ProductApr 22, 20265 min read

What is Podflare? (And no, we're not Cloudflare — different company, different product)

Podflare is a hardware-isolated cloud sandbox built for AI agents. Not Cloudflare. Here's what we actually do: 80 ms fork(), persistent Python REPL, 5 regions, Podflare Pod microVMs.

Robel TegegnePodflare, founder

If you typed "podflare" into Google and ended up on Cloudflare’s homepage, you are not the first. The names are one letter apart, Cloudflare is twenty years older, and Google’s knowledge graph defaults to the entity it already knows. This post is the direct answer.

Podflare is a hardware-isolated cloud sandbox for AI agents. We are not part of Cloudflare, affiliated with Cloudflare, or a Cloudflare product. We are a separate, independent company building a separate product. The similarity of the name is a coincidence (and, in retrospect, a product of wanting a short four-syllable domain that was still available).

What Podflare actually does

An AI agent that writes and runs code needs somewhere safe to execute it. Your own servers are the wrong place — one prompt-injected rm -rf away from disaster. Serverless functions (Lambda, Cloud Run) are too restrictive — no persistent state between calls, no full filesystem access, time limits in the seconds. Docker containers share a kernel with the host, and the last few years of kernel CVEs have shown that’s not a strong enough boundary when the code was written by an LLM responding to untrusted user input.

Podflare is the right place. Every time your agent calls Sandbox(), we hand it a brand-new, dedicated Linux microVM:

  • Hardware-isolated. Each VM is a Podflare Pod — a dedicated KVM-backed microVM, the same category of isolation AWS Lambda is built on. The security boundary is the hypervisor, not the kernel. Container-escape CVEs don’t apply.
  • Fast. Create + exec + close round-trips at ~190 ms p50 from a residential laptop (p99 under 240 ms), ~43 ms p50 from an agent running in a nearby cloud region.
  • Persistent. Each sandbox keeps a live Python REPL across run_code calls. When your agent imports pandas on turn 3 and uses it on turn 7, globals() still has the import.
  • Forkable. parent.fork(n=5) spawns 5 children from the parent’s exact mid-flight state in ~80 ms. The primitive tree-of-thought and multi-attempt code synthesis patterns actually want.
  • Multi-region. 5 production regions today — us-west, us-central, us-east, eu, sg — with automatic haversine routing from the edge and failover on origin 5xx.

The one-paragraph architecture

When you call Sandbox(), the request hits a Cloudflare Worker (yes, we use Cloudflare — as a CDN, like everyone — but we are not Cloudflare) that haversine-routes to the nearest region. That region runs hostd, our Rust-based control plane, which pulls a pre-booted Podflare Pod microVM off a warm pool (6 ms server-side), assigns it to your org, and returns the sandbox ID. Your run_code calls stream over a vsock binary protocol inside the guest — no TCP, no TLS inside the VM, which is why our hot-exec is 46 ms p50 vs E2B’s 180 ms. The full benchmark post has the numbers.

What you’d use Podflare for

The common patterns we see:

  • Code-execution tool for an AI agent. Claude / GPT / Gemini / Llama emits Python as a tool_use or function call; your app routes it to Podflare; the stdout comes back; the agent uses it on the next turn.
  • Tree-of-thought solver. Load an expensive context once (a large DataFrame, a trained model), then fork(n=5) to try five strategies in parallel. Pick the winner, merge it back, destroy the losers.
  • Long-running agent sessions. Create a persistent=True sandbox, train a model, load a dataset, then freeze it to a Space when idle. Resume hours or days later with the same Python process still holding the same variables.
  • Drop-in replacement for OpenAI’s code interpreter — except you control the infrastructure, the data doesn’t go to OpenAI, and your bill isn’t tied to a model-tier quota.

Pricing

Free tier includes a $200 starter credit, 10 concurrent sandboxes, 1 GB RAM per sandbox, 5 regions, and the full SDK. Pro is $29/month (50 concurrent, 4 GB), Scale is $200/month (500 concurrent, 16 GB), Enterprise is custom with SOC-2-roadmap access, dedicated hostd pools, and data residency. Full breakdown on the pricing page.

How to try it in 60 seconds

pip install podflare   # or: npm install podflare
export PODFLARE_API_KEY=pf_live_...   # mint one at dashboard.podflare.ai/keys

python -c "
from podflare import Sandbox
with Sandbox() as sb:
    out = sb.run_code('print(2 + 2)')
    print(out.stdout)"  # 4

That’s the whole onboarding. Real compute, real network, real hardware isolation, real sub-200 ms cold start. Create a free account and run the above.

Related reading

#podflare#what is podflare#podflare vs cloudflare#cloud sandbox#ai agent sandbox#pod microvm

Frequently asked questions

+Is Podflare part of Cloudflare?

No. Podflare and Cloudflare are completely separate companies with different products. Cloudflare is a CDN and edge networking provider. Podflare is a cloud sandbox platform for AI agents — we give each LLM-generated code execution its own hardware-isolated Linux microVM. The names are similar; the products, teams, and funding are not.

+What does Podflare actually do?

Podflare gives you an HTTP API that returns a fresh, disposable Linux VM in ~190 ms. Your AI agent pushes code to it (Python, Bash, anything), captures stdout, and destroys the VM when done. The VM is a hardware-isolated Podflare Pod microVM — the same category of isolation AWS Lambda uses under the hood — which means LLM-generated code can't escape into your host.

+How is Podflare different from E2B, Daytona, or Blaxel?

All four platforms compete in the same category. Podflare wins head-to-head benchmarks at every latency percentile (p50 3x faster than E2B, 4.7x vs Daytona), exposes a unique fork(n) primitive for tree-of-thought patterns, supports persistent VM-memory Spaces for cross-session agent state, and operates 5 regions with Cloudflare-edge haversine routing.

+Who is Podflare for?

Anyone building an AI agent that needs to run LLM-generated code. The most common users are companies shipping agents that use OpenAI's Agents SDK, Anthropic's tool_use protocol, Vercel AI SDK, LangChain, Gemini, or MCP. If your agent calls a code-execution tool, Podflare is what plugs in behind it.

+Is Podflare open source?

The platform itself is proprietary, but our SDKs are MIT-licensed and our benchmark harness is public. If you need self-hostable sandbox infrastructure and can accept Apache-2.0 terms, E2B is the closest competitor. If you're comfortable with AGPL, Daytona is an option.

Keep reading

Ship an AI agent on Podflare in under a minute.

Hardware-isolated microVM per sandbox, ~190 ms round-trip, 80 ms fork(), full Python REPL persistence. Free tier includes $200 credit.

Get started free
What is Podflare? (And no, we're not Cloudflare — different company, different product) — Podflare