Arjun | Building Stuff with AI

Redesigning Intelligence

[Arjun | Building Stuff with AI @Arjun4Shukla]

@typesafeai built Jev, a specialized System One model.

I built Kev as an open-source alternative that can use local 9B models and still achieve comparable results on our benchmarks.

Model-agnostic. Local-first. Open source.

⭐ https://t.co/pOBa1TczE2

[Arjun | Building Stuff with AI @Arjun4Shukla]

Built Kev, an open-source System One-style decision engine.

It can compete with Jev using a local 9B model and beat it with better model.

Open, local, model-agnostic.

Released on npm + GitHub with benchmarks.

https://t.co/pOBa1TczE2
If you like it, ⭐ the repo for updates.

[Arjun | Building Stuff with AI @Arjun4Shukla]

I wanted my AI agents to use my friend's GPU when mine was busy.

So I built GPUMesh with Claude Code.

P2P GPU sharing → Docker jobs → remote NVIDIA GPU.

⭐ Star the repo if you think shared GPU compute should exist:
https://t.co/72iHl6FnAo

[Arjun | Building Stuff with AI @Arjun4Shukla]

Your GPU is idle. My AI agent needs compute.

So why rent another GPU?

I built GPUMesh — open-source P2P GPU sharing for AI agents and training jobs.

If you want to see this idea grow, ⭐ the repo:
https://t.co/72iHl6FnAo

[Arjun | Building Stuff with AI @Arjun4Shukla]

My AI agents needed more GPU compute, while my friend's RTX 5060 was sitting idle.

So I built GPUMesh — an open-source P2P GPU network that lets me run Docker GPU jobs on his machine.

If you want to see this idea grow, ⭐ the repo:
https://t.co/72iHl6FnAo

[Arjun | Building Stuff with AI @Arjun4Shukla]

I’m building the missing build layer for agentic AI.

aimake tracks dependencies + content hashes so changing one prompt doesn’t mean rebuilding everything.

It’s open source and early.

If you want to see where this goes, ⭐ the repo:
https://t.co/UbSD5k0BtG

[Arjun | Building Stuff with AI @Arjun4Shukla]

10 agents. 50 tools. 100 prompts. One tiny change → rerun everything?

I built aimake for agentic AI + ML pipelines: incremental builds, dependency tracking, and caching. Only rebuild what changed.

Open source. ⭐ Star the repo if useful:
https://t.co/UbSD5k0BtG

[Arjun | Building Stuff with AI @Arjun4Shukla]

Why should an AI pipeline rerun everything when one thing changes?

I built aimake - an incremental build system for AI/ML that tracks dependencies and hashes to rebuild only what changed.

Open source. If useful, a ⭐ would help: https://t.co/UbSD5k0BtG

[Arjun | Building Stuff with AI @Arjun4Shukla]

Why should an AI pipeline rerun everything when one thing changes?

I built aimake — an incremental build system for AI/ML that tracks dependencies and hashes to rebuild only what changed.

Open source. If useful, a ⭐ would help: https://t.co/UbSD5k0BtG

[Arjun | Building Stuff with AI @Arjun4Shukla]

AI pipelines shouldn't rerun everything because you changed one prompt.

I built aimake for AI/ML. It tracks dependencies + content hashes and only rebuilds what changed.

It's open source, so if useful, consider a ⭐ on GitHub: https://t.co/UbSD5k0BtG

[Arjun | Building Stuff with AI @Arjun4Shukla]

While vibe coding in Blender, I kept repeating the same context to AI.

So I built Blender Skills.

It gives Cursor, Claude Code, and Kiro the Blender context they need from the start.

If it saves you time, ⭐ the repo. More skills coming soon.

GitHub: https://t.co/gMSWqjDrrw

[Arjun | Building Stuff with AI @Arjun4Shukla]

Teaching AI Blender was easier than I expected.

Built Blender Skills—an open-source skill pack that works with Claude Code, Cursor, and Kiro to make AI better at Blender.

Feedback is welcome!

⭐ the repo for future updates with more skills.

GitHub: https://t.co/gMSWqjDrrw

[Arjun | Building Stuff with AI @Arjun4Shukla]

Your AI is only as good as the context you give it.

