Agent Sandboxesagentsandboxes.org
Head-to-head

boat vs exe.dev

Answer in brief

Choose boat for long-lived EU-hosted VMs that an agent keeps for days, with SSH, Docker and a desktop; choose exe.dev for developers who want a fleet of persistent root VMs they and their agents reach over SSH, at a flat monthly price. boat uses Full VM, own kernel isolation; exe.dev uses VM (VMM per VM) isolation.

By the Agent Sandboxes editors · Updated

Key differences between boat and exe.dev

  • Isolation: boat uses Full VM, own kernel; exe.dev uses VM (VMM per VM).
  • Company headquarters: Boat is based in Paris, France; exe.dev is based in Berkeley, United States.
  • Session length: No cap (auto-stop 1 h default) (boat) versus No cap (exe.dev).
  • SDKs and interfaces: Only boat lists Python, JavaScript/TypeScript and REST API. Only exe.dev lists HTTPS API and MCP server.

What they have in common

  • Both are hosted platforms.
  • Both use full virtual machines.
  • Neither is open source.
  • Both support snapshots.
  • Both list CLI.

boat vs exe.dev at a glance

Attributeboatexe.dev
What it isPersistent Ubuntu VMs for AI agents in EU data centres, with SSH, Docker, disk snapshots, forking, a 60 fps virtual desktop and per-second billing from a $20/month plan.Persistent root VMs for people and their agents, driven entirely over SSH (or the same commands via HTTPS and MCP), with replicated NVMe storage, VM copies and flat-rate CPU/RAM pools in nine regions.
TypeHosted platformHosted platform
IsolationFull virtual machine per sandbox with its own kernel, disk and IP address; hypervisor not namedEach VM runs as its own VMM process inside a shared CPU/RAM pool; hypervisor not named
Open sourceNoNo
Self-host / BYOCNot documented / Not documentedNot documented / Yes
SDKsPython, JavaScript/TypeScript, CLI, REST APICLI (over SSH), HTTPS API, MCP server
Cold start (vendor claim)Not documentedAPI explorer: creating a VM takes "about a second" (vendor claim)
Max sessionNo fixed cap on paid plans: auto-stop defaults to 1 hour after start or resume, can be set up to 30 days or turned off; free trial is limited to 2 hours of auto-stopVMs are long-lived and persistent with no session limit; stopped standalone VMs keep their disk
PersistenceDisk is snapshotted every minute while running and on every stop; stopping pauses billing and keeps the disk for at least 14 days; boat fork clones a sandbox from a snapshot; running processes do not come back after a resumePersistent VM disks on local NVMe, streamed to other machines in the regional cluster for durability; cp copies a VM's disk and config; S3 backups (development preview) with incremental 1 MB chunks and 7-day minimum retention; no memory snapshots documented
Snapshots / pauseYes / YesYes / Not documented
GPUNo - "No size has a GPU" (pricing docs); the homepage says "Graphics run on the CPU"Not mentioned
NetworkingOutbound open by default (public IPv6 plus outbound IPv4, some sandboxes IPv6-only); inbound refused except SSH and boat ports, ports exposed via host <port> public URLs or ufw; no API-level network rules, and the default user has passwordless sudo so in-sandbox firewall rules can be removed by the agent; egress is not billedEgress all by default or integrations (blocks the public internet, keeps metadata and attached integrations); public or private HTTPS app URLs via an SNI/Host-routed TLS proxy and global load balancer; SSH with public-key auth only; an LLM gateway adds provider keys outside the VM
PricingPer second while running: small 2 vCPU/4 GB $0.018/h, default 4 vCPU/8 GB $0.036/h, large 8 vCPU/16 GB $0.072/h, xlarge 16 vCPU/32 GB $0.200/h ($100 plan or higher). Monthly plans of $20 (100 concurrent sandboxes, 555 h of default VM time), $100 (300, 2,777 h), $500 (1,000, 13,888 h) and $2,000 (2,000, 55,555 h); included time does not roll over. Saved snapshots beyond the plan allowance $0.056/day each; extra starts $0.03-$0.07 eachPersonal: $15/month for a 2 vCPU/4 GiB pool, $35 (4/8), $75 (8/16), $155 (16/32), up to 50 VMs, 100 GiB disk, 200 GiB bandwidth. Work: $75/month per team ($37.50 for the first 3 months) including 2 vCPU/4 GiB, extra capacity $0.105 per 2 vCPU/4 GiB unit-hour, pools of 2-512 vCPUs, 1,000 VMs per pool. Standalone VMs metered per second at the same unit rate ($0.0525/h for 1 vCPU/2 GiB to $0.84/h for 16 vCPU/32 GiB). Enterprise custom with dedicated hardware and AWS/GCP VPC
Free tier7-day free trial (card required) with 25 compute hours, 2 concurrent sandboxes and auto-stop capped at 2 hours; no $0 plan7-day trial of the Personal plan, no card required when linking a paid ChatGPT subscription; no permanent free tier
ComplianceSOC 2 listed as "in progress", not yet certified; zero-data-retention option; measured uptime 99.95%Not documented
RegionsGermany, Finland and France only (no US or Asia regions); snapshot copies may be stored outside the EULos Angeles, New York, Dallas, Frankfurt, Tokyo, Sydney, Singapore, London (Oregon closed to new accounts); the account "lobby" server is in the United States
Company headquartersParis, FranceBerkeley, California, United States
Good fit forLong-lived EU-hosted VMs that an agent keeps for days, with SSH, Docker and a desktopDevelopers who want a fleet of persistent root VMs they and their agents reach over SSH, at a flat monthly price

Verified November 14, 2026 from each provider’s documentation. Cold-start figures are vendor claims, not our measurements.

