Niches · Code execution sandboxes
Run many sandboxes at once for tests, evaluations or parallel attempts
No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.
What counts as done
50 sandboxes start from the same snapshot without a 429, each returns its result, and the account's concurrency cap and the route to raise it are documented.
Measured, for our own tests: all 50 start within 60 seconds of the first create call. No docs we read state these figures, so they don't count against a listing here.
How agents ask for it: run the test suite split across 20 machines
, try five fixes in parallel and keep the one that passes
, run this eval over 1,000 tasks
, fork the machine at this point
Does the job, with a limit 18
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Agent 37 Cloud C Agent 37 Inc. | POST /v1/instances/{id}/fork copies an instance, but a workspace runs 3 instances before its first top-up, 10 after it and 50 only after $50 of top-ups; past the limit a create returns 409 instance_limit_reached. source |
| Amazon Bedrock AgentCore Code Interpreter BB Amazon Web Services, Inc. | Sessions start from a clean runtime, so there is no shared snapshot and packages install on every session; concurrency and API rates are account quotas raised through Service Quotas, with ThrottlingException on 429. source |
| Blaxel Sandboxes C Blaxel, Inc. | Snapshots capture filesystem, processes and memory and fork into new sandboxes, but tiers start at 10 concurrent sandboxes and rise with 30-day top-up volume, with QUOTA_EXCEEDED past the cap. source |
| Celesto (formerly SmolVM) BB Celesto AI, Inc. | Snapshots and unique-name concurrent computers exist, but no fork-to-N call or concurrency cap is documented for local or Cloud use. source |
| Cloudflare Sandbox SDK BB Cloudflare, Inc. | Each sandbox is a Durable Object you name, and several can start from one snapshot, but no concurrency cap for sandboxes was found on the pages read; the 0.x limits page covers subrequests only. source |
| Daytona BB Daytona Platforms Inc. | Fork is Linux VM only; containers go via snapshots. Tier 1 has 10 vCPU and 10 GiB in total, so 50 sandboxes need Tier 2 (card plus $25). Issue 5137 reports sandboxes unreachable under concurrent verifier load. source |
| E2B BB FoundryLabs, Inc. | Fork snapshots a running sandbox once and boots N copies with memory in a single call, but Hobby allows 10 concurrent sandboxes at 1 create a second; 50 in 60 seconds needs Pro (100 concurrent, 5 a second). source |
| Freestyle B Freestyle Cloud Inc. | A snapshot captures exact memory and disk and boots any number of clones, but concurrent VMs are 10 on Free, 40 on Hobby and 400 on Pro ($500); one user found 50 restrictive. source |
| InstaVM D Checksum Labs, Inc. | vms.clone() clones a running VM for fan-out and snapshots boot in milliseconds, but the Free plan allows 5 concurrent VMs and no higher cap is published short of Pro. source |
| Maritime B Maritime AI, Inc. | Swarms run thousands of sandboxes from one command but need the Scale plan ($500); otherwise machines awake at once are 2 on trial and 5 on Starter, with 429 awake_limit_reached. source |
| Modal Sandboxes B Modal Labs, Inc. | A memory snapshot restores into any number of clones with processes running, and Offload cut a test run from about 726 to 120 seconds, but the concurrency cap was not on the pages read and a card is required. source |
| Morph Cloud D Morph Labs, Inc. | POST /api/instance/{id}/branch saves a snapshot and creates `count` children with memory, but no concurrency cap is published; 503s carry Retry-After. source |
| SPACE C Perplexity AI | Forks and warm pools exist and snapshots are incubating, but the concurrency cap is whatever the operator's cluster and admission limits allow. source |
| Runloop Devboxes B Runloop AI, Inc. | Disk snapshots create new devboxes, but the trial allows 3 running devboxes and the service ends on 13 November 2026. source |
| Sandbox0 C Lougao, LLC | Fork and claim-from-snapshot fan out a rootfs, but the default quota is 20 running sandboxes and 5 claims a second, answered with 429 quota_exceeded and Retry-After. source |
| Sprites B Fly.io, Inc. | Checkpoints snapshot the filesystem and restore the same Sprite; no fork, and creation is limited to 10 a minute on pay-as-you-go, so 50 in 60 seconds needs a plan. source |
| Together Code Sandbox C Together Computer, Inc. | Any number of sandboxes start from one snapshot, including memory snapshots, but there is no live fork and no concurrency cap is published. source |
| Vercel Sandbox BB Vercel Inc. | Sandbox.fork starts copies from a filesystem snapshot and Pro allows 10,000 concurrent sandboxes at 150 vCPUs a minute, but Hobby allows 10 and 20 vCPUs a minute. source |
Doesn't do this job 4
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| DeltaBox Lite C DeltaBox (delta-box) | Concurrent private sessions for several local agents exist, but there is no fleet of sandboxes or fork-to-N. source |
| Deno Sandbox D Deno Land Inc. | 5 concurrent sandboxes per organisation during pre-release, raised only by emailing deploy@deno.com; 50 at once is not possible by default. source |
| Microsoft Execution Containers BB Microsoft Corporation | No fleet, snapshot or fork; runs are local processes. source |
| Offscreen B Mark Phelps (individual) | At most two VM jobs at once, by Apple's macOS virtualisation licence. source |
What stops agents finishing
- concurrency caps around 50 on entry tiers with a sales step to raise them
- a snapshot build is mandatory before any sandbox (Together)
- Free plans start with zero compute (Morph) or need a card (Modal)
Around it
Before: code-sandboxes.coding-agent-workspace, agent-harnesses.plan-task. After: decision-models.pick-best-candidate, agent-harnesses.open-pull-request.
Where this comes from
Weight 9 of 100 in Code execution sandboxes: 5 of 53 mentions: Offload on Modal, a Freestyle thread comment on the 50 concurrent VM limit, a Daytona issue on concurrent verifier workloads, a team testing on three providers, and one builder who evaluated three vendors for per-thread sandboxes.
The same as data: /api/v1/use-cases/code-sandboxes.parallel-fanout.json, or the MCP tool get_use_case with id code-sandboxes.parallel-fanout. Other jobs in this category: /api/v1/niches?category=code-sandboxes.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.