So I built Blender Skills—an open-source Blender skill pack for Claude Code, Cursor, and Kiro.

Try it out and let me know what you build.

Star⭐ the repo for future updates with more skills.

GitHub: https://t.co/gMSWqjDrrw

[Arjun | Building Stuff with AI @Arjun4Shukla]

Inspired by Loop Engineering, I built Loop-MCP.

If you're into vibe coding with Cursor, Kiro, or any MCP client, it's an easy way to add structured loops and get more precise, reliable results.

Install. Configure. Build.
" pip install loop-mcp "
GitHub: https://t.co/LRbrdFoY0R

[Arjun | Building Stuff with AI @Arjun4Shukla]

Inspired from @addyosmani blog on loop engineering and @karpathy
Released Loop-MCP.

Today it used its own loop engineering workflow to improve itself.

If you'd like to try it, check it out and ⭐ the repo.

GitHub: https://t.co/LRbrdFoY0R
PyPI: https://t.co/7tJmPkalkg

[Arjun | Building Stuff with AI @Arjun4Shukla]

Been using this workflow for a while. Recently learned it's called Loop Engineering.

So I open-sourced it as Loop-MCP.

Install, configure in Cursor/Kiro via MCP, and start building.

GitHub: https://t.co/LRbrdFoY0R
PyPI: https://t.co/7tJmPkalkg

[Andrew Ng @AndrewYNg]

“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build.

Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention.

The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention!

Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on.

The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience.

When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful.

AI-native teams are increasingly using AI to help shape product direction, for example, automating the gathering and analysis of usage data, summarizing written and verbal customer feedback, or carrying out competitive analysis. However, for pretty much all the products I’m involved in, I see humans as having a significant context advantage over current AI systems — we know a lot more than the AI system about the users and the context the product has to operate in — and thus humans play a critical role. Many people describe this human contribution as “taste,” but I prefer to think of it as humans having a context advantage, since that gives us a clearer path to helping AI systems get better. This also speaks to why this step can’t be automated: So long as the human knows something the AI does not, human-in-the-loop is needed to to inject that knowledge into the system.

External feedback loop: This includes a wide range of tactics like asking a few friends for feedback, launching to alpha testers, or putting the code into production with A/B testing. These tactics are usually slow, rarely taking less than hours and sometimes taking days or even weeks. This data informs the developer vision, which in turn continues to drive the detailed product spec, which in turn drives the coding agent.

With coding agents speeding up software development, more engineers are starting to play a partial product management role. For many engineers who are growing into this role, the hardest part is shaping the product vision and striking a balance between building (bridging the gap between vision and spec) and getting user feedback to evolve the vision. It is important to do both!

I will write more about how to do this in future posts, but for now, I find it encouraging that engineers are playing an expanded role (just as product managers and designers now do more engineering).

[Original text: The Batch]

[Arjun | Building Stuff with AI @Arjun4Shukla]

@marconoiz I think I am going to hire the coder who uses loop-mcp.
loop engineering your entire IDE cursor or Kiro.
Build smarter systems

GitHub: https://t.co/LRbrdFoY0R
PyPI: https://t.co/7tJmPkalkg

[Arjun | Building Stuff with AI @Arjun4Shukla]

How many of you here use Cursor or Kiro to build?
Have you tried Loop Engineering in IDE?

I built Loop-MCP to make it simple. It's open source, easy to install, and easy to configure.

Let me know what you think!

GitHub: https://t.co/LRbrdFoY0R
PyPI: https://t.co/7tJmPkalkg

[Arjun | Building Stuff with AI @Arjun4Shukla]

I just want to know how many of you guys here in community loves to code or build new thing with cursor or kiro ?
Let me know in the comments I have something to help you guys have better context and smarter build with your same IDE.

[Arjun | Building Stuff with AI @Arjun4Shukla]

@Raytar maybe you could use loop-mcp , it is simple to install configure and run.
It completely automates your IDE be it cursor or kiro to loop.
you can checkout it at :
GitHub: https://t.co/LRbrdFoY0R
PyPI: https://t.co/7tJmPkalkg