Code & AI agent sandboxes: read the guide

Judge0

Open coreSandbox

Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.

Homepage Docs Pricing Repository

Scanned 14 Oct 2026 · Schema v5 · features v21

From: €27/mo
Tiered subscription with daily-submission quotas + per-extra-submission overage (Shared Cloud, billed via RapidAPI); Dedicated Cloud + Enterprise are custom/contact; self-host is free under GPL-3.0.
Free tier: Yes
yes
Isolation: Container
shares the host kernel
Regions: —
Hosted workload regions not disclosed on fetched homepage/pricing/docs. Company address is Zagreb, Croatia; that is not a hosting-location guarantee. Self-host placement is operator-controlled.
Capabilities: 4 / 61
0 partial · 24 fail · 0 not assessed
Agent readiness: 9/11 · 7/11
read · drive, pre-login surface

Advertised for

Sandboxed compilation + execution of untrusted / AI generated code in 60+ (CE) / 90+ (CE + Extra CE) languages and frameworks; single file and multi file (project) programs.

Built for

Developers, then technical

· Documented HTTP JSON submissions API at ce.judge0.com
· Official Python, Dart and JavaScript SDKs
· Pricing uses submissions/day and per-extra-submission overage

01 Pricing Tiered subscription with daily-submission quotas + per-extra-submission overage (Shared Cloud, billed via RapidAPI); Dedicated Cloud + Enterprise are custom/contact; self-host is free under GPL-3.0.

Tier	EntryBasic (Shared Cloud)	Pro (Shared Cloud)	Ultra (Shared Cloud)	Mega (Shared Cloud)	TopDedicated Cloud
Price	Free	€27/month	€54/month	€107/month	Custom / contact

Free tier: yes

submissions/day (quota) + €0.001 per extra submission·Card required: unconfirmed·€0.001 per extra submission beyond the daily quota (Shared Cloud).·judge0.com

02 Website design Desktop public website · assessed 14 Oct 2026

Complete assessment.

The desktop landing and pricing views use a spacious monochrome, monospaced presentation: a split hero with a tilted inverse-text highlight and IDE screenshot, followed by restrained rounded plan cards. The API docs use a denser sidebar-and-article layout with light sans-serif headings and a colorful circuit-pattern banner.

Editorial minimalism
Corporate

Landing page: captured
Pricing: captured
Docs: captured

03 Runtime Each fact carries its source; dots show confidence. Open a row for the evidence.

Isolation & lifecycle

Isolation primitive

Containershares the host kernel

Persistence

ephemeral

Snapshots / forks

Resources & limits

Storage

ephemeral

Limits & quotas

Per-submission cpu_time_limit, wall_time_limit, memory_limit, max_processes_and_or_threads, max_file_size and stack_limit; paid Shared Cloud tiers list 2000/5000/10000 submissions/day, Basic FAQ 50/day.

GPU

Access

Deploy interface

apisdk

SDK languages

PythonDartJavaScript

Network & secrets

Egress controls

yes

Secrets

Bring your own cloud

Placement & use

Jurisdiction

Advertised workloads

Sandboxed compilation + execution of untrusted / AI-generated code in 60+ (CE) / 90+ (CE + Extra CE) languages and frameworks; single-file and multi-file (project) programs.

04 Capabilities 4 pass · 0 partial · 24 fail · 61 of 61 assessed

Supported — Documented on the public surface and verified.
Partially supported — Exists with caveats: gated, thin, or enterprise-only.
Not supported — Checked and not offered.
Not assessed — Scanned before this capability was tracked. Not a lack.

Compute & storage 0/8

Persistent diskStorage that survives restart/stop (not ephemeral-only).

Not supported

Object storageManaged S3-compatible / blob object store the platform PROVIDES to a user's workloads (buckets, presigned URLs). DISTINCT from persistent-disk (block/volume attached to an instance) and from a self-host dependency (source.self_host.deps[]=["object-storage"] is an infra dep to RUN an OSS tool — the opposite direction). SCOPE varies and matters: native first-class (Railway Buckets, Cloudflare R2) vs a sibling SKU / extension (Fly Tigris, Bunny Storage, DigitalOcean Spaces) — record which in the evidence quote / note. Admitted v15.

Not applicable

Snapshots / forkingSnapshot or copy-on-write fork of a running instance (filesystem-only counts). Whether the snapshot also restores memory + running processes is recorded separately by memory-snapshot (v19).

