# Execute Code in Sandboxes — AI agents

Source: [Execute Code in Sandboxes — AI agents](<https://www.sota2.com/rankings/industries/agent-native/execute-code-in-sandboxes/editions/2026-11-10-e3-100>)

Collection index: [llms.txt](<https://www.sota2.com/rankings/llms.txt>)

Data updated: 2026-11-10T19:14:36.025071+00:00

Task: Execute Code in Sandboxes. Industry or audience: AI agents. Give an agent an isolated runtime in which it can execute code, commands, or long-running work safely.

Edition: 2026-11-10-e3-100. Method: e3-score-edition-v1 (six pillars).

Coverage: 44 product records from 40 companies; 10 displayed entries. This is not a claim of complete market coverage.

Positions and scores below are the published values. Equal display ranks are ties; an entry's display order does not break a tie. Scores describe available evidence within this scope, not hands-on performance testing or guaranteed outcomes.

## Comparison at a glance

| Published rank | Product | Company | Score / 100 | Best for |
| --- | --- | --- | --- | --- |
| 1 | Sandboxes | Beam | 65 |  |
| 2 | Superserve | Superserve | 63.29343 |  |
| 3 | Replicas | Replicas | 61.289939 |  |
| 4 | E2B | E2B | 60.723817 |  |
| 5 | Sandboxes | Blaxel | 55.790883 |  |
| 5 | boat | Boat | 55.790883 |  |
| 5 | boxes.dev | boxes.dev | 55.790883 |  |
| 5 | cmux Cloud VMs | Manaflow | 55.790883 |  |
| 5 | Archil | Archil | 55.790883 |  |
| 5 | Cursor | Cursor | 55.790883 |  |

## Task evidence by product

Selected public excerpts for Execute Code in Sandboxes in AI agents (edition 2026-11-10-e3-100). Read each excerpt with its source and qualifications; coverage varies by product.

