Hacker News Reader

theaniketgirion Show HN: AIP – A Cryptographic Identity Protocol for Autonomous AI Agents

Hi HN — I'm Aniket, working on AIP.

As AI agents begin executing real-world actions (calling APIs, writing to databases, triggering workflows), there's currently no native identity or authorization layer for them.

AIP is an open protocol that gives every agent a cryptographic identity and requires actions to be signed and verified before execution.

The goal is simple: if an agent wants to act, the system should be able to verify who it is and what it's allowed to do — in milliseconds.

The repo includes a Python SDK, verification pipeline, and a decorator that can protect agent actions with a single line.

Curious to hear what the HN community thinks about identity and trust layers for autonomous systems.

theaniketgirion Show HN: AIP – An open protocol for verifying what AI agents are allowed to do

Exactly — current platforms authenticate the account, but with agents the account isn’t the decision-maker anymore.

Two identical API calls can come from either intended behavior or a manipulated model, and today they look the same to the system. Permissions tied to a static identity don’t describe the real risk.

So the missing piece is verifying the agent’s declared intent and boundaries before execution, not just who sent the request.

That’s why this starts looking more like protocol infrastructure than a product feature.

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Thanks a lot, really appreciate that Building something new always gets mixed reactions, but messages like yours keep me going.

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Yeah, that’s how I see it too. LLMs are part of the toolkit now what matters is how you use them to actually ship something useful.

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Yeah, I did! I trained a few small ones — mostly the “nano” and “tiny” templates (a few million params) on datasets like Shakespeare and Alpaca. The goal was to make sure the training loop, tokenizer, and evaluation all worked smoothly.

Didn’t go for massive models — more about making the whole setup process quick and reliable. You can actually train the nano one on CPU in a few minutes just to see it working.

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Thanks everyone for the feedback and discussion. For those asking technical questions - happy to help! The tool works on Mac/Linux/Windows, check the README for setup. For those concerned about the architecture - it follows standard scaffolding patterns (create-next-app, etc). TypeScript CLI generates Python projects. 82+ stars in 24 hours - grateful for everyone trying it out. Keep the feedback coming!

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Fair point I agree embedding code as strings isn’t ideal. I did it mainly to make npx create-llm portable without needing a Python setup during scaffolding. Definitely open to improving that happy to refactor if you have suggestions.

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

The Python-in-TS bit made me smile But to clarify, it’s a standard TypeScript CLI — no such hacks involved, just template-based generation.

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Fair points and I get where you’re coming from. I’ve been very open that AI helped with repetitive parts (docs, boilerplate, commit messages). The functional code training logic, model architecture, CLI was written and tested by me. Some design choices (like storing scripts as strings or using if-else) were just pragmatic decisions made while iterating fast, not signs of AI authorship. Either way, the project is open source — you can inspect, critique, or even improve any part of it. I’m happy to take constructive feedback. My goal’s just to make LLM training more accessible.

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Thanks for the support! Appreciate you trying it out. Let me know if you hit any issues or have ideas for improvements.

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Good question! I think you mean nanoGPT (Karpathy's minimal GPT implementation)?

Key differences:

nanoGPT: - Minimal reference implementation (~300 lines) - Educational code for understanding transformers - Requires manual setup and configuration - Great for learning the internals

create-llm: - Production-ready scaffolding tool (like create-next-app) - One command: npx create-llm → complete project ready - Multiple templates (nano/tiny/small/base) - Built-in validation (warns about overfitting, vocab mismatches) - Includes tokenizer training, evaluation, deployment tools - Auto-detects issues before you waste GPU time

Think of it as: nanoGPT is the reference, create-llm is the framework.

nanoGPT teaches you HOW it works. create-llm lets you BUILD with what you learned.

You can actually use nanoGPT's architecture in create-llm templates - they're complementary tools!

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

To clarify the AI question once and for all:

What AI did: - Generated README templates (boilerplate markdown) - Suggested commit messages (I didn't always edit them) - Helped with documentation structure

What I wrote: - All Python training logic (train.py, trainer.py, callbacks) - All model architectures (gpt.py, tiny.py, small.py, etc.) - Tokenizer integration - Data pipeline - CLI scaffolding (

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Thanks for the support!

And yeah, the commit history is messy - I was learning and shipping fast. Not perfect, but the tool works and people are using it.

Let me know if you have any questions when you try it!

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Thanks! The blog post is just my honest journey - spent way too much time trying to understand LLMs, figured others had the same frustration.

If you try create-llm, would love your feedback. Always looking to make it better.

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Great question - I should've been clearer.

When I started, I wanted to understand LLMs deeply. But I hit a wall: tutorials were either "hello world" toys or "here's 500 lines of setup before you start."

What I needed was: "give me working code quickly, THEN let me modify and learn."

That's what create-llm does. It scaffolds the boilerplate (like create-next-app), so you can spend time learning the interesting parts: - Why does vocab size matter? (adjust config, see results) - What causes overfitting? (train on small data, see it happen) - How do different architectures perform? (swap templates, compare)

It's "easy to start, deep to master." The abstraction gets you running in 60 seconds, then you dig into the code

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Totally fair question!

Docs / Markdown: AI handled repetitive stuff like READMEs and summaries.

Core logic / Python: fully written by me.

Commit messages: some minimal ones just for quick iterations — the real work is in the code.

AI helped with boilerplate so I could ship faster; all functionality is hand-crafted.

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Mostly the repetitive stuff like README generation and pushing code with meaningful commit messages was handled by AI. The actual work and logic were done by me.

theaniketgirion Show HN: Create-LLM – Train your own LLM in 60 seconds

Yep, works fine on Mac. Try the nano or tiny templates if you want quicker training runs