Not supported

Live-state (memory) snapshotsA snapshot / checkpoint / pause captures a running instance's MEMORY and PROCESS state and restores it, so running processes continue where they left off instead of a freshly booted instance with the same files. Counts whether user-triggered (snapshot, checkpoint, pause-to-storage) or used to restore pre-initialised state (memory snapshots for fast cold starts). Distinct from snapshots-forks (any snapshot or fork, including filesystem-only; a product passing that key may still fail this one) and from scale-to-zero (an idle-cost property; suspension may or may not keep memory). Actor multiplexing (see scale-to-zero) records its live-state half here — only when the suspended actor's MEMORY/process state is what comes back, not a freshly booted worker with the actor's files.

Not supported

Scale to zeroIdle instances suspend at no / negligible cost. ACTOR MULTIPLEXING (many suspended stateful actors sharing a small pool of pre-warmed workers, woken on request — Agent Substrate, AX, kagent; Rivet's hibernating actors) has NO key of its own (proposal REJECTED v20) — score the idle-cost half HERE and the live-state half under memory-snapshot; the oversubscription ratio / density is a performance characteristic the registry does not key.

Not supported

GPU computeGPU-backed instances available.

Not supported

Multi-regionCompute placeable in more than one geographic region.

Not supported

Sandbox templates / custom imagesBuild reusable sandbox/VM images from an OCI image or Dockerfile (a base you fork instances from).

Not supported

Cloud-init / ignition configCustomise a VM / microVM / instance at boot via cloud-init (or ignition) user-data — the same boot-metadata interface as AWS/Azure/GCP. Inject packages, users, SSH keys, files, and run-commands declaratively at launch. Distinct from sandbox-templates (a PREBUILT image you fork instances from) — this is PER-LAUNCH declarative customisation, not a baked image.

Not applicable

Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.

Not applicable

Selectable isolation runtimeThe user chooses the isolation runtime per workload / environment / sandbox from more than one option (e.g. microVM vs gVisor vs plain container, native namespaces vs gVisor, gVisor vs VM). Records the CHOICE; the isolation_primitive facet still records the best-evidenced primary. A platform that switches runtime automatically without a user choice (e.g. gVisor forced for GPU) does not pass on that alone.

Not supported

Networking & delivery 1/1

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Not applicable

Built-in reverse proxyPlatform routes external traffic to workload services.

Not applicable

Custom domainsBring-your-own domain via CNAME/DNS.

Not applicable

Public preview URLsShareable per-deploy / per-branch URLs.

Not applicable

Direct public IPv6Per-instance stable public IPv6 for raw TCP/UDP (beyond a managed HTTPS proxy) — e.g. mosh / raw sockets.

Not applicable

Egress controlsConfigurable OUTBOUND network policy — egress firewall / allowlist / egress proxy on traffic LEAVING a workload. Scoped to OUTBOUND only (v15): private-network REACHABILITY between a user's own services is private-networking, not this. Static-egress-IP belongs here (an outbound concept).

Supported

Private networkingA platform-internal private network between a user's OWN services — service-to-service connectivity, VPC, service mesh, and/or service discovery, not exposed to the public internet. DISTINCT from egress-controls (OUTBOUND firewall/allowlist), reverse-proxy (PUBLIC inbound ingress), and direct-ipv6 (per-instance PUBLIC addressing). Admitted v15.

Not applicable

Email send / receiveSend and/or receive email from the workload.

Not applicable

Edge KV storeA globally-replicated key-value store read from WITHIN an edge runtime at the PoP (low-latency, eventually-consistent) — Cloudflare Workers KV, Deno KV, Fastly KV Store, Akamai EdgeKV, Vercel Edge Config. Distinct from first-party-db (a managed DATABASE service you provision and connect to) and from http-query-api (HTTP access to an external store) — edge-kv is colocated with the edge compute and read at the edge.

Not applicable

Developer access 2/7

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Not supported

CLIOfficial command-line tool.

Not supported

SDKOfficial client library/libraries.

Supported

SSH accessDirect SSH into workloads.

Not supported

Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.

Not supported

Git deployDeploy from a Git repo / push-to-deploy.

Not applicable

Private container registryHosted private image registry.

Not applicable

E2B-compatible APIDrop-in compatibility with the E2B sandbox API/SDKs — existing E2B client code runs against this product by changing the endpoint/domain + key, with no business-code changes. E2B itself passes as the reference implementation. Distinct from public-api / sdk (the product has its own API — this key says it also speaks another vendor's) and from self-host-oss (a self-hosted E2B-compatible server is scored on both).