Which should you choose?

Reasons to choose boat

  • You want a persistent full VM with SSH, Docker and root that an agent can keep for days or weeks
  • You need EU-only compute (Germany, Finland, France) for sandbox workloads
  • You want predictable per-second VM pricing with a low monthly minimum and no egress charges
  • You want a streamed virtual desktop without paying for a GPU

Reasons to choose exe.dev

  • You want many small persistent VMs for a flat monthly price rather than per-second metering
  • You and your agents work over SSH and want the same commands via HTTPS or MCP
  • You need regions in Asia-Pacific and Europe as well as the US
  • You want app URLs and an LLM key gateway without running a proxy yourself

Trade-offs to check first

  • boat: No US or Asian regions, and snapshot copies may be stored outside the EU
  • boat: SOC 2 is "in progress", not certified
  • exe.dev: Hypervisor and compliance are not documented
  • exe.dev: Language SDKs are not documented; the API is one POST endpoint wrapping SSH commands with a 30-second timeout and no stdin

Both are worth piloting with your own image and region. See the full boat profile and exe.dev profile, or the complete comparison.

More comparisons

Frequently asked questions

Is boat or exe.dev better for AI agents?
Neither is better for every workload. boat suits long-lived EU-hosted VMs that an agent keeps for days, with SSH, Docker and a desktop. exe.dev suits developers who want a fleet of persistent root VMs they and their agents reach over SSH, at a flat monthly price.
What is the difference between boat and exe.dev?
boat uses Full VM, own kernel; exe.dev uses VM (VMM per VM). Boat is based in Paris, France; exe.dev is based in Berkeley, United States. Session length: No cap (auto-stop 1 h default) (boat) versus No cap (exe.dev). Only boat lists Python, JavaScript/TypeScript and REST API. Only exe.dev lists HTTPS API and MCP server.
Which is open source, boat or exe.dev?
Neither is open source.
How do boat and exe.dev isolate code?
boat: Full virtual machine per sandbox with its own kernel, disk and IP address; hypervisor not named. exe.dev: Each VM runs as its own VMM process inside a shared CPU/RAM pool; hypervisor not named.
How does boat pricing compare with exe.dev?
boat: Per second while running: small 2 vCPU/4 GB $0.018/h, default 4 vCPU/8 GB $0.036/h, large 8 vCPU/16 GB $0.072/h, xlarge 16 vCPU/32 GB $0.200/h ($100 plan or higher). Monthly plans of $20 (100 concurrent sandboxes, 555 h of default VM time), $100 (300, 2,777 h), $500 (1,000, 13,888 h) and $2,000 (2,000, 55,555 h); included time does not roll over. Saved snapshots beyond the plan allowance $0.056/day each; extra starts $0.03-$0.07 each. exe.dev: Personal: $15/month for a 2 vCPU/4 GiB pool, $35 (4/8), $75 (8/16), $155 (16/32), up to 50 VMs, 100 GiB disk, 200 GiB bandwidth. Work: $75/month per team ($37.50 for the first 3 months) including 2 vCPU/4 GiB, extra capacity $0.105 per 2 vCPU/4 GiB unit-hour, pools of 2-512 vCPUs, 1,000 VMs per pool. Standalone VMs metered per second at the same unit rate ($0.0525/h for 1 vCPU/2 GiB to $0.84/h for 16 vCPU/32 GiB). Enterprise custom with dedicated hardware and AWS/GCP VPC. Rates change, so check the boat and exe.dev pricing pages before deciding.
Do boat and exe.dev support GPUs?
boat: No - "No size has a GPU" (pricing docs); the homepage says "Graphics run on the CPU". exe.dev: Not mentioned.
How long can sessions run on boat and exe.dev?
boat: No fixed cap on paid plans: auto-stop defaults to 1 hour after start or resume, can be set up to 30 days or turned off; free trial is limited to 2 hours of auto-stop. exe.dev: VMs are long-lived and persistent with no session limit; stopped standalone VMs keep their disk.
Do boat and exe.dev support snapshots or pause and resume?
boat: snapshots yes, pause and resume yes. exe.dev: snapshots yes, pause and resume not documented.

Sources

  1. boat.dev
  2. docs.boat.dev
  3. docs.boat.dev/pricing
  4. docs.boat.dev/security
  5. exe.dev
  6. exe.dev/docs
  7. exe.dev/pricing
  8. exe.dev/security

Check before you rely on it. Products change quickly, and this page reflects public documentation as of November 14, 2026. Confirm anything that matters in the provider’s own documentation.

Cite this page

Agent Sandboxes. (2026). boat vs exe.dev. agentsandboxes.org. Last reviewed November 14, 2026. https://agentsandboxes.org/compare/boat-vs-exe-dev/