Skip to content

Arena

Agent Sandboxes & Code Execution arenaAgent Sandboxes & Code Execution

Isolated cloud execution environments where AI agents safely run untrusted code — judged on provisioning speed, isolation and network policy, snapshot/restore, concurrency at agent scale, and per-second economics.

51 user stories · 408 judged cells · updated 2026-09-16 · Evidence as of 2026-09-16

Buyer checklist →Procurement report →

Leaderboard — every product ranked by evidenceLeaderboard

Rank by

Best by user type — persona-weighted winnersBest by user type

Per persona, the product with the highest persona-weighted coverage over just that persona's stories — not the same ranking as the overall PA Score leaderboard above.

Best for developer

E2B logo

E2B

61/100

Runner-up: Daytona logo Daytona (58/100)

15 developer stories scored

Best for platform-engineer

E2B logo

E2B

55/100

Runner-up: Modal Sandboxes logo Modal Sandboxes (43/100)

4 platform-engineer stories scored

Best for ai-native

E2B logo

E2B

39/100

Runner-up: Daytona logo Daytona (34/100)

32 ai-native stories scored

Story matrix — every product × every judged storyStory matrix

51/51 stories shown · legend

Agenticness — how well agents can access and operate the productAgenticness

Agent access

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Agenticness — how well agents can access and operate the productPoint an agent at llms.txt or agent-oriented docsai-native
fullT
9/10
fullT
9/10
fullT
8/10
partialT
6/10
fullT
8/10
fullT
9/10
fullT
9/10
fullT
9/10
Agenticness — how well agents can access and operate the productRun the product headlessly / in CI for automationai-native
fullC
8/10
fullT
8/10
fullT
8/10
partialX
6/10
fullT
8/10
fullC
8/10
partialT
6/10
fullT
8/10
Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their toolsai-native
n/a
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
partialT
5/10
none
0/10
Agenticness — how well agents can access and operate the productConnect an agent via an official MCP serverai-native
none
0/10
fullT
8/10
none
0/10
none
0/10
none
0/10
fullT
7/10
fullT
7/10
none
0/10
Agenticness — how well agents can access and operate the productUse an official CLIai-native
fullT
8/10
fullT
8/10
fullT
8/10
none
0/10
fullC
7/10
fullT
8/10
fullT
7/10
fullT
9/10
Agenticness — how well agents can access and operate the productDrive the product through a documented public APIai-native
fullT
8/10
fullT
9/10
fullT
8/10
fullT
8/10
fullT
9/10
fullT
8/10
partialT
5/10
fullT
8/10
Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agentai-native
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
partialC
6/10
none
0/10
fullC
8/10
Agenticness — how well agents can access and operate the productBuild against official SDKsai-native
fullT
8/10
fullT
9/10
fullX
8/10
fullC
8/10
fullC
7/10
partialC
6/10
partialC
3/10
fullT
8/10
Agenticness — how well agents can access and operate the productSubscribe to events via webhooksai-native
fullC
6/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
fullC
7/10

Agentic features

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Agenticness — how well agents can access and operate the productGet AI-generated insights and suggestions from my data inside the productai-native
n/a
n/a
n/a
n/a
n/a
n/a
n/a
none
0/10
Agenticness — how well agents can access and operate the productSet up automations that run autonomously in the backgroundai-native
partialC
5/10
none
0/10
partialX
6/10
partialX
6/10
partialC
5/10
partialC
7/10
partialC
5/10
fullC
8/10
Agenticness — how well agents can access and operate the productDelegate tasks to a built-in AI assistant inside the productai-native
n/a
n/a
n/a
n/a
n/a
n/a
n/a
none
0/10
Agenticness — how well agents can access and operate the productOperate the product with natural-language commandsai-native
partialC
5/10
partialT
6/10
none
0/10
none
0/10
none
0/10
partialT
6/10
partialT
6/10
partialC
6/10

Api quality

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examplesai-native
none
0/10
partialT
3/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent)ai-native
none
0/10
fullT
9/10
none
0/10
partialT
4/10
fullT
9/10
none
0/10
none
0/10
none
0/10
Agenticness — how well agents can access and operate the productTest against a sandbox environment without touching production dataai-native
fullC
8/10
fullT
8/10
fullT
7/10
fullX
7/10
fullC
8/10
fullC
8/10
fullC
7/10
none
0/10
Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policyai-native
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10