Not supported

HTTP data APIQuery / read / write the stored DATA over plain HTTP/REST (or GraphQL) WITHOUT the native protocol driver (Postgres wire / Redis RESP) — agent- and edge-friendly data access via fetch(). The DATA plane; distinct from public-api (a control-plane / management API). Auto-generated-from-schema REST/GraphQL (PostgREST, pg_graphql) is a flavour of this.

Not applicable

AI & agents 0/2

Built-in coding agentShips a first-party AI coding agent in the product.

Not applicable

Agent skillsInstallable / declarable agent skills or tools.

Not applicable

AI app builderPrompt-to-app / vibe-coding generation surface.

Not applicable

MCP serverExposes a Model Context Protocol server for agents.

Not supported

MCP clientActs as an MCP client / consumes MCP tools.

Not applicable

MCP-server hostingRun/host MCP servers as a workload on the platform (distinct from exposing a first-party MCP control server — that is mcp-server).

Not applicable

LLM gatewayRoutes LLM API calls through the platform (multi-provider).

Not applicable

BYOK for LLMsBring-your-own LLM provider keys.

Not applicable

Model inference API (first-party)A FIRST-PARTY hosted LLM/model inference API — the provider serves its OWN catalogue of (usually open-weight) models behind a (typically OpenAI-compatible) endpoint, billed per token. Distinct from llm-gateway (a multi-PROVIDER proxy/router for YOUR calls to external providers like OpenAI/Anthropic) and from byok-llm (bring your own provider keys) — here the platform IS the inference provider, serving its own models.

Not applicable

Autonomous QA agentA first-party AUTONOMOUS AI agent that QA-TESTS a running app / implementation — exercising it like a real user (clicking through flows, checking behaviour) and reporting bugs/defects (often back to a coding agent, or before a human review). Distinct from built-in-agent (a code-AUTHORING agent — this one VERIFIES the result, it does not write the feature; a product can ship both), from ai-guided-code-review (organises a diff for a HUMAN to review — not an autonomous tester), and from observability (runtime metrics/logs, not active testing).

Not applicable

Credential-injection proxyThe platform holds real secrets OUTSIDE the workload and injects them on the wire (an egress / broker proxy swaps a placeholder or phantom token for the real credential on matching outbound requests), so code running in the sandbox — e.g. an untrusted agent — never sees or can exfiltrate the real key. Distinct from secrets-management (storage + injection INTO the workload as env vars/files — the workload holds the secret) and from egress-controls (outbound allow/deny POLICY; a product can have an allowlist without injecting credentials, and vice versa).

Not supported

Preinstalled coding agentThe platform installs and launches a THIRD-PARTY coding agent (a harnesses.yml entry — Claude Code, Codex, OpenCode, Pi ...) inside a workspace/sandbox it provisions, with the agent's auth wired in (your own account or API key), so you start an agent session rather than an empty box. Distinct from built-in-agent (a FIRST-PARTY agent the vendor ships) and from harnesses[] (which records that a harness CAN target the product, not that the product runs it for you).

Not applicable

Data 0/0

First-party databasePlatform-provided managed database.

Not applicable

Database branchingCopy-on-write branch of a DATABASE (schema + data) as a dev-lifecycle primitive — branch your data like code, usually instant via a metadata operation. Distinct from snapshots-forks (forks a running compute INSTANCE / VM state) and from preview-environments (a full per-PR environment that may USE a DB branch). For a data product a CoW branch maps HERE, not to snapshots-forks.

Not applicable

Vector searchFirst-class storage, indexing, and similarity search of vector embeddings — a native vector type/index or a managed vector DB. The data-layer primitive for RAG / semantic retrieval.

Not applicable

Ephemeral instant DB (no-signup)Provision a working, usable instance via a single command / HTTP call with NO account, signup, or card — typically time-boxed (expires unless claimed). A zero-onboarding path an agent can hit directly.

Not applicable

Platform & operations 0/2

Scheduled tasksCron / scheduled job primitive.

Not supported

Durable workflowsDurable execution / long-running workflow primitive.

Not applicable

Preview environmentsA full EPHEMERAL environment spun up per PR / branch — compute + addons + (often) a DB branch — torn down on merge. More than preview-urls (which is just a shareable URL for one deploy).

Not applicable

Built-in observabilityFirst-party metrics / logs / tracing / APM / profiling included in the platform (no third-party stack required to see what a workload is doing).

