Hacker News: theaniketmaurya

New comment by theaniketmaurya in "What if database branching was easy?"

theaniketmaurya — Mon, 20 Apr 2026 12:57:09 +0000

i was using neon and they had some similar feature but now using planetscale. would be curious to know how you all are doing it?

New comment by theaniketmaurya in "Open-source isolated runtime for AI agents"

theaniketmaurya — Sat, 18 Apr 2026 17:04:58 +0000

I've been dogfooding it by running coding agents. I mount my local filesystem and pull the changes back when done.

New comment by theaniketmaurya in "Open-source isolated runtime for AI agents"

theaniketmaurya — Sat, 18 Apr 2026 16:55:55 +0000

I've been working on an open-source isolated runtime for AI agents. Over a period of time I was able to bring the cold start time in sub-seconds, persistent filesystem, and network control.

I'm looking for feedback and if you're into this field - why or *why not* you would use it.

Open-source isolated runtime for AI agents

theaniketmaurya — Sat, 18 Apr 2026 16:55:55 +0000

Article URL: https://github.com/CelestoAI/SmolVM

Comments URL: https://news.ycombinator.com/item?id=47817395

Points: 4

# Comments: 3

I rewrote network setup for sandboxes in Rust and it sped up by 57x

theaniketmaurya — Tue, 14 Apr 2026 20:34:53 +0000

Article URL: https://github.com/CelestoAI/SmolVM/pull/145

Comments URL: https://news.ycombinator.com/item?id=47771136

Points: 2

# Comments: 0

New comment by theaniketmaurya in "Show HN: SmolVM – open-source sandbox for coding and computer-use agents"

theaniketmaurya — Fri, 10 Apr 2026 11:34:06 +0000

yes, we have an example of OpenClaw.

SmolVM uses microVMs which means the resource consumption is quite minimal. For now, you can specify the amount of RAM while starting the VM. We are making it elastic so you can configure to expand the RAM based on usage.

Here is the link to the [documentation](https://docs.celesto.ai/smolvm), but I can also show you on a call.

Show HN: SmolVM – open-source sandbox for coding and computer-use agents

theaniketmaurya — Fri, 10 Apr 2026 00:01:00 +0000

SmolVM is an open-source local sandbox for AI agents on macOS and Linux.

I started building it because agent workflows need more than isolated code execution. They need a reusable environment: write files in one step, come back later, snapshot state, pause/resume, and increasingly interact with browsers or full desktop environments.

Right now SmolVM is a Python SDK and CLI focused on local developer experience.

Current features include: - local sandbox environments - macOS and Linux support - snapshotting - pause/resume - persistent environments across turns

Install: ``` curl -sSL https://celesto.ai/install.sh | bash smolvm ```

I’d love feedback from people building coding agents or computer-use agents. Interested in what feels missing, what feels clunky, and what you’d expect from a sandbox like this.

Comments URL: https://news.ycombinator.com/item?id=47711887

Points: 8

# Comments: 3

Open-source sandboxes to run AI code, browser agents and computer-use

theaniketmaurya — Mon, 06 Apr 2026 23:29:23 +0000

Article URL: https://github.com/CelestoAI/smolVM

Comments URL: https://news.ycombinator.com/item?id=47668778

Points: 2

# Comments: 0

New comment by theaniketmaurya in "An attempt to make MicroVMs more accessible (SmolVM – Python SDK)"

theaniketmaurya — Mon, 16 Feb 2026 22:42:59 +0000

Also, I've been running OpenClaw using SmolVM on my macOS. It adds a hardware level isolation (using KVM).

https://github.com/CelestoAI/SmolVM/blob/main/examples/openc...

An attempt to make MicroVMs more accessible (SmolVM – Python SDK)

theaniketmaurya — Mon, 16 Feb 2026 22:40:41 +0000

Article URL: https://github.com/CelestoAI/SmolVM

Comments URL: https://news.ycombinator.com/item?id=47041334

Points: 1

# Comments: 1

Show HN: Built an open-source SDK to simplify tool authentication for AI Agents

theaniketmaurya — Sun, 12 Oct 2025 02:27:05 +0000

Article URL: https://github.com/CelestoAI/agentor

Comments URL: https://news.ycombinator.com/item?id=45554626

Points: 1

# Comments: 0

New comment by theaniketmaurya in "Abundant Intelligence"

theaniketmaurya — Tue, 23 Sep 2025 15:05:22 +0000

let me put some more in nvidia now

New comment by theaniketmaurya in "Deploy your own AI vibe coding platform from Cloudflare"

theaniketmaurya — Tue, 23 Sep 2025 14:33:27 +0000

Also found this Vibe coding OSS from Modal - https://github.com/modal-labs/modal-vibe

Curious if Vercel is also gonna open-source theirs.

New comment by theaniketmaurya in "Deploy your own AI vibe coding platform from Cloudflare"

theaniketmaurya — Tue, 23 Sep 2025 14:32:18 +0000

Nice! they forgot to add the Github link for the repo lol.

PS: If you're looking too - https://github.com/cloudflare/vibesdk

New comment by theaniketmaurya in "Use One Big Server (2022)"

theaniketmaurya — Sun, 31 Aug 2025 22:06:21 +0000

I’m using Neon too and upgraded to the scale up version today. Curious, what do you mean rhat they can get pricey?

New comment by theaniketmaurya in "Llama 3.2: Revolutionizing edge AI and vision with open, customizable models"

theaniketmaurya — Thu, 26 Sep 2024 11:30:07 +0000

You can run with LitServe. here is the code - https://lightning.ai/lightning-ai/studios/deploy-llama-3-2-v...

New comment by theaniketmaurya in "Llama 3.2: Revolutionizing edge AI and vision with open, customizable models"

theaniketmaurya — Thu, 26 Sep 2024 11:29:02 +0000

You can run it with LitServe (MPS GPU), here is the code - https://lightning.ai/lightning-ai/studios/deploy-llama-3-2-v...

A full-stack Python model serving library

theaniketmaurya — Wed, 28 Aug 2024 12:57:16 +0000

Article URL: https://github.com/Lightning-AI/LitServe

Comments URL: https://news.ycombinator.com/item?id=41378951

Points: 8

# Comments: 0

New comment by theaniketmaurya in "LLM training in simple, pure C/CUDA"

theaniketmaurya — Mon, 08 Apr 2024 20:17:32 +0000

LLM training in simple, pure C/CUDA. There is no need for 245MB of PyTorch or 107MB of cPython.

LLM training in simple, pure C/CUDA

theaniketmaurya — Mon, 08 Apr 2024 20:17:32 +0000

Article URL: https://twitter.com/karpathy/status/1777427944971083809

Comments URL: https://news.ycombinator.com/item?id=39973268

Points: 4

# Comments: 1