HN Explorer

theaniketmaurya

↗ HN profile [ 72.8 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. Stop Looking for the Next Jony Ive (maurya.bearblog.dev)
    1 points 0
  3. Show HN: Petabyte-scale storage for AI agent sandboxes (twitter.com)

    We enabled Petabyte scale durable storage for Celesto sandboxes, useful for coding agents, harnesses and store large files.

    3 points 1
  4. Show HN: A durable filesystem layer for AI agents (github.com)

    I run AI agents on my laptop and cloud. Often I wish to synchronize the memory markdowns created on multiple platforms. So I built a S3 based durable filesystem which can be mounted anywhere. It is implemented in Rust…

    4 points 8
  5. How Qcow2 Overlays Work in QEMU (celesto.ai)
    2 points 2
  6. SkillOpt: Executive Strategy for Self-Evolving Agent Skills (arxiv.org)
    4 points 1
  7. Show HN: Automate legacy software on a Windows Sandbox (celesto.ai)

    The majority of legacy systems run on the Windows operating system. It is hard to automate with computer-use agents because of weird pop-ups, lack of a DOM like browsers, random clicks, and cost at scale. We built an…

    1 points 2
  8. 1 points 0
  9. Show HN: I'm running parallel Pi agents on a local sandbox (github.com)

    I've been running Pi using SmolVM to build SmolVM! SmolVM provides an abstraction over microVMs to easily create sandboxes for coding agents, OpenClaw, or just to build a custom harness. To use it, install using: curl…

    8 points 2
  10. Parallel Pi coding agents in a sandbox (github.com)
    3 points 2
  11. Show HN: Run coding agents in a sandbox locally (github.com)

    Launching SmolVM -- run claude and codex in sandboxed environment with full permissions worry free. It sucks to “press enter and accept changes” every few seconds while using coding agents. We made it easy to isolate…

    2 points 1
  12. Open-source isolated runtime for AI agents (github.com)
    4 points 2
  13. I rewrote network setup for sandboxes in Rust and it sped up by 57x (github.com)
    2 points 0
  14. Show HN: SmolVM – open-source sandbox for coding and computer-use agents (github.com)

    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,…

    8 points 3
  15. Open-source sandboxes to run AI code, browser agents and computer-use (github.com)
    2 points 1
  16. An attempt to make MicroVMs more accessible (SmolVM – Python SDK) (github.com)
    1 points 1
  17. Show HN: Built an open-source SDK to simplify tool authentication for AI Agents (github.com)
    1 points 0
  18. A full-stack Python model serving library (github.com)
    8 points 1
  19. LLM training in simple, pure C/CUDA (twitter.com)
    4 points 1
  20. 1 points 0
  21. Where do LLMs spend their FLOPS? (artfintel.com)
    3 points 0
  22. 1 points 0
  23. Scaling Large (Language) Model Training with PyTorch Lightning (lightning.ai)
    2 points 0
  24. OpenLLaMA – comparable performance and better in several task to original LLaMA (twitter.com)
    2 points 0
  25. Tutorial: How to Build a Machine Learning Training and Deployment Pipeline (lightning.ai)
    3 points 0