# blog

Engineering the millisecond cloud.

Deep-dives and how-tos on microVMs, Firecracker, snapshot-restore, and the infrastructure behind safe, fast AI agent execution.

·12 min read·Ajay Kumar

Best Code Execution Sandboxes for AI Agents (2026)

The honest best-of for running AI-agent code: PandaStack, E2B, Modal, Daytona, Northflank, Vercel Sandbox, Fly Sprites, and the OSS field — judged by decision criteria, not a leaderboard.

comparisonai-sandboxfirecrackercode-executioninfrastructure
·12 min read·Ajay Kumar

Best Open-Source Sandboxes for Running Untrusted Code

The honest set of open-source, self-hostable options for isolating untrusted code execution — characterized by license and isolation model, not a leaderboard.

open-sourceai-sandboxfirecrackergvisorkatainfrastructure
·11 min read·Ajay Kumar

Self-Hosted Code Execution Sandbox for Production AI

Why self-host a code execution sandbox — data residency, VPC isolation, cost at scale — what it actually takes to run, and the honest cases where hosted wins.

self-hostingai-sandboxfirecrackerinfrastructurecompliance
·8 min read·Ajay Kumar

The Real Cost of Hosted Sandboxes at Scale

Hosted sandboxes are cheap until they aren't. The cost structure of per-second sandboxes — idle, per-create overhead, egress — and where the math flips toward self-hosting.

pricingai-sandboxe2b-alternativefirecrackerself-hosting
·8 min read·Ajay Kumar

Copy-on-Write Rootfs: Why MicroVM Create Is O(metadata)

Cloning a multi-gigabyte rootfs sounds expensive. With a copy-on-write filesystem it isn't: XFS reflink makes a clone that shares data extents until a write copies a single block, so the clone is O(metadata), not O(data). Here's the mechanism, and why ext4 can't do it.

copy-on-writefirecrackerreflinkxfsrootfsinternals
·9 min read·Ajay Kumar

userfaultfd: Lazy Memory for Instant VM Restore

userfaultfd hands a page fault to your own code instead of the kernel resolving it. That one inversion is what lets a microVM resume before its whole memory image has arrived — PandaStack uses it to stream vm.mem from object storage on restore.

userfaultfdfirecrackersnapshotsmemorylinux-kernelarchitecture
·9 min read·Ajay Kumar

How PandaStack Creates a MicroVM in Under 200ms

A cold Firecracker boot is genuinely fast — minimal device model, no firmware, a stripped kernel. But PandaStack's 179ms create isn't a boot at all: it restores a frozen machine's memory and device state and resumes. Here's the difference, with real numbers.

firecrackermicrovmsnapshot-restoreperformanceinternalsarchitecture
·9 min read·Ajay Kumar

WebAssembly vs MicroVMs for Sandboxed Code

WASM isolates one program's memory behind a software boundary; a microVM isolates a whole OS behind a hardware one. They're more complementary than competing — here's how to choose, honestly.

wasmwasimicrovmfirecrackerisolationconcepts
·9 min read·Ajay Kumar

Code Interpreter API Pricing, Compared

A model-by-model map of code interpreter API pricing — no invented competitor numbers. What you actually pay for, and the self-host break-even at scale.

pricingai-sandboxcode-interpreterfirecrackerinfrastructure
·9 min read·Ajay Kumar

Stop an AI Agent Touching the Host Filesystem & Network

An agent should not read your host files, reach your internal services, or quietly exfiltrate. Here's the per-sandbox boundary that enforces that — own kernel, own filesystem, own network namespace — and the parts you still have to configure yourself.

ai-agentssecuritynetworkingisolationmicrovm
·14 min read·Ajay Kumar

How to Sandbox Untrusted & AI-Generated Code

You have to run code you don't trust — user submissions, CI, and now LLM output — without it owning your host or your other tenants. This is the decision framework: what threat you're defending against, what isolation actually holds, and where each option fits.

securitysandboxmicrovmai-agentsconcepts
·8 min read·Ajay Kumar

Why Docker Isn't a Sandbox

A container is excellent isolation for software that cooperates with you. It is not a security boundary against software that's actively trying to break out — because it shares the one thing it's supposed to be protected from: the host kernel.

dockercontainerssecuritysandboxingkernel
·11 min read·Ajay Kumar

The Code Isolation Hierarchy

Bare process, container, gVisor, Kata, microVM, confidential VM — a clean walk up the isolation ladder, with each rung's real threat model and overhead, and why higher isn't automatically better.

securityisolationcontainersgvisormicrovmconcepts
·9 min read·Ajay Kumar

Multi-Tenant Code Execution: Isolation Requirements

If you run other people's code on shared hosts, the requirements aren't a wishlist — they're the line between a platform and a breach. Hardware isolation between tenants, network isolation, resource limits, ephemerality, and blast-radius containment, with honest notes on residual risk.

multi-tenancysecurityisolationmicrovmcode-execution
·12 min read·Ajay Kumar

E2B Alternatives: A Guide to AI Code Execution Sandboxes

E2B is good and hosted-first. Here are the real E2B alternatives and a framework for choosing one — organized by decision criteria, not a ranked list.

