Stories by theaniketmaurya

Show HN: A durable filesystem layer for AI agents

How Qcow2 Overlays Work in QEMU

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Show HN: Automate legacy software on a Windows Sandbox

Show HN: I'm running parallel Pi agents on a local sandbox

Parallel Pi coding agents in a sandbox

Show HN: Run coding agents in a sandbox locally

Open-source isolated runtime for AI agents

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

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

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

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

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

A full-stack Python model serving library

LLM training in simple, pure C/CUDA

Where do LLMs spend their FLOPS?

Scaling Large (Language) Model Training with PyTorch Lightning

OpenLLaMA – comparable performance and better in several task to original LLaMA