Runloop vs Instabox
Both give each AI agent its own Linux VM. Runloop is a paid platform built to run fleets of devboxes, with network rules and Dockerfile images, while Instabox is a free invite-only beta that launched on 2026-10-14 with one machine size and 5 machines per account.
The companies and products
Runloop
Runloop is a US platform of sandboxes, called devboxes, for building, running and testing AI coding agents.
You get Linux devboxes built from Dockerfile-style blueprints, disk snapshots, HTTPS tunnels, agent gateways that hide API keys, and Axons, event streams that drive agents such as Claude Code. Each devbox runs in a micro-VM on Runloop's own bare-metal hypervisor, with a container layer inside. It is built for teams shipping coding agents, plus evaluation and RL fine-tuning work on the Enterprise plan.
- Compliance
- SOC 2 Type 2
- Architectures
- x86_64 and arm64 base blueprints
- Own-cloud deploy
- Deploy to VPC on AWS, GCP and Azure (Enterprise)
- Regions
- Not documented or selectable
- Company
- Runloop AI, Inc.
Instabox
Instabox, made by InsForge, gives each AI agent its own Linux computer in the cloud. It launched on 2026-10-14 as an invite-only beta.
Each Instabox machine is a Firecracker microVM with its own kernel, root and Docker, started from one of four templates (agent-browser, universal, herdr or orca) or from your own snapshot. Every machine is 4 vCPU / 8 GiB with 20 GB of storage, and you drive it from a CLI, a TypeScript SDK or an HTTP API, with SSH, mosh, public port URLs and a desktop for computer use. It is aimed at developers who want a cloud box for a coding agent.
- Isolation
- Firecracker microVM per machine
- Machines per account
- 5, in any state: paused and stopped ones count
- Company
- InsForge AI, Inc.
Which use cases each one fits
For each use case, Battleships prices every sandbox provider on the same workload and sorts them from the cheapest monthly bill up. “20th cheapest of 367” means 19 of the other 366 providers run that workload, with every feature it needs, for less. “With limits” means the provider runs it but misses something, so it is listed after every full match. Open a use case for its whole ranking and what each provider misses.
| Use case and its workload | Runloop: price rank | Instabox: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Runloop fits a software factory fully; Instabox has one 4 vCPU / 8 GiB size and forks only stopped machines, while boat forks a running sandbox and goes up to 16 vCPU / 32 GB. | 20th cheapest of 367 $8,152 a month | No published price | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Runloop can run a devbox all month with an idle policy, Instabox pauses a machine after 30 idle minutes unless you turn that off, and boat has no session cap on paid plans. | 32nd cheapest of 366 $10,194 a month | No published price | 5th cheapest of 366 $657 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month | 44th cheapest of 345 $525 a month | No published price | 186th of 345, with limits $2,000 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Instabox allows 5 machines per account, paused and stopped ones included, so it cannot give a sandbox to each of many users; Runloop and boat both fit. | 26th cheapest of 361 $3,301 a month | No published price | Cheapest of 361 $209 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month Runloop ranks 4th for RL rollouts: it starts large waves with no published start limits, which Instabox's 5-machine cap and boat's start limits do not match. | 4th cheapest of 360 $15,922 a month | No published price | 34th of 360, with limits $2,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month Instabox's 5-machine cap limits how many evals run at the same time; Runloop and boat both run evals in parallel. | 81st cheapest of 364 $2,562 a month | No published price | 10th cheapest of 364 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI that builds Android apps or VM images needs /dev/kvm, which neither Runloop nor Instabox documents and boat exposes. | 121st cheapest of 377 $1,554 a month | No published price | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Instabox works well as a free cloud dev box with SSH and mosh during the beta; Runloop has no public IP or raw TCP, and boat adds a published price and plans. | 113th cheapest of 368 $410 a month | No published price | 18th cheapest of 368 $26 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month All three have a desktop an agent can control; Instabox can share a view or control link, and boat streams its desktop at 60fps. | 39th cheapest of 369 $2,306 a month | No published price | 6th cheapest of 369 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 40th cheapest of 367 $1,153 a month | No published price | 7th cheapest of 367 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 68th cheapest of 346 $781 a month | No published price | 6th cheapest of 346 $90 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 266th of 338, with limits $15,611 a month | No published price | 71st of 338, with limits $1,800 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 10th cheapest of 360 $770 a month | No published price | 2nd cheapest of 360 $200 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Can't run it | No published price | Can't run it |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Can't run it | No published price | Can't run it |
Key features
| Feature | Runloop | Instabox | boat |
|---|---|---|---|