comparisonai-sandboxfirecrackerinfrastructuree2b
·9 min read·Ajay Kumar

PandaStack vs Vercel Sandbox: MicroVM Code Execution

Two real Firecracker microVM platforms. The decision isn't isolation — it's ecosystem lock-in, forking, and whether you can run it on your own infra.

comparisonai-sandboxfirecrackerinfrastructurevercel-sandbox
·9 min read·Ajay Kumar

PandaStack vs Northflank: Sandboxes for AI Agents

A fair, technical breakdown of PandaStack and Northflank for running AI-agent code — isolation model, boot path, forking, open-source self-host, and platform scope.

comparisonai-sandboxfirecrackerinfrastructurenorthflank
·9 min read·Ajay Kumar

PandaStack vs Fly.io Sprites: Firecracker Sandboxes

Two Firecracker products, two opposite bets: persistent-by-default VMs that scale to zero versus snapshot-restore on every create with no warm pool.

comparisonai-sandboxfirecrackerinfrastructurefly-iosprites
·10 min read·Ajay Kumar

An Open-Source OpenAI Code Interpreter Alternative

OpenAI's hosted Code Interpreter is Python-only and a black box you can't run yourself. Here's a self-hostable, Firecracker-isolated alternative — and an honest read on when OpenAI's built-in is the right call.

code-interpreteropenaialternativefirecrackerai-agents
·8 min read·Ajay Kumar

What is a microVM? Firecracker, isolation, and why agents need it

Containers share the host kernel; microVMs don't. Here's what that means for security, cold-start latency, and why agent platforms are built on Firecracker.

microvmfirecrackerisolationconcepts
·9 min read·Ajay Kumar

Firecracker vs Docker: which one runs untrusted code?

They're not competitors — Docker builds images, Firecracker runs VMs. But for the one question that matters (can it run untrusted code?), the answer differs sharply.

firecrackerdockercontainerscomparison
·10 min read·Ajay Kumar

How to run untrusted (and AI-generated) code safely

Your agent just wrote a shell command. Before you run it: here's what can go wrong, which isolation actually holds, and a pattern for executing arbitrary code without betting your infrastructure.

securitysandboxai-agentshow-to
·10 min read·Ajay Kumar

Secure code execution for AI agents: isolation, ephemerality, and network control

Your agent doesn't just talk — it runs code. Here's the boundary that makes that safe: hardware isolation, a fresh disposable environment per task, and locked-down network and secrets.

ai-agentssecuritysandboxmicrovmconcepts
·9 min read·Ajay Kumar

Snapshots and Forks: Copy-on-Write for Running Machines

A snapshot freezes a running microVM's RAM and device state to disk; a fork clones that frozen machine with copy-on-write so you can branch a live environment — and your agent's mid-task state — in around 400ms.

snapshotsforkingfirecrackercopy-on-writeai-agentsarchitecture
·9 min read·Ajay Kumar

How to Give Your AI Agent a Sandbox (With Code)

Wire a microVM sandbox as a run_code tool so your LLM agent can run model-written code safely — the loop, the tool schema, and cleanup, with runnable Python.

tutorialai-agentscode-executionpythonsandbox
·9 min read·Ajay Kumar

PandaStack vs E2B: Choosing an AI Sandbox Provider

A fair, technical breakdown of PandaStack and E2B across the dimensions that actually matter when you're choosing a Firecracker sandbox provider.

comparisonai-sandboxfirecrackerinfrastructuree2b
·9 min read·Ajay Kumar

PandaStack vs Modal: which for AI code execution?

Modal runs serverless functions you own; PandaStack runs untrusted agent code in per-task Firecracker microVMs. An honest, fact-based comparison.

comparisonmodalfirecrackerai-agentsserverlessmicrovm
·9 min read·Ajay Kumar

PandaStack vs Daytona for AI Sandboxes

Daytona is a dev-environment platform; PandaStack is a Firecracker microVM platform with managed Postgres and git app hosting. An honest, factual comparison.

comparisonsandboxesai-agentsfirecrackerdaytonaisolation
·9 min read·Ajay Kumar

Build a Code Interpreter with a Python Sandbox

Build a ChatGPT-style code interpreter that runs untrusted Python in its own microVM — capture stdout, read back plots, persist state across cells.

code-interpreterpythonsandboxtutorialai-agents
·9 min read·Ajay Kumar

Ephemeral CI Runners on MicroVMs: Fresh Isolation Per Job

Persistent CI runners leak state between jobs and expose your build host to untrusted fork PRs. A fresh microVM per job fixes both — and at under 50ms p50 per create, it's cheap.

CI/CDmicroVMssecurityDevOpsFirecracker
·10 min read·Ajay Kumar

How to run Firecracker on a Mac (Apple Silicon)

Firecracker is Linux/KVM-only, so it can't run natively on macOS. The fix: a lightweight Linux VM with Apple's nested virtualization. Here are the exact, working steps.

firecrackermacosapple-siliconlimahow-to