| Task | Company and product | Evidence |
| --- | --- | --- |
| Execute Code in Sandboxes | [Beam](<https://www.sota2.com/companies/beam.md>) · [Sandboxes](<https://www.sota2.com/products/beam-sandboxes.md>) | **Task fit** “Spin up isolated, Python-native compute environments in seconds — with GPUs, dynamic port exposure, snapshot and resume, and Docker-in-Docker. Run untrusted or LLM-generated code safely, at any scale.” [www.beam.cloud](<https://www.beam.cloud/sandbox>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Task fit** “Execute Python with run\_code, run any shell command with exec, upload and download files, and stream logs back in real time.” [www.beam.cloud](<https://www.beam.cloud/sandbox>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “A cloud environment for agents Sandboxes give you a secure, fully configurable machine in the cloud.” [www.beam.cloud](<https://www.beam.cloud/sandbox>) · Retained capability excerpt; it does not establish independent customer validation. |
| Execute Code in Sandboxes | [Superserve](<https://www.sota2.com/companies/superserve.md>) · [Superserve](<https://www.sota2.com/products/superserve-superserve.md>) | **Task fit** “Sandboxes where agents build and run complex applications,” [www.superserve.ai](<https://www.superserve.ai/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Task fit** “File reads, writes, and directory listings, and saved-snapshot captures.” [docs.superserve.ai](<https://docs.superserve.ai/sandbox/lifecycle>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “Run Claude Code, Codex, or your own agent loop inside the machine, and control it from TypeScript, Python, MCP, the CLI, or the API.” [www.superserve.ai](<https://www.superserve.ai/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Adoption** “We benchmarked several sandbox providers, and Superserve stood out for its speed and reliability. They helped us launch Lindy’s AI teammates in under a month.” [www.superserve.ai](<https://www.superserve.ai/>) · Vendor-published source; independent confirmation is not established. |
| Execute Code in Sandboxes | [Replicas](<https://www.sota2.com/companies/replicas.md>) · [Replicas](<https://www.sota2.com/products/replicas-replicas.md>) | **Task fit** “Every task boots its own Linux VM in the cloud, sharing nothing with the agents running beside it.” [tryreplicas.com](<https://tryreplicas.com/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Task fit** “Each task runs in an isolated Linux VM you configure once. Agents install dependencies, run services, drive a browser, and verify their own work.” [tryreplicas.com](<https://tryreplicas.com/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “Agents install dependencies, run services, drive a browser, and verify their own work.” [tryreplicas.com](<https://tryreplicas.com/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “Run coding agents inside cloud machines with your codebases, tooling, and dependencies.” [tryreplicas.com](<https://tryreplicas.com/>) · Retained capability excerpt; it does not establish independent customer validation. |
| Execute Code in Sandboxes | [E2B](<https://www.sota2.com/companies/e2b.md>) · [E2B](<https://www.sota2.com/products/e2b-e2b.md>) | **Task fit** “E2B runs the isolated machine your agent works on.” [e2b.dev](<https://e2b.dev/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Task fit** “Run code, control the network, keep files, hold secrets, watch it, pause or fork it.” [e2b.dev](<https://e2b.dev/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “One isolated microVM per session, with an API around it. Run code, control the network, keep files, hold secrets, watch it, pause or fork it.” [e2b.dev](<https://e2b.dev/>) · Retained capability excerpt; it does not establish independent customer validation. |
| Execute Code in Sandboxes | [Blaxel](<https://www.sota2.com/companies/blaxel.md>) · [Sandboxes](<https://www.sota2.com/products/blaxel-sandboxes.md>) | **Task fit** “Blaxel Sandboxes are AI-native: a high-performance OS-as-a-service that gives every agent full Linux access to filesystems, libraries, shells, and logs.” [blaxel.ai](<https://blaxel.ai/platform/sandboxes>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Task fit** “Start and manage processes, run arbitrary commands, and stream stdout and stderr live from every sandbox.” [blaxel.ai](<https://blaxel.ai/platform/sandboxes>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “Every sandbox runs in its own microVM with no shared kernel.” [blaxel.ai](<https://blaxel.ai/platform/sandboxes>) · Retained capability excerpt; it does not establish independent customer validation. |
| Execute Code in Sandboxes | [Boat](<https://www.sota2.com/companies/boat.md>) · [boat](<https://www.sota2.com/products/boat-boat.md>) | **Task fit** “A sandbox is a persistent Linux (Ubuntu) virtual machine with SSH and SCP access, Docker support inside the VM” [boat.dev](<https://boat.dev/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Task fit** “$ boat execRun a command, no SSH” [boat.dev](<https://boat.dev/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “Yes. Create them no-env so they receive none of your account's secrets and stay confined to themselves.” [boat.dev](<https://boat.dev/>) · Retained capability excerpt; it does not establish independent customer validation. |
| Execute Code in Sandboxes | [boxes.dev](<https://www.sota2.com/companies/boxes-dev.md>) · [boxes.dev](<https://www.sota2.com/products/boxes-dev-boxes-dev.md>) | **Task fit** “A boxes.dev devbox gives you another computer—its own filesystem, processes, ports, and database state—created from a Template box snapshot.” [boxes.dev](<https://boxes.dev/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Task fit** “Each agent can run your app, change dependencies, edit the database schema, or break things without affecting the others.” [boxes.dev](<https://boxes.dev/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “boxes.dev gives each agent a whole computer that’s already running your dev environment (a “devbox”), and a way to steer that agent from anywhere.” [boxes.dev](<https://boxes.dev/>) · Retained capability excerpt; it does not establish independent customer validation. |
| Execute Code in Sandboxes | [Manaflow](<https://www.sota2.com/companies/manaflow.md>) · [cmux Cloud VMs](<https://www.sota2.com/products/manaflow-cmux-cloud-vms.md>) | **Task fit** “What are Cloud VMs?Persistent Linux machines in the cloud: pets, not cattle.” [cmux.com](<https://cmux.com/pricing>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Task fit** “Agents clone repositories, run commands, and open pull requests there without touching your Mac.” [cmux.com](<https://cmux.com/pricing>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “Cloud agents on Cloud VMs in isolated remote sandboxes” [cmux.com](<https://cmux.com/pricing>) · Retained capability excerpt; it does not establish independent customer validation. |
| Execute Code in Sandboxes | [Archil](<https://www.sota2.com/companies/archil.md>) · [Archil](<https://www.sota2.com/products/archil-archil.md>) | **Task fit** “Each call runs Bash, Python, or Node against the disk on demand, and the files it writes are there for the next call.” [archil.com](<https://archil.com/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Task fit** “Archil runs tool calls and sandboxes beside a durable, shared filesystem.” [archil.com](<https://archil.com/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “Give your agent a bash tool.Each call runs Bash, Python, or Node against the disk on demand” [archil.com](<https://archil.com/>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “Give your agent a bash tool.Each call runs Bash, Python, or Node against the disk on demand, and the files it writes are there for the next call.” [archil.com](<https://archil.com/>) · Retained capability excerpt; it does not establish independent customer validation. |
| Execute Code in Sandboxes | [Cursor](<https://www.sota2.com/companies/cursor.md>) · [Cursor](<https://www.sota2.com/products/cursor-cursor.md>) | **Task fit** “Run shell commands directly from Cursor, from builds to tests to installs. Sandboxed by default.” [cursor.com](<https://cursor.com/product>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Task fit** “Reading package.json Running terminal command $ npm run build Build complete. Ready to deploy?” [cursor.com](<https://cursor.com/product>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “build this project Reading package.json Running terminal command $ npm run build Build complete. Ready to deploy?” [cursor.com](<https://cursor.com/product>) · Retained capability excerpt; it does not establish independent customer validation.<br>**Industry fit** “Agents use their own computers to build, test, and demo features end to end for you to review.” [cursor.com](<https://cursor.com/home>) · Retained capability excerpt; it does not establish independent customer validation. |

