Code & AI agent sandboxes: read the guide

sandboxd (formerly sandboxed)

Open source toolSandbox

Open-source, self-hosted AI app builder.

Homepage Docs Repository

Scanned 12 Oct 2026 · Schema v5 · features v21

Licence: MIT
Self-hosted; you pay for the infrastructure.
Free tier: Free to run
Isolation: Container
shares the host kernel
Regions: —
Not disclosed on the public surface.
Capabilities: 17 / 61
9 partial · 26 fail · 0 not assessed
Agent readiness: 8/10 · 5/10
read · drive, pre-login surface

Advertised for

AI app builder backends and prompt generated apps · Per user or per branch developer sandboxes · Ready made OSS apps, Node/Python web servers and background workers · Headless Claude Code/OpenCode tasks

Built for

Developers, then semi-technical builders

· README: API-first — everything is a /v1 call; Go/Docker/Traefik/Linux operator requirements.
· One-command self-host installer; detailed isolation, API and configuration reference.
· Own infrastructure/keys; operator hardening required.

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

Isolation & lifecycle

Isolation primitive

Containershares the host kernel

Persistence

Workspace bind mounts and SQLite state survive stop and reboot; root filesystem read-only, /tmp ephemeral.

Snapshots / forks

Workspace snapshots, app fork/restore, and automatic per-task Git checkpoints; directory-storage backend still experimental. No memory/process-state restoration claimed.

Resources & limits

Storage

Persistent per-sandbox workspace directory; SQLite WAL control-plane state. User apps may bring embedded SQLite; no managed Postgres/Redis/object-store provisioner.

Limits & quotas

Hard memory/PID/fd limits; optional cgroup memory.high; idle reaper default 2100 seconds plus memory-pressure reaper. No per-workspace disk quota; single host and one public preview endpoint per sandbox. Configuration says /v1 requires session/bearer key by default, despite stale contrary AGENTS/OpenAPI introduction.

GPU

Not documented

Access

Deploy interface

apidashboardtemplatecontainer-image

SDK languages

None

Network & secrets

Egress controls

Default egress is open/unlogged. nftables subsystem exists but is compiled off in self-hosted Compose build; domain-level per-sandbox allowlist is roadmap. Operator firewall/proxy required.

Secrets

App secrets encrypted at rest and write-only. Model credentials stay in control plane and are injected by auth proxy; sandbox receives dummy credentials. Disabling proxy enables legacy credential-dir mount.

Bring your own cloud

Placement & use

Jurisdiction

Advertised workloads

AI app builder backends and prompt generated appsPer user or per branch developer sandboxesReady made OSS apps, Node/Python web servers and background workersHeadless Claude Code/OpenCode tasks

02 Capabilities 17 pass · 9 partial · 26 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 3/10

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

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 supported

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).

Partially 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.

Partially supported

GPU computeGPU-backed instances available.

Not supported

Multi-regionCompute placeable in more than one geographic region.

Not applicable

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

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 supported

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

Not supported

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.

Supported

Networking & delivery 2/7

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Partially supported

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

Supported

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

Partially supported

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

Supported

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).

Partially 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.

Partially supported

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

Not supported

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 3/9

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Supported

CLIOfficial command-line tool.

Not supported

SDKOfficial client library/libraries.

Not supported

SSH accessDirect SSH into workloads.

Not supported

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

Supported

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

Partially supported

Private container registryHosted private image registry.

Not supported

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 5/12

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

Not supported

Agent skillsInstallable / declarable agent skills or tools.

Not supported

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

Supported

MCP serverExposes a Model Context Protocol server for agents.

Not supported

MCP clientActs as an MCP client / consumes MCP tools.

Not supported

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 supported

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

Supported

BYOK for LLMsBring-your-own LLM provider keys.

Supported

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 supported

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 supported

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).

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).

Supported

Data 0/1

First-party databasePlatform-provided managed database.

Not supported

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 0/6

Scheduled tasksCron / scheduled job primitive.

Not supported

Durable workflowsDurable execution / long-running workflow primitive.

Not supported

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 supported

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).

Partially 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 supported

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 supported

Organisation & security 4/7

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

Supported

SSO / SAMLEnterprise single sign-on.

Not supported

Secrets managementFirst-class secrets storage / injection.

Supported

TeamsMulti-user team accounts.

Partially supported

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

Supported

BYOCRuns inside the customer's own cloud account.

Not applicable

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 applicable

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.

Interactive browser terminal (PTY over WebSocket)web-shell
“/v1/sandboxes/{id}/terminal” raw.githubusercontent.com

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

Can an agent read it?