Automation depth — how much of the product can run unattendedAutomation depth

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Automation depth — how much of the product can run unattendedPerform bulk operations across many items at onceai-native
partialC
5/10
partialC
4/10
partialX
6/10
partialX
5/10
none
0/10
partialC
6/10
partialC
6/10
partialC
4/10
Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on eventsai-native
partialC
3/10
none
0/10
none
0/10
partialC
4/10
none
0/10
partialC
4/10
none
0/10
partialC
6/10
Automation depth — how much of the product can run unattendedSchedule recurring jobs or workflowsai-native
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
fullC
8/10
Automation depth — how much of the product can run unattendedVersion, review, and roll back my automationsai-native
n/a
none
0/10
none
0/10
partialC
4/10
none
0/10
partialC
4/10
none
0/10
none
0/10

Capabilities hardware — stories about capabilities hardware in this arenaCapabilities hardware

Agent workloads

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Capabilities hardware — stories about capabilities hardware in this arenaRun coding agents like Claude Code or Codex inside the sandbox following the vendor's own recipeai-native
fullC
8/10
none
0/10
none
0/10
none
0/10
partialC
6/10
partialC
5/10
none
0/10
fullC
8/10

Workloads

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Capabilities hardware — stories about capabilities hardware in this arenaRun a headless browser or full desktop environment inside the sandboxdeveloper
partialC
6/10
fullC
8/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
fullC
7/10
Capabilities hardware — stories about capabilities hardware in this arenaAttach GPUs to sandboxed workloadsdeveloper
none
0/10
fullC
8/10
fullX
8/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10

Code execution — stories about code execution in this arenaCode execution

Files

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Code execution — stories about code execution in this arenaRead, write, upload, and download files in the sandbox filesystem via the SDKdeveloper
fullC
8/10
partialC
5/10
fullT
8/10
fullC
9/10
partialC
6/10
partialC
4/10
none
0/10
none
0/10

Runtimes

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Code execution — stories about code execution in this arenaDefine custom sandbox templates or bring my own container imagedeveloper
fullC
9/10
fullC
8/10
fullX
8/10
none
0/10
fullC
9/10
fullC
8/10
partialC
6/10
partialC
6/10
Code execution — stories about code execution in this arenaExecute code in multiple language runtimes (Python, JavaScript, and more) and get rich results backdeveloper
fullC
8/10
fullC
8/10
partialC
6/10
fullC
8/10
fullC
7/10
partialC
5/10
partialC
3/10
none
0/10

Untrusted code

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Code execution — stories about code execution in this arenaExecute untrusted, AI-generated code without risking my own infrastructuredeveloper
fullC
9/10
fullT
9/10
fullT
8/10
partialX
7/10
fullC
9/10
fullT
8/10
fullC
7/10
partialT
5/10
Code execution — stories about code execution in this arenaRun arbitrary shell commands and install packages inside the sandboxdeveloper
fullC
9/10
fullC
9/10
fullT
9/10
fullC
9/10
fullC
8/10
fullC
7/10
partialC
5/10
none
0/10

Dev experience — day-to-day developer experience — setup friction, docs, debugging, iteration speedDev experience

Agent lifecycle

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Dev experience — day-to-day developer experience — setup friction, docs, debugging, iteration speedMy agent can provision its own sandbox, execute code, read the results, and tear it down — end to end without a humanai-native
fullC
9/10
fullT
9/10
fullT
8/10
partialX
7/10
fullC
8/10
fullC
8/10
fullC
8/10
partialC
6/10

Isolation security — stories about isolation security in this arenaIsolation security

Isolation

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Isolation security — stories about isolation security in this arenaRely on a documented hard isolation boundary (microVM or equivalent) between sandboxes and my systemsplatform-engineer
fullC
8/10
partialC
6/10
partialT
5/10
fullX
7/10
partialC
6/10
partialT
3/10
none
0/10
none
0/10
Isolation security — stories about isolation security in this arenaGive an agent a sandbox where host secrets and credentials are unreachable by the code it runsai-native
fullC
7/10
fullT
8/10
partialT
5/10
partialX
6/10
fullC
8/10
partialC
6/10
partialC
5/10
partialC
6/10

Network policy

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Isolation security — stories about isolation security in this arenaRestrict or allow the sandbox's network egress with explicit policyplatform-engineer
fullC
8/10
fullC
8/10
partialT
5/10
disputedD
3/10
none
0/10
none
0/10
none
0/10
none
0/10

Openness — open source, data portability, and self-hosting storiesOpenness

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Openness — open source, data portability, and self-hosting storiesDo everything through the API that I can do in the UIai-native
partialT
6/10
partialT
7/10
partialT
6/10
fullX
7/10
fullT
7/10
partialT
6/10
partialT
5/10
partialT
6/10
Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leaveai-native
partialC
4/10
partialC
4/10
none
0/10
partialC
4/10
none
0/10
partialC
4/10
none
0/10
none
0/10
Openness — open source, data portability, and self-hosting storiesRead the product's source under an open licenseai-native
fullC
7/10
disputedD
4/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
Openness — open source, data portability, and self-hosting storiesSelf-host the core productai-native
partialC
6/10
disputedD
4/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10