## Scoring method

The score combines task fit, industry fit and supported customer signals. Task and industry fit account for 65 points. Partial evidence marks a calculated fit score with unconfirmed steps; it is not a fully established assessment. Unknown means there is insufficient evidence to score that pillar; unknown fit uses a neutral value in the total. Evidence samples are selected examples, not a complete evidence record.

| Pillar | Maximum contribution |
| --- | --- |
| Task fit | 45 |
| Industry fit | 20 |
| Adoption | 12 |
| Customer satisfaction | 10 |
| Value signals | 10 |
| Popularity | 3 |

[L1, L2, pillars and edition rules](<https://www.sota2.com/rankings/methodology.md>)

## Sandboxes — rank 1

- [Product profile](<https://www.sota2.com/products/beam-sandboxes.md>): Isolated, secure code execution environments for running untrusted code at scale with file system operations, snapshots, and Docker-in-Docker.

Company: [Beam](<https://www.sota2.com/companies/beam.md>)

Why included: Isolated, secure code execution environments for running untrusted code at scale with file system operations, snapshots, and Docker-in-Docker.

Best for: Not recorded

Qualifications: No additional qualification recorded

Recorded pricing: Not recorded

| Pillar | Stored contribution | Maximum | Observed value | Evidence basis |
| --- | --- | --- | --- | --- |
| Task fit | 45 | 45 | 100 | observed |
| Industry fit | 20 | 20 | 100 | observed |
| Adoption | 0 | 12 | Unknown | unknown |
| Satisfaction | 0 | 10 | Unknown | unknown |
| Value signals | 0 | 10 | Unknown | unknown |
| Popularity | 0 | 3 | Unknown | unknown |

- [Task fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=632f9858-5be6-497b-8c94-681113d1019d&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=taskFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Industry fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=632f9858-5be6-497b-8c94-681113d1019d&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=industryFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

## Superserve — rank 2

- [Product profile](<https://www.sota2.com/products/superserve-superserve.md>): Virtual machines for long-running AI agents, with isolated sandboxes, persistent storage, programmable networking, and pause, resume, and fork capabilities.

Company: [Superserve](<https://www.sota2.com/companies/superserve.md>)

Why included: Virtual machines for long-running AI agents, with isolated sandboxes, persistent storage, programmable networking, and pause, resume, and fork capabilities.