| Isolation | Micro-VM on a custom bare-metal hypervisor, plus a container layer | Firecracker microVM with its own kernel and root | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Machine sizes | Several sizes, such as 2 vCPU / 4 GiB and 4 vCPU / 8 GiB; disk up to 64 GiB | One size for everyone: 4 vCPU / 8 GiB with 20 GB storage; other sizes are refused | Several sizes, up to 8 vCPU / 16 GB on the $20 plan and 16 vCPU / 32 GB on $100 and above |
| CPU benchmark (4 vCPU / 8 GB) | 8.29 runs/s | Not measured | 26.69 runs/s |
| Docker inside | Yes, on the Docker-in-Docker blueprints, as root | Docker and Docker Compose run inside | Docker and Compose run inside, with root and systemd |
| Nested virtualization | Not documented; Docker-in-Docker only | Not documented | Yes, /dev/kvm for Android emulators and VMs |
| Images and CPU type | Blueprints built from Dockerfiles, plus disk snapshots; x86_64 and arm64 | Four templates or your own snapshot; x86_64 templates | Templates from named snapshots, no Dockerfile builds; x86_64 only |
| Keeping files | Disk kept through suspend (Pro plan) or disk snapshots you take; shutdown ends the devbox | Snapshots saved by hand, up to 10; saving stops a running machine first unless the server allows a live save | Disk saved every minute and on stop, on every plan; resume with the same disk |
| Fork | New devboxes from disk snapshots | Fork copies a stopped machine only | Fork a running sandbox with its disk |
| Sleep and wake | Suspend after idle, wake on an HTTP request to the tunnel (Pro plan) | Pause keeps memory and running programs; resume usually takes about a second; a visit to a port URL does not wake it | Stop keeps the disk; start boots the machine again |
| Inbound networking | One HTTPS tunnel per devbox, open or bearer token; SSH through a TLS proxy; no public IP | HTTPS on up to 16 ports, open to anyone with the URL; offline while the machine is paused | HTTPS on up to 50 ports, token-protected by default; raw TCP; dedicated IPv6 or IPv4 |
| SSH | SSH through a TLS proxy | SSH gateway with short-lived certificates, paste-anywhere SSH tokens and mosh | SSH into every sandbox |
| Egress rules | Hostname allowlist with wildcards, or block all | Not documented | Open internet, no provider-side allowlist |
| Keeping API keys out of the sandbox | Agent gateways for any API endpoint with bearer, header or basic auth | Vault writes your secrets into each machine as environment variables or files | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when one runs out |
| Where it runs | Regions not documented; Deploy to VPC on AWS, GCP or Azure (Enterprise) | Regions not published | EU only (Germany, Finland, France), EU data residency |
Every feature Battleships tracks (43)
| Feature | Runloop | Instabox | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No | Not published | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | Yes | Yes | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | Yes | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | No | Yes |
| Memory fork | No | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No |
| Wake on request | Yes | No | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Not published | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | Not published | Yes |
| Agent harness API | Yes | Not published | Yes |
| MCP server | Yes | Not published | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | Yes | Not published | No |
| Self-hosting | No | Not published | No |
| BYOC | Yes | Not published | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Yes | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | Yes | No | No |
| SOC 2 | Yes | Not published | No |
| HIPAA | Not published | Not published | No |
| EU data residency | No | Not published | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
On the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB (run 36498291449, 2026-09-29), boat scored 26.69 runs per second and Runloop 8.29, about 3.2 times apart. Instabox has no comparable measurement, so this page makes no CPU claim about it. Instabox says a new machine's shell is ready in under a second; that has not been measured either.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Instabox has no published run in this suite yet, so there is no like-for-like number to compare.
Pricing in five scenarios
Each bill is priced from the providers' public price lists by the open Battleships engine, with the cheapest plan that runs the scenario.
| Scenario | Runloop, a month | Instabox, a month | boat, a month |
|---|---|---|---|
| One coding agent, workdays 4 vCPU / 8 GB, 50 GB disk, 8 hours a day, 22 days a month, files kept between days | $113 · Basic | No published price | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $429 · Basic | No published price | $26 · $20/mo |
| 50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside | $5,268 · Basic | No published price | $317 · $20/mo × 3 seats |
| Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once | $1,441 · Basic | No published price | $200 · $100/mo × 2 seats |
| 1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month | $3,184 · Basic | No published price | $2,000 · $2000/mo · with limits |
Runloop: Runloop bills per second for the CPU and memory you allocate, and bills disk for the devbox's whole life. Basic has no plan fee; Pro adds $250 a month that is not usage credit and unlocks suspend and resume.
Instabox: Instabox is free during the beta, with 5 free machines per user, and its pricing page says it is free until they figure it out. No price is published, so no bill can be compared with Runloop's yet.
