Blog

Technical deep-dives on secure AI execution, sandboxing, and building production agents.

April 17, 2026·5 min read·Abhishek

InstaVM is a sandbox provider for the OpenAI Agents SDK.

InstaVM is a sandbox provider for the OpenAI Agents SDK. Run SandboxAgent workloads inside Firecracker microVMs with PTY support, egress controls, and port exposure.

OpenAIAgents SDKSandboxAI AgentsInstaVMPTY
April 5, 2026·18 min read·Abhishek

How Claude Code & Codex approach sandboxing

How OpenAI's Codex and Anthropic's Claude Code prevent an LLM from running arbitrary commands on your machine. Same OS primitives, different trust architectures.

AISecuritySandboxingClaude CodeCodexDeep Dive
March 17, 2026·7 min read·Abhishek & Manish

Meet InstaVM

Today we're launching the public beta of InstaVM with $50 in free compute, no credit card required, plus the full runtime, networking, and observability stack agents need in production.

InstaVMAI AgentsInfrastructureAnnouncement
February 28, 2026·3 min read·Manish

Fastest Way to Deploy OpenClaw

Deploy OpenClaw in minutes on InstaVM: create snapshot, launch VM, share URL, set token, and approve device. Just Claw.

OpenClawInstaVMDeploymentSnapshotAgents
November 10, 2025·8 min read·Manish

Anti-patterns while working with LLMs

Anti-patterns observed while working extensively with LLMs — from redundant context to over‑engineering.

BlogAILLMBest PracticesAnti-patterns
We use cookies to improve your experience. See our cookie policy.