Project
E2B is an open-source platform providing isolated cloud sandboxes (microVMs) for safely running AI-generated or untrusted code used by AI agents.
plimsoll's docs say E2B, Modal, Daytona, Vercel, Cloudflare and Northflank never report which isolation tier a run got. A dev.to writer verified two of them. The other four rest on plimsoll's reading alone.
Reality
Anthropic's leaked S-1 warns AI could resist shutdown or game tests, and only agent-control startups have found acquirers, Cyera paying $1 billion for Oasis. Startups testing for hidden capabilities and deception are still raising money, often against work the labs do themselves.
Reality
Misha, who works on Gobare, found in public docs that OpenAI may delete a sandbox idle for an hour and Gobare pauses one after five minutes. Perplexity promises nothing between responses, so jobs that wait on a human or serve a preview have to fit one of those clocks.
Reality
OpenAI's Agents API, in public beta since September 10th, runs the Codex harness on OpenAI's own infrastructure. The documentation says data residency is US-only and Zero Data Retention is unsupported, whichever sandbox you pick.
Perspective Coverage
6 publishersReality
Baseten's case for owning the agent runtime is that latency and idle compute accumulate at every boundary an agent crosses between the model call and its sandbox, on numbers Blaxel reported itself.
Reality
Devin Outposts on Modal moves code execution into infrastructure the customer runs, which makes a sandbox vendor, not a model vendor, the thing platform teams must procure and secure.
Reality
Durable execution restores orchestration state. It cannot untake a payment, a send, or a ticket, and no ranked feature table for AutoGen, CrewAI, LangGraph or Flowise closes that gap.
Reality