Not supported

Managed CI/CD runnersPlatform-hosted, drop-in CI/CD runner VMs (GitHub Actions / GitLab), typically faster and cheaper than the CI vendor's own hosted runners, billed per runner-minute; isolated + ephemeral per job. Distinct from git-deploy (push-to-deploy of an APP) and scheduled-tasks (cron) — this is managed CI COMPUTE you point your existing pipelines at.

Not applicable

Project template marketplaceA marketplace / gallery of prebuilt PROJECT STARTER templates (apps or websites) a user clones or launches a new project from and then customises — the "start from a template" surface of a builder / PaaS. Distinct from sandbox-templates (a COMPUTE base IMAGE you fork runtime INSTANCES from — Dockerfile / OCI), from app-builder (the prompt-to-app GENERATION surface — a product can have both), and from one-click OSS-app catalogues / helm-addon-marketplace (deploy a FINISHED app as-is, not a starter you build on).

Not applicable

Organisation & security 1/8

Built-in authPlatform-provided authentication / IAM for workloads.

Not supported

SSO / SAMLEnterprise single sign-on.

Not supported

Secrets managementFirst-class secrets storage / injection.

Not supported

TeamsMulti-user team accounts.

Not supported

SharingShare a running workload/resource via link (optionally gated).

Not applicable

BYOCRuns inside the customer's own cloud account.

Not supported

Deploy into customers' VPCsA SaaS vendor uses the platform to deploy and operate ITS software inside ITS CUSTOMERS' cloud accounts / VPCs (nested or "customer BYOC"), managed from the vendor's control plane. Distinct from byoc (your own workloads in your own cloud account).

Not supported

Workload identityThe platform gives each workload its own verifiable identity (OIDC token, SPIFFE SVID, cloud IAM federation) that it exchanges for short-lived credentials, so no long-lived static secret is stored or injected. Distinct from secrets-management (stores / injects static secrets) and credential-injection-proxy (swaps real secrets in on the wire).

Not supported

Self-host / OSS coreOpen-source core that can be self-hosted.

Supported

Proposed, not verified

Capabilities the scan saw but the registry does not track yet. A key is admitted only once two distinct products exhibit it. These are not scored.

Polyglot sandboxed compilation and executionmulti-language-execution
“Support for 90+ languages” github.com

05 Agent readiness Pre-login surface · counts, not a grade

Can an agent read it?

parse-ability · docs, metadata, machine-readable surfaces

9/11

7 full · 2 partial · 82% of applicable checks

llms.txt
Supported
“Substantive /llms.txt links products, docs (ce.judge0.com), guides, references, blog, contact, research paper, Postman.”
llms-full.txt
Not supported
“/llms-full.txt returns the Next.js app shell (HTTP 404).”
robots.txt AI policy
Partially supported
“robots.txt 'Allow: /' (Disallow /api/, /_next/); default-allow, no explicit AI-UA allow or block.”
JSON-LD
Supported
“Fresh homepage HTML/RSC contains Organization, SoftwareApplication and WebSite JSON-LD.”
Sitemap
Supported
“/sitemap.xml lists 27 URLs (home, llms.txt, blog posts, authors).”
Meta tags
Supported
“Complete <title>, meta description, OpenGraph + Twitter card tags.”
Markdown negotiation
Not supported
“Accept: text/markdown returns text/html; /index.md 404. No markdown variant served.”
Content efficiency
Partially supported
“Fresh homepage:5350 bytes normalized readable text excluding script/style/noscript /182382 HTML bytes=2.93%; RSC JSON is not readable text.”
Docs discoverable
Supported
“API documentation linked first-class from the homepage + llms.txt (ce.judge0.com).”
Machine-readable pricing
Supported
“Structured pricing tiers (Pro/Ultra/Mega €27/54/107/mo with submissions/day) rendered on /#pricing.”
No anti-bot wall
Supported
“First-party homepage/docs and well-known probes fetched without challenge; linked third-party ResearchGate paper blocked and separately recorded.”