Best for: Not recorded

Qualifications: No additional qualification recorded

Recorded pricing: $20/month; Subscription, Usage Based, Tiered, Enterprise Custom

| Pillar | Stored contribution | Maximum | Observed value | Evidence basis |
| --- | --- | --- | --- | --- |
| Task fit | 35.79088291032767 | 45 | Unknown | partial-support |
| Industry fit | 20 | 20 | 100 | observed |
| Adoption | 5.019612895309031 | 12 | 41.83010746090859 | observed |
| Satisfaction | 0.7329344942554207 | 10 | 7.329344942554207 | observed |
| Value signals | 1.75 | 10 | 17.5 | observed |
| Popularity | 0 | 3 | Unknown | unknown |

- [Task fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=9dc6c1f1-f9e2-4837-87e9-4626c920efbe&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=taskFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Industry fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=9dc6c1f1-f9e2-4837-87e9-4626c920efbe&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=industryFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Adoption: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=9dc6c1f1-f9e2-4837-87e9-4626c920efbe&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=adoption&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Satisfaction: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=9dc6c1f1-f9e2-4837-87e9-4626c920efbe&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=satisfaction&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

## Replicas — rank 3

- [Product profile](<https://www.sota2.com/products/replicas-replicas.md>): Background coding agent platform that spawns Claude Code, Codex, Cursor, or Opencode in isolated VM-based sandboxed development environments.

Company: [Replicas](<https://www.sota2.com/companies/replicas.md>)

Why included: Background coding agent platform that spawns Claude Code, Codex, Cursor, or Opencode in isolated VM-based sandboxed development environments.

Best for: Not recorded

Qualifications: No additional qualification recorded

Recorded pricing: $50/mo, billed monthly, includes $50 of usage; Usage Based

| Pillar | Stored contribution | Maximum | Observed value | Evidence basis |
| --- | --- | --- | --- | --- |
| Task fit | 35.79088291032767 | 45 | Unknown | partial-support |
| Industry fit | 20 | 20 | 100 | observed |
| Adoption | 5.499055704172308 | 12 | 45.825464201435906 | observed |
| Satisfaction | 0 | 10 | Unknown | unknown |
| Value signals | 0 | 10 | Unknown | unknown |
| Popularity | 0 | 3 | Unknown | unknown |

- [Task fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=104a783d-e894-4059-868e-893eb0f55194&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=taskFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Industry fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=104a783d-e894-4059-868e-893eb0f55194&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=industryFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

## E2B — rank 4

- [Product profile](<https://www.sota2.com/products/e2b-e2b.md>): Isolated Linux microVMs for AI agent sessions, with code execution, networking, storage, observability, and lifecycle controls.

Company: [E2B](<https://www.sota2.com/companies/e2b.md>)

Why included: Isolated Linux microVMs for AI agent sessions, with code execution, networking, storage, observability, and lifecycle controls.

Best for: Not recorded

Qualifications: No additional qualification recorded

Recorded pricing: Hobby $0 base + usage ($100 one-time credit), 1h/run; Pro USD150/mo + usage, 24h/run. Hobby/Pro compute: $0.000014/vCPU-second + $0.0000045/GiB-second. Enterprise minimum USD3000/mo + usage; BYOC.; Hobby/Pro metered compute; Pro monthly base; Enterprise custom.

| Pillar | Stored contribution | Maximum | Observed value | Evidence basis |
| --- | --- | --- | --- | --- |
| Task fit | 35.79088291032767 | 45 | Unknown | partial-support |
| Industry fit | 20 | 20 | 100 | observed |
| Adoption | 4.2 | 12 | 35 | observed |
| Satisfaction | 0.7329344942554207 | 10 | 7.329344942554207 | observed |
| Value signals | 0 | 10 | Unknown | unknown |
| Popularity | 0 | 3 | Unknown | unknown |

- [Task fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=ce7ebf85-2be4-4308-a6b0-fece1d6d4ec5&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=taskFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Industry fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=ce7ebf85-2be4-4308-a6b0-fece1d6d4ec5&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=industryFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

## Sandboxes — rank 5

- [Product profile](<https://www.sota2.com/products/blaxel-sandboxes.md>): Isolated microVMs per agent, app, or job.