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

8/10

8 full · 0 partial · 80% of applicable checks

llms.txt
Supported
“https://sandboxd.io/llms.txt: substantive docs, API and ancillary-pricing pointers.”
llms-full.txt
Not supported
“https://sandboxd.io/llms-full.txt returns 404 HTML; no modular full-text set advertised in llms.txt.”
robots.txt AI policy
Supported
“https://sandboxd.io/robots.txt explicitly allows GPTBot, ClaudeBot, PerplexityBot and Google-Extended.”
JSON-LD
Supported
“Homepage SoftwareApplication JSON-LD includes name, description and zero-price MIT offer.”
Sitemap
Supported
“https://sandboxd.io/sitemap.xml is substantive nontrivial XML, also linked in robots.”
Meta tags
Supported
“Self-hosted, open-source AI app builder | sandboxd; descriptive meta and OG tags.”
Markdown negotiation
Not supported
“Accept: text/markdown still returns text/html; /.md returns 404 HTML.”
Content efficiency
Supported
“Readable homepage text ~19.1% of 23635 HTML bytes after ignoring script/style; SSR content.”
Docs discoverable
Supported
“Docs visible in header with direct /what-is-sandboxd URL; no JS needed.”
Machine-readable pricing
Not applicable
“No first-party hosted compute tier. Ancillary Cloud/Managed prices are public HTML and linked in meta, not runtime pricing.”
No anti-bot wall
Supported
“curl successfully fetches public landing/docs/well-known without challenge. Initial urllib 403 recovered by curl and required sequential foxcrawl retry: statusCode 200, blocked false; one informational JS error.”

Can an agent drive it?

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

5/10

4 full · 1 partial · 50% of applicable checks

Public API
Supported
“https://sandboxd.io/reference/api documents self-hosted tenant-scoped /v1 API.”
OpenAPI spec
Supported
“https://raw.githubusercontent.com/tastyeffectco/sandboxd/main/docs/openapi.yaml fetchable OpenAPI 3.0.3.”
MCP server
Not supported
“No documented Model Context Protocol control server; /.well-known/mcp 404 HTML.”
SDK packages
Not supported
“No official client SDK packages advertised in docs/repository.”
Auth documented
Supported
“https://sandboxd.io/reference/configuration documents bearer/scoped key and session auth; docs/agent-auth.md covers provider OAuth/proxy. Stale OpenAPI intro auth-default caveat noted.”
Self-serve credentials
Not applicable
“No hosted signup/key-issuance service; operator initializes self-hosted token/session configuration.”
Webhooks
Not supported
“SSE task/events are not outbound signed webhooks; none documented.”
CLI tool
Not supported
“Installer/server daemon and curl examples, not official client CLI.”
Error model
Supported
“OpenAPI Error.error has code, message, retryable.”
Rate limits documented
Not supported
“No API request rate-limit response headers/limits documented in reviewed spec/configuration; resource quotas are different.”
Agent config files
Partially supported
“https://raw.githubusercontent.com/tastyeffectco/sandboxd/main/AGENTS.md plus platform/per-app grounding prompt; no public well-known agent endpoint or skill listing.”

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

Advertised integrations 2

Claude Code Anthropic
Supported
“Both CLIs (claude, opencode) are pre-installed in every sandbox”
Source sandboxd.io
OpenCode opencode
Supported
“opencode is the default when a task omits agent”
Source sandboxd.io

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.

05 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 —

No region list captured.

Legal

Privacy notice

06 Open source MIT · fetched by machine, not quoted from marketing

Licence & repository

Licence: MITOSI
Primary language: Go
Stars: 968
Forks: 65
Created: 3 Jun 2026
Archived: No

Activity

Last commit: 12 Oct 2026
Latest release: v0.3.22 · 12 Oct 2026
Issues open / closed: 7 / 20 · 74% closed

Recent fetched tags include v0.3.22 (Oct 12), v0.3.21 (Sep 20), v0.3.20/v0.3.19 (Aug 28); patch releases in a pre-1.0 beta, not a promised schedule.

Fetched via gh on 12 Oct 2026.

Self-hosting

Methods: composesource-build
You operate: dockergit

MIT software is free plus your own hardware/infrastructure and optional LLM provider usage. Linux Docker + Compose; amd64/arm64; macOS Docker Desktop best-effort. Single host, hardened runc by default; optional experimental gVisor requires operator installation. Not a hardware VM boundary. Default egress open, nftables subsystem compiled off; no per-workspace disk quota; snapshots experimental. Paid Managed installs/operates this same OSS build on YOUR server, not vendor compute ($199 setup, $79/month; founding $49/month). Cloud is optional paid tunnel/public URL ($4.99/server/month launch, normal $9.99), not hosting. No managed compute exists yet.

Documentation signals 8/8

SupportedQuickstart
SupportedAPI reference
SupportedSelf-host guide
SupportedChangelog
SupportedOpenAPI
Supportedllms.txt
SupportedExamples
SupportedArchitecture doc

07 Company & presence Facts only, not scored

Company

Headquarters: Not disclosed
Founded: —
Team size: Not disclosed
Hiring: unknown

Activity

Last release: v0.3.22 (2026-10-12) github.com
Last blog post: 2026-09-20 sandboxd.io

Presence 4

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

08 Sources & method How this entry was produced

Public surface only

Everything here was read from sandboxd.io's unauthenticated pages, docs, pricing and repository on 12 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 →