantee they'll actually solve your problems the way you expect.

That's the problem I built NanoCrew to solve.

NanoCrew doesn't give you a collection of pre-built agents.

It gives you the ability to create your own specialized agents—without writing code or having any AI engineering experience.

All you need is your business problem.

Simply explain your problem to NanoCrew's Recruiter Agent in plain English. It understands what you're trying to accomplish and generates a draft of your new agent, including the skills, knowledge, tools, and capabilities it needs to solve your specific problem.

Review the draft or edit it, once satisfied, click Approve, and your new agent instantly joins your crew.

But that's just the beginning.

Unlike traditional AI agents, NanoCrew agents continue to evolve after they're created.

If an agent encounters a limitation while performing a task, it doesn't simply fail. It can create the tools it needs to overcome the obstacle, allowing it to complete the work instead of getting stuck.

Your agents also don't work in isolation.

Each agent specializes in a specific responsibility, and they can hand off work to one another whenever necessary. Together, they function like a real team, collaborating to solve complex business problems that would be difficult for a single agent to handle alone.

And the more you use an agent, the better it becomes.

Over time, it accumulates experience, learns from previous work, and becomes increasingly effective at handling your business processes.

NanoCrew also gives you complete flexibility in how your agents operate.

You can:

Run them on demand.
Schedule them to work autonomously.
Operate them directly from WhatsApp.
Integrate them into your existing applications, products, or workflows through APIs.

My vision for NanoCrew is simple:

AI shouldn't force businesses to adapt to generic agents. Businesses should be able to create AI agents that adapt to them.

Instead of buying one AI agent after another—or hiring engineers every time your business evolves—NanoCrew lets you build, deploy, and grow a crew of specialized AI agents that work together, improve over time, and solve the problems that are unique to your business.

That's why I built NanoCrew.

[Shiva Saini @shivasainix]

I quietly built an AI platform while working a part-time job.

Today it's live.

nanocrew — instead of one AI chatbot, you HIRE a team of AI agents. A coder. A researcher. An assistant. or anything you want. Each remembers your business and does the work on its own.

Here's a look 👇

[Shiva Saini @shivasainix]

Made this entire short story with Opus 5.5 🤯

No MCP, No other tools, No fancy setup.
Just Opus 5.5 + code + a cheap TTS model.
The fact that this can be built from a single model is honestly wild.

AI is moving FAST.

[Shiva Saini @shivasainix]

@CACandChill @hanghuang_ How you setup linkedin and X on that?

[Shiva Saini @shivasainix]

@Salman_Bareesh @eliakuratli Yes same question, I'm paying 12 dollar for contabo vps for 12 gb ram and 80gb SSD storage but can't differentiate between what cloudflare is offering compare to contabo

[Shiva Saini @shivasainix]

Every "Customer Onboarding Specialist" job post is really saying: our onboarding process doesn't scale yet. We build AI systems that handle the repeatable onboarding/support workflows, so your team only touches what actually needs a human. https://t.co/VTpgGerW9a

[Shiva Saini @shivasainix]

I build my own multi AI agent harness, agents that works for me as an digital employee to manage my Agency work

[Shiva Saini @shivasainix]

@benteisheuer @kylejeong Hey I'm also working on my own computer use for my own harness, right now it's works fine for most of the models but lags in speed and sometimes not accurate, is your tool open source?

[Shiva Saini @shivasainix]

@orioninc_ng You're just an idiot

[Shiva Saini @shivasainix]

AI has taken mathematician job before a frontend developer's job, crazy 🤣

[Shiva Saini @shivasainix]

More from this big companies going to be the biggest threat for individuals in future

[Kyan Yang @kyanyang_]

this is insane.

Levent and Tristan make major independent progress towards Navier–Stokes, with help from Claude and Codex.

word reaches OpenAI.

days later, OpenAI claims internal NS results, coincidentally using the same novel methods as Levent and Tristan.

Tristan asks if OpenAI trained on their private Codex sessions. he never gets an answer.

then OpenAI pressures Tristan to publish without Levent because Levent works at Anthropic.

when Tristan refuses, he says OpenAI threatens his career.

[Shiva Saini @shivasainix]

Most wild thing I've seen and from now on the fear is very real of losing your job, your salary and conventional working ways, no job is safe if AI solving with very limited human intervention that humans couldn't solve for years .

[OpenAI @OpenAI]

We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics.

The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra.

The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.

[Shiva Saini @shivasainix]

@catalinmpit you can use contabo it's cost around 10 dollar or something for the 12gb ram

[Shiva Saini @shivasainix]

@huesofbanter Oh great place do you live there in like shared pg or flat ? How much is rent let's say if one person want to move?

[Shiva Saini @shivasainix]

@ShubhAgrawal26 The front camera is actually designed for that and I think it's just lightning nothing else , in real life the front camera picture resembles the real life.

[Shiva Saini @shivasainix]

Hehe 😅😂

[Z.ai @Zai_org]

We’re still up.

[Shiva Saini @shivasainix]

ChatGPT is working, claude Sonnet is working but Opus 5 and fable still down.

[Shiva Saini @shivasainix]

@ShubhAgrawal26

[Shiva Saini @shivasainix]

@enesovat22 @grok Why did God create humans in Hinduism vs Buddhism @grok

[Shiva Saini @shivasainix]

Ek baar mai apni bike se ja raha tha beech me traffic police ne rok liye aur mera driving licence manga, maine dikane se mana kar diya aur bola phele prime minister ko bolo apna driving licence dikhaya phir mai dikhauga.

Same energy

[Abhijeet Dipke @abhijeet_dipke]

People are really running out of patience waiting to see my degree.

Makes me wonder how they’ve managed for 12 years without seeing the Prime Minister’s.

Sir @narendramodi, let’s both show our degrees and put an end to this?

[Shiva Saini @shivasainix]

@abhijeet_dipke @narendramodi Sidha bol na lodu tere pass degree nhi hai, sonam wangchuk ke dum pe protest karne wala khud ko compare kar bhi kis se raha hai pradhanmantri se