Company: [Blaxel](<https://www.sota2.com/companies/blaxel.md>)

Why included: Isolated microVMs per agent, app, or job.

Best for: Not recorded

Qualifications: No additional qualification recorded

Recorded pricing: Active CPU: $0.0000115/ GB RAM · second. Snapshots storage: $0.20/ GB · month. Images: $0.045/ GB · month.; Usage Based

| Pillar | Stored contribution | Maximum | Observed value | Evidence basis |
| --- | --- | --- | --- | --- |
| Task fit | 35.79088291032767 | 45 | Unknown | partial-support |
| Industry fit | 20 | 20 | 100 | observed |
| Adoption | 0 | 12 | Unknown | unknown |
| Satisfaction | 0 | 10 | Unknown | unknown |
| Value signals | 0 | 10 | Unknown | unknown |
| Popularity | 0 | 3 | Unknown | unknown |

- [Task fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=38a0fbcb-4bc6-47f0-998a-0a617b5acbee&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=taskFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Industry fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=38a0fbcb-4bc6-47f0-998a-0a617b5acbee&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=industryFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

## boat — rank 5

- [Product profile](<https://www.sota2.com/products/boat-boat.md>): A cloud platform for persistent Linux virtual machines, or sandboxes, for AI agents.

Company: [Boat](<https://www.sota2.com/companies/boat.md>)

Why included: A cloud platform for persistent Linux virtual machines, or sandboxes, for AI agents.

Best for: Not recorded

Qualifications: No additional qualification recorded

Recorded pricing: From $20/mo; Subscription, Usage Based, Per Seat, Tiered

| Pillar | Stored contribution | Maximum | Observed value | Evidence basis |
| --- | --- | --- | --- | --- |
| Task fit | 35.79088291032767 | 45 | Unknown | partial-support |
| Industry fit | 20 | 20 | 100 | observed |
| Adoption | 0 | 12 | Unknown | unknown |
| Satisfaction | 0 | 10 | Unknown | unknown |
| Value signals | 0 | 10 | Unknown | unknown |
| Popularity | 0 | 3 | Unknown | unknown |

- [Task fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=fc475a4a-6ade-4a4c-ad75-72295409adfd&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=taskFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Industry fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=fc475a4a-6ade-4a4c-ad75-72295409adfd&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=industryFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

## boxes.dev — rank 5

- [Product profile](<https://www.sota2.com/products/boxes-dev-boxes-dev.md>): Cloud development environments giving each coding agent its own cloud Linux computer (devbox) with steerable access from desktop, mobile, terminal, Slack, Linear, schedules, and...

Company: [boxes.dev](<https://www.sota2.com/companies/boxes-dev.md>)

Why included: Cloud development environments giving each coding agent its own cloud Linux computer (devbox) with steerable access from desktop, mobile, terminal, Slack, Linear, schedules, and...

Best for: Not recorded

Qualifications: No additional qualification recorded

Recorded pricing: $0 (Trial); Per Seat, Usage Based, Tiered, Enterprise Custom

| Pillar | Stored contribution | Maximum | Observed value | Evidence basis |
| --- | --- | --- | --- | --- |
| Task fit | 35.79088291032767 | 45 | Unknown | partial-support |
| Industry fit | 20 | 20 | 100 | observed |
| Adoption | 0 | 12 | Unknown | unknown |
| Satisfaction | 0 | 10 | Unknown | unknown |
| Value signals | 0 | 10 | Unknown | unknown |
| Popularity | 0 | 3 | Unknown | unknown |

- [Task fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=48ff64e8-bd01-4fa2-a076-168b0fd6f043&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=taskFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Industry fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=48ff64e8-bd01-4fa2-a076-168b0fd6f043&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=industryFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

## cmux Cloud VMs — rank 5

- [Product profile](<https://www.sota2.com/products/manaflow-cmux-cloud-vms.md>): Remote Linux sandboxes where AI coding agents run in the cloud, with automatic suspension of idle VMs.

