Top all-time · #19735
InstaVM
Company blog · instavm.io/blog · on HN as mkageniusaisecurity
InstaVM is the company blog at instavm.io, writing about ai and security. Since 2025, 3 different Hacker News readers have linked it 29 times, most often “How Claude Code and Codex approach sandboxing”. No feed was found, so read it on the site itself.
Too few sampled comments (5) to say how often HN recommends it.?
Why HN links it
The comments link InstaVM's site as a cloud VM sandbox product for AI agents, with a feature-tour blog post. The commenters are mostly the company's own founders promoting it, not praising the writing.
Summarised by Claude from a sample of 5 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
The production control plane for AI agents. Run agents like production servers: isolated, observable, and controlled. Firecracker microVMs with sub-200ms boot.
Most-linked posts?
- /2 people · 8 mentions · first linked 2026-01-30
- How Claude Code and Codex approach sandboxing2 people · 3 mentions · first linked 2026-04-22
What Hacker News says?
It's also unclear what kind of sandboxing they are referring to. Is it the codex one - coz that one has built-in ways to circumvent guardrails, for example by "just asking user" and sometimes just resolves to no sandbox needed on its own. In case someone wants to deep dive into how codex and claude code approaches sandboxing - https://instavm.io/blog/how-claude-code-and-codex-approach-s...
Comment linking /blog/how-claude-code-and-codex-approach-sandboxing
on “OpenAI and Hugging Face partner to address security incident”Submitted I want everything local – Building my offline AI workspace as a story · 1143 points
HN discussionIf you are into nixos, we at InstaVM have just launched[1] nixos based sandboxes. 1. https://instavm.io/blog/nixos-reproducible-dev-environments-...
Comment linking /blog/nixos-reproducible-dev-environments-on-instavm
on “Show HN: Clawk – Give coding agents a disposable Linux VM, not your laptop”Submitted Anti-patterns while working with LLMs as a story · 76 points
HN discussionHi Ben, one of the founders of InstaVM here. Congrats on the launch! Here is a feature tour of InstaVM https://instavm.io/blog/meet-instavm-infra-for-your-agents We would be publishing on the tech soon. Would love to give you a demo of InstaVM and trade notes. Let me know abhishek@instavm.io
Comment linking /blog/meet-instavm-infra-for-your-agents
on “Launch HN: Freestyle: Sandboxes for AI Coding Agents”Submitted How Claude's Watermark Works as a story · 3 points
HN discussionIs this similar to https://instavm.io/ ?
Comment linking /
on “Launch HN: Freestyle: Sandboxes for AI Coding Agents”Submitted How Claude Code and Codex approach sandboxing as a story · 2 points
HN discussionAWS for AI agents - https://instavm.io Providing sandboxes through a CLI. Guardrails such as egress control and secret injection and audit trails built in. We can also be used as 3rd party sandboxes in Anthropic managed agent and OpenAI sdk. https://instavm.io/blog/self-hosting-claude-managed-agents-o...
Comment linking /blog/self-hosting-claude-managed-agents-on-instavm
on “Ask HN: What are you working on? (June 2026)”Submitted Anthropic Skills Can Be Programmatically Optimized (Using DSPy) as a story · 2 points
HN discussion> continued using Artifactory for their sandbox This is still fine. Infact, they had gone one step ahead by having an internal cluster of artifactory rather public managers like pip. The thing they missed is they didn't revoke the write access to it. Even after the ssrf. In our[1] or other sandbox providers' sandboxes, by default you have access to npm, pip etc package managers, but only read access. 1. https://inst…
Comment linking /
on “Responding to the next frontier of critical cyber capabilities”Submitted Show HN: I built a mitmproxy AI agent using 4000 paid security disclosures as a story · 2 points
HN discussionWith instavm ( https://instavm.io ), you can provide an OCI image built from a dockerfile.
Comment linking /
on “Show HN: Smol machines – subsecond coldstart, portable virtual machines”Submitted I Used 4,000 Paid Bug Bounty Reports to Build a CLI-First Security Agent as a story · 2 points
HN discussionYou can use https://instavm.io for that. It's a full linux machine. Run anything. There is a mac only open source version based on apple containers - ideal for local llm use cases https://github.com/instavm/coderunner
Comment linking /
on “Show HN: Smol machines – subsecond coldstart, portable virtual machines”Submitted InstaPoT: Using InstaVM with DSPy's Program of Thought as a story · 2 points
HN discussionThe images or rather portable artifacts rehydration on any platform plus the packaging is neat. I have been working on https://instavm.io for some time around VM based sandboxes and related infra for agents and this is refreshing to see.
Comment linking /
on “Show HN: Smol machines – subsecond coldstart, portable virtual machines”Submitted How Claude's Watermark Works as a story · 1 points
HN discussionThis looks cool, congratulations. We investigated WASM for our use case but then turned to Apple containers which run 1:1 mapped to a microVM for local use here, which is being used by a bunch of folks https://github.com/instavm/coderunner We are currently also building a solution InstaVM which is ideologically the same but for cloud https://instavm.io
Comment linking /
on “Show HN: Amla Sandbox – WASM bash shell sandbox for AI agents”Submitted Code mode can help smaller LLM models as a story · 1 points
HN discussionHey, this is exactly what we do at https://instavm.io Agents get persistent storage that outlive the sandbox and when the agent spins up again you get access to the computer with same files.
Comment linking /
on “Show HN: Tilde.run – Agent Sandbox with a Transactional, Versioned Filesystem”Submitted Why AI Agents Need a Two-Tier Architecture as a story · 1 points
HN discussionHave you tried https://instavm.io in US
Comment linking /
on “Run isolated sandboxes with full lifecycle control: AWS introduces MicroVMs”Submitted How Claude Code and Codex approach sandboxing as a story · 1 points
HN discussionNot so subtle plug from yet another sandbox provider, https://instavm.io : Apart from the above features. 1. We support more than 32GB disk (as a detachable device, ideal for agentic memory) 2. We provide egress control 3. We provide vault for secret injection (to counter prompt injection) 4. Snapshot / forking. 5. long lived sandboxes. Everything supported in APIs and CLI for agents. Can be used via - npx skills ad…
Comment linking /
on “Run isolated sandboxes with full lifecycle control: AWS introduces MicroVMs”Submitted Hacking 'Skill' distilled from 4200 Hackerone vulns as a story · 1 points
HN discussionSubmitted I Want Everything Local – Building My Offline AI Workspace (incl. Claude Skills) as a story · 1 points
HN discussionSubmitted Claude Skills but Local (and Private) as a story · 1 points
HN discussion