Can an agent drive it?

act-ability · APIs, SDKs, MCP, credentials, webhooks

7/11

3 full · 4 partial · 64% of applicable checks

Public API
Supported
“Rich HTTP JSON API fully documented at ce.judge0.com (submissions, languages, statuses, system/config, authorization).”
OpenAPI spec
Not supported
“No fetchable OpenAPI/Swagger spec (Slate-style docs; standard spec paths 404). Postman collection exists but is not OpenAPI.”
MCP server
Not supported
“No first-party MCP server (/.well-known/mcp 404; none in docs). Community MCP servers exist (BACH-AI-Tools, javaguru, ZefanHu) — third-party, not counted.”
SDK packages
Supported
“Official Python, Dart and JavaScript SDK README/org repositories fetched; JavaScript package @judge0/judge0-js.”
Auth documented
Supported
“Documented API auth: X-Auth-Token (authn) + X-Auth-User (authz) with an Authorize endpoint; cloud uses RapidAPI keys.”
Self-serve credentials
Partially supported
“SDK instructions use RapidAPI/dashboard API keys; no programmatic key issuance documented. Homepage RSC FAQ says Basic50/day and no card.”
Webhooks
Partially supported
“callback_url documented (Judge0 PUTs the submission to your URL on completion); no payload-signing documented.”
CLI tool
Not supported
“No official CLI; integration is via the HTTP API or the Python/Dart SDKs.”
Error model
Partially supported
“Documented submission status model (status object id/description: Accepted, Compilation Error, Runtime Error SIGSEGV, …) + auth error responses; no formal API-wide JSON error schema.”
Rate limits documented
Partially supported
“Daily submission quotas in current homepage pricing; no own API rate-limit response headers documented. Do not assume RapidAPI headers without evidence.”
Agent config files
Not supported
“No agents.md / /.well-known/agent / skills listing (llms.txt counts under parse_ability).”

06 Coding harnesses Which agents and IDEs are documented to run here

Advertised integrations 0

The public surface names no coding harness as supported or documented-to-run-here.

Plausible compatibility 0

Derived, not stored: the product passes SSH access, so any CLI coding agent is installable inside it. This is plausible compatibility, not a supported integration.

No general shell access documented, so nothing is derived. Absence is not unsupported.

07 Compliance & regions Standards held, with ordinal rigor; never a score

Certifications held 0

No attestations found on the public surface. Empty means nothing is advertised, after checking, not that nothing was checked.

Regions —

Regions are not disclosed on the public surface.

Hosted workload regions not disclosed on fetched homepage/pricing/docs. Company address is Zagreb, Croatia; that is not a hosting-location guarantee. Self-host placement is operator-controlled.

Legal

Privacy notice

08 Open source GPL-3.0 · fetched by machine, not quoted from marketing

Licence & repository

Licence: GPL-3.0OSI
Primary language: HTML
Stars: 4,474
Forks: 945
Created: 27 Jan 2017
Archived: No

Activity

Last commit: 8 Oct 2026
Latest release: v1.13.1 · 17 Apr 2024
Issues open / closed: 171 / 305 · 64% closed

Latest CE release v1.13.1 (2024-04-17); Extra CE tag v1.13.1-extra followed seconds later. Previous v1.13.0 dates to March 2021. Master pushed 2026-10-08; release tags lag current development.

Fetched via gh on 14 Oct 2026.

Self-hosting

Methods: dockercompose
You operate: postgresredis

Free under GPL-3.0 plus operator infrastructure. Linux-tested Docker Compose server/worker plus PostgreSQL 16.2 and Redis 7.2.4. Operator owns security updates and availability rather than hosted support. v1.13.1 changelog fixes three critical sandbox vulnerabilities in <=1.13.0 (CVE-2024-28185, CVE-2024-28189, CVE-2024-29021).

Documentation signals 7/8

SupportedQuickstart
SupportedAPI reference
SupportedSelf-host guide
SupportedChangelog
Not supportedOpenAPI
Supportedllms.txt
SupportedExamples
SupportedArchitecture doc

09 Company & presence Facts only, not scored

Company

Headquarters: Zagreb, Croatia
Founded: 2016
Team size: Small (undisclosed)
Hiring: No current hiring board established

Notable people

Herman Zvonimir Došilović
Igor Mekterović

Activity

Last release: v1.13.1 (2024-04-17) github.com
Last blog post: 2026-03-04 judge0.com

Presence 8

Links found on the public surface scanned; not an exhaustive search.

10 Sources & method How this entry was produced

Public surface only

Everything here was read from judge0.com's unauthenticated pages, docs, pricing and repository on 14 Oct 2026. Nothing behind a login was used.

Statuses, not scores

Capabilities are pass, partial or fail against a written rubric (features v21). “Not assessed” means the scan predates the key.

Confidence is separate

Each fact carries its own confidence. Low-confidence facts are shown, never hidden, so you can weigh them.

Schema: scan v5
Features registry: v21
Keys tracked today: 61
Assessed on this entry: 61

Something wrong on this page?

Nearby in the atlas

All Sandbox products →