Company: [Manaflow](<https://www.sota2.com/companies/manaflow.md>)

Why included: Remote Linux sandboxes where AI coding agents run in the cloud, with automatic suspension of idle VMs.

Best for: Not recorded

Qualifications: No additional qualification recorded

Recorded pricing: Included with Pro: $480/yr ($40/mo) when billed yearly, or $50/mo; Subscription, Enterprise Custom

| Pillar | Stored contribution | Maximum | Observed value | Evidence basis |
| --- | --- | --- | --- | --- |
| Task fit | 35.79088291032767 | 45 | Unknown | partial-support |
| Industry fit | 20 | 20 | 100 | observed |
| Adoption | 0 | 12 | Unknown | unknown |
| Satisfaction | 0 | 10 | Unknown | unknown |
| Value signals | 0 | 10 | Unknown | unknown |
| Popularity | 0 | 3 | Unknown | unknown |

- [Task fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=fee1b0de-3c4d-4ee1-ba32-e7cff2bc9e53&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=taskFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Industry fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=fee1b0de-3c4d-4ee1-ba32-e7cff2bc9e53&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=industryFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

## Archil — rank 5

- [Product profile](<https://www.sota2.com/products/archil-archil.md>): Multi-tenant file system that thousands of machines mount at once.

Company: [Archil](<https://www.sota2.com/companies/archil.md>)

Why included: Multi-tenant file system that thousands of machines mount at once.

Best for: Not recorded

Qualifications: No additional qualification recorded

Recorded pricing: Not recorded

| Pillar | Stored contribution | Maximum | Observed value | Evidence basis |
| --- | --- | --- | --- | --- |
| Task fit | 35.79088291032767 | 45 | Unknown | partial-support |
| Industry fit | 20 | 20 | 100 | observed |
| Adoption | 0 | 12 | Unknown | unknown |
| Satisfaction | 0 | 10 | Unknown | unknown |
| Value signals | 0 | 10 | Unknown | unknown |
| Popularity | 0 | 3 | Unknown | unknown |

- [Task fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=4d47f95f-6996-46a3-b6cb-de6bd6e4e65e&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=taskFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Industry fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=4d47f95f-6996-46a3-b6cb-de6bd6e4e65e&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=industryFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

## Cursor — rank 5

- [Product profile](<https://www.sota2.com/products/cursor-cursor.md>): Cursor is an AI coding agent that plans, writes, and reviews code using AI agents that understand your entire codebase.

Company: [Cursor](<https://www.sota2.com/companies/cursor.md>)

Why included: Cursor is an AI coding agent that plans, writes, and reviews code using AI agents that understand your entire codebase.

Best for: Not recorded

Qualifications: No additional qualification recorded

Recorded pricing: Free; Subscription, Usage Based

| Pillar | Stored contribution | Maximum | Observed value | Evidence basis |
| --- | --- | --- | --- | --- |
| Task fit | 35.79088291032767 | 45 | Unknown | partial-support |
| Industry fit | 20 | 20 | 100 | observed |
| Adoption | 0 | 12 | Unknown | unknown |
| Satisfaction | 0 | 10 | Unknown | unknown |
| Value signals | 0 | 10 | Unknown | unknown |
| Popularity | 0 | 3 | Unknown | unknown |

- [Task fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=ae4feaf9-b3e7-4e8c-8826-28e2a921c2ac&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=taskFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

- [Industry fit: public source excerpts](<https://www.sota2.com/api/rankings/samples?productId=ae4feaf9-b3e7-4e8c-8826-28e2a921c2ac&industry=agent-native&task=execute-code-in-sandboxes&editionId=2026-11-10-e3-100&pillar=industryFit&limit=2>): Exact product, task, industry, edition and pillar scope; selected examples, not the full evidence record.

## Preserved editions

- [October 28, 2026](<https://www.sota2.com/rankings/industries/agent-native/execute-code-in-sandboxes/editions/2026-10-29-profile-badges.md>): Historical scores and their recorded methodology; not today's ranking.

## Related task comparisons