Instabox: Plans start at $20 a month and the whole fee is usage credit, billed per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Instabox allows 5 machines per account, paused and stopped ones included, so the 50-agent and user-sandbox scenarios do not fit it today, and with no published rate none of our scenarios can be priced on it. Every Instabox machine is 4 vCPU / 8 GiB with 20 GB storage, and an API exec call runs at most 10 minutes, with 4 at once. Runloop fits all five scenarios; its fixed lifetime tops out at 48 hours unless an idle policy replaces it, its disk tops out at 64 GiB, and it publishes no egress price. boat's limit that bites is start rate: even the $2,000 plan queues bursts above 90 starts a minute, so 1,000 jobs at once does not fit.
| Scenario | Runloop | Instabox | boat |
|---|---|---|---|
| One coding agent, workdays |
|
| None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel |
|
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Runloop when
you need many devboxes at once today, large bursts of short jobs, hostname allowlists, arm64, Dockerfile images or devboxes inside your own cloud.
- Ready for a fleet today. Runloop fits all five of our scenarios, including 50 agents in parallel and 1,000 short jobs at once, with published per-second rates.
- Lock down the network. Useful if a sandbox must only reach a fixed list of hosts: Runloop allows listed hostnames, with wildcards, or blocks everything.
- Dockerfiles, arm64 and your own cloud. Runloop builds images from Dockerfiles, offers arm64, and on Enterprise runs devboxes inside your own AWS, GCP or Azure account.
Use Instabox when
you want to try a few free 4 vCPU / 8 GiB agent machines during its invite-only beta, with memory pause and mosh.
- Free during the beta. While the invite-only beta lasts, every account can run 5 machines of 4 vCPU / 8 GiB for free.
- Pause with memory. A paused machine keeps its memory and running programs, and its docs say it usually resumes in about a second.
- SSH gateway with mosh. Its SSH gateway relays mosh and gives paste-anywhere SSH tokens, so a session survives sleep and network changes.
Where boat fits
If your agents do real work for hours, with installs, builds, Docker and emulators, look at boat. It gives each agent a full VM with /dev/kvm, keeps its disk on every plan, and on the same CPU benchmark ran 26.69 runs per second against Runloop's 8.29; Instabox has not been measured.
Emulators and VMs inside
Neither Runloop nor Instabox documents /dev/kvm, so an Android emulator or a VM inside the sandbox does not start. Runloop offers Docker-in-Docker only. boat exposes /dev/kvm in every sandbox.
Branch work without stopping
On Instabox a fork copies a stopped machine, and saving a snapshot stops a running one first. On Runloop a devbox is gone after shutdown unless you pay for Pro suspend or write snapshot code. boat forks a running sandbox and saves its disk every minute.
Private ports and raw TCP
Instabox port URLs are open to anyone who finds them and go offline while paused. Runloop gives one HTTPS tunnel and no public IP. boat serves up to 50 ports with a token by default, plus raw TCP and a dedicated IP.
Use boat when your agents need a full VM with /dev/kvm, forks of running work, private port URLs and files kept on every plan, on CPUs measured about three times faster than Runloop's. Compare it one to one: boat vs Runloop and boat vs Instabox.
Questions people ask
Is Runloop cheaper than Instabox?
It can't be compared yet. Instabox is free during the beta, with 5 free machines per user, and publishes no price, so there is no bill to set against Runloop's. On Runloop, one coding agent on workdays comes to $113 a month in our scenario.
Which is faster, Runloop or Instabox?
Only Runloop has been measured: 8.29 runs per second on the Node.js build-and-test benchmark at 4 vCPU / 8 GB, against 26.69 for boat. Instabox's CPU speed has not been benchmarked, so we make no claim either way.
Does Instabox start a machine in under a second?
Instabox says you are in a new machine's shell in under a second. Its docs say a paused machine usually resumes in about a second. Neither has been measured here.
Can Runloop and Instabox run Docker?
Yes. Runloop runs Docker as root on its Docker-in-Docker blueprints, and Instabox runs Docker and Docker Compose inside each machine. boat runs Docker and Compose too, with root and systemd.
Can I run Android emulators or VMs inside Runloop or Instabox?
Neither documents nested virtualization or /dev/kvm. boat exposes /dev/kvm, so Android emulators and VMs run inside a sandbox.
How many machines can I run on Instabox?
5 per account, and paused and stopped machines count. Every machine is 4 vCPU / 8 GiB with 20 GB storage. Runloop publishes no concurrency cap for its paid plans.
Try boat
Install the CLI, then run boat new.
7-day free trial