Performance scale — stories about performance scale in this arenaPerformance scale

Latency

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Performance scale — stories about performance scale in this arenaStart sandboxes with documented sub-second-to-few-second cold startsdeveloper
none
0/10
partialC
6/10
partialC
4/10
none
0/10
none
0/10
partialC
6/10
partialC
6/10
none
0/10

Scale

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Performance scale — stories about performance scale in this arenaRun large concurrent fleets of sandboxes with documented concurrency limitsplatform-engineer
partialC
6/10
none
0/10
partialX
5/10
none
0/10
partialC
3/10
partialC
5/10
partialC
3/10
none
0/10
Performance scale — stories about performance scale in this arenaKeep a sandbox session running for hours or days for long agent tasksdeveloper
partialC
7/10
none
0/10
partialX
5/10
disputedD
5/10
partialC
6/10
fullC
8/10
partialC
5/10
partialT
5/10

Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits

Pricing

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payStart building with a free tier or included credits without talking to salesdeveloper
fullC
8/10
fullC
8/10
none
0/10
none
0/10
none
0/10
fullC
8/10
none
0/10
fullC
8/10
Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPay per second only for the compute a sandbox actually usesplatform-engineer
partialC
4/10
partialC
6/10
fullX
8/10
none
0/10
partialC
4/10
none
0/10
partialC
3/10
none
0/10

Privacy posture — data-handling and privacy storiesPrivacy posture

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Privacy posture — data-handling and privacy storiesChoose where my data is stored (region/residency)ai-native
partialC
4/10
none
0/10
none
0/10
none
0/10
partialC
5/10
none
0/10
partialC
6/10
none
0/10
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI modelsai-native
none
0/10
none
0/10
n/a
n/a
n/a
none
0/10
none
0/10
none
0/10
Privacy posture — data-handling and privacy storiesControl data retention and deletionai-native
partialC
6/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
Privacy posture — data-handling and privacy storiesOpt out of telemetry and usage trackingai-native
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10
none
0/10

Provisioning lifecycle — creating, updating, and tearing down resources across their lifecycleProvisioning lifecycle

Lifecycle

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Provisioning lifecycle — creating, updating, and tearing down resources across their lifecycleSet timeouts so sandboxes shut down automatically and stop billing when idle or donedeveloper
fullC
8/10
none
0/10
none
0/10
disputedD
3/10
fullC
8/10
partialC
5/10
partialC
6/10
none
0/10
Provisioning lifecycle — creating, updating, and tearing down resources across their lifecycleSpin up an isolated sandbox with one API/SDK call and get a live environment in secondsdeveloper
fullC
9/10
fullT
9/10
fullT
8/10
fullX
8/10
fullC
8/10
fullC
9/10
partialT
6/10
fullT
7/10

Preview access

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Provisioning lifecycle — creating, updating, and tearing down resources across their lifecycleExpose a port from the sandbox on a public preview URL to reach services running insidedeveloper
none
0/10
none
0/10
partialT
3/10
fullC
9/10
partialC
5/10
fullC
8/10
fullC
8/10
partialC
6/10

Snapshot persistence — stories about snapshot persistence in this arenaSnapshot persistence

Snapshots

StoryPersona
E2B logoE2B
Daytona logoDaytona
Modal Sandboxes logoModal Sandboxes
Cloudflare Sandboxes logoCloudflare Sandboxes
Vercel Sandbox logoVercel Sandbox
Runloop logoRunloop
Blaxel logoBlaxel
Maritime logoMaritime
Snapshot persistence — stories about snapshot persistence in this arenaPause a running sandbox and resume it later with filesystem and memory state intactdeveloper
fullC
8/10
partialC
6/10
partialC
4/10
partialX
5/10
fullC
8/10
fullC
8/10
partialC
5/10
none
0/10
Snapshot persistence — stories about snapshot persistence in this arenaSnapshot a sandbox and later restore or fork new sandboxes from that snapshotdeveloper
fullC
8/10
fullC
8/10
partialC
5/10
partialX
5/10
partialC
6/10
fullC
8/10
none
0/10
none
0/10
Verdict✓ fullclear evidence~ partialwith caveats! disputedevidence conflicts— noneno evidence foundn/aquestion doesn't apply to this kind of product
ProofT probedtested by usX communityusers back itC claimedvendor claim onlyD contradictedevidence disagrees⚿ auth-gatedprobe hit a live sign-in wall — verified reachable, untestable keylessly
quality 0–10 · PA Score /100 · A–D = evidence confidence · full guide

Adjacent arenas — categories often shopped togetherAdjacent arenas

Shopping this category often means shopping these too.