Code & AI agent sandboxes: read the guide

Gondolin

Open source toolSandbox

Local Linux micro-VMs with programmable network and filesystem control.

Homepage Docs Repository

Scanned 12 Oct 2026 · Schema v5 · features v21

Licence: Apache-2.0
Self-hosted; you pay for the infrastructure.
Free tier: Free to run
Isolation: Virtual machine
hypervisor, or nothing at all
Regions: —
Not disclosed on the public surface.
Capabilities: 15 / 61
2 partial · 39 fail · 0 not assessed
Agent readiness: 5/10 · 5/6
read · drive, pre-login surface

Advertised for

Agent generated shell/code execution · Disposable task/turn sandboxes · Local guest HTTP services · Headless Chromium browser automation via Browser Use · Pi tool execution

Built for

Developers, then technical

· https://github.com/earendil-works/gondolin code-first CLI/TypeScript onboarding
· https://earendil-works.github.io/gondolin/security/ VM, DNS, VFS, TLS policy vocabulary

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

Isolation & lifecycle

Isolation primitive

Virtual machinehypervisor, or nothing at all

Persistence

Default rootfs ephemeral; durable RealFSProvider host mounts; qcow2 disk checkpoints. VFS/tmpfs are not checkpointed.

Snapshots / forks

Disk-only qcow2 checkpoints stop the original VM; multiple resumes use temporary CoW overlays and fresh boots. Matching guest assets required.

Resources & limits

Storage

Host-backed programmable VFS via FUSE; MemoryProvider, RealFSProvider, ReadonlyProvider, ShadowProvider; readonly/memory/cow rootfs modes and configurable disk size.

Limits & quotas

Configurable sandbox.cpus, sandbox.memory and rootfs.size; capacity depends on operator host. No complete DoS isolation. No full-memory snapshots, Windows, HTTP/2/3 or default generic UDP.

GPU

Not documented

Access

Deploy interface

clisdkcontainer-image

SDK languages

TypeScriptJavaScript

Network & secrets

Egress controls

Host-side JavaScript HTTP/TLS mediation, allowedHosts, default internal-range blocking, DNS-rebinding defense; optional allowlisted SSH and explicitly mapped TCP.

Secrets

Host-held placeholder credentials injected into allowed outbound request headers (optional queries); never present as real values in guest env. Bodies/path/response substitution excluded; custom host hooks can observe actual values.

Bring your own cloud

Placement & use

Jurisdiction

Advertised workloads

Agent generated shell/code executionDisposable task/turn sandboxesLocal guest HTTP servicesHeadless Chromium browser automation via Browser UsePi tool execution

02 Capabilities 15 pass · 2 partial · 39 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 4/10

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).

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 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.

Partially 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 2/9

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Not supported

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

Supported

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

Not supported

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

Not supported

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

Not supported

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 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 supported

Developer access 5/10

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Not supported

CLIOfficial command-line tool.

Supported

SDKOfficial client library/libraries.

Supported

SSH accessDirect SSH into workloads.

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.

Not 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 supported

AI & agents 2/12

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

Not supported

Agent skillsInstallable / declarable agent skills or tools.

Supported

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

Not 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).

Not supported

BYOK for LLMsBring-your-own LLM provider keys.

Not 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).

Not supported

Data 0/4

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 supported

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 supported

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 supported

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 2/5

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

Not supported

SSO / SAMLEnterprise single sign-on.

Not applicable

Secrets managementFirst-class secrets storage / injection.

Supported

TeamsMulti-user team accounts.

Not applicable

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

Not 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.

Programmable VFS filesystem policiesprogrammable-filesystem-policy
“The VFS is backed by host-side providers (JavaScript objects) and is mounted into the guest via FUSE.” earendil-works.github.io

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

Can an agent read it?

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

5/10

3 full · 2 partial · 50% of applicable checks

llms.txt
Not supported
“https://earendil-works.github.io/gondolin/llms.txt and host-root llms.txt: HTTP 404.”
llms-full.txt
Not supported
“https://earendil-works.github.io/gondolin/llms-full.txt and host-root llms-full.txt: HTTP 404.”
robots.txt AI policy
Partially supported
“Project and host-root robots.txt return HTTP 404; default-allow.”
JSON-LD
Not supported
“https://earendil-works.github.io/gondolin/ has no application/ld+json script.”
Sitemap
Not supported
“https://earendil-works.github.io/gondolin/sitemap.xml returns HTTP 200 with empty <urlset> (zero URLs).”
Meta tags
Not supported
“Homepage title Gondolin Documentation - Gondolin exists; no description or OpenGraph metadata.”
Markdown negotiation
Partially supported
“Accept: text/markdown returns HTML; site index.md/sdk.md 404. Homepage View source links expose raw Markdown docs on GitHub.”
Content efficiency
Supported
“Homepage readable text/HTML = 12.0503%; >5% server-rendered threshold.”
Docs discoverable
Supported
“Homepage is docs index with first-class CLI/SDK/security/workload links in server-rendered HTML.”
Machine-readable pricing
Not applicable
“Self-host-only Apache-2.0 tool, no hosted pricing tiers.”
No anti-bot wall
Supported
“All required public documentation and raw source pages fetched HTTP 200 without a challenge; ordinary missing paths returned 404.”

Can an agent drive it?

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

5/6

2 full · 3 partial · 83% of applicable checks

Public API
Supported
“https://earendil-works.github.io/gondolin/sdk/ documents VM.create, exec, fs, network, checkpoint APIs (local API).”
OpenAPI spec
Not applicable
“No hosted HTTP API; local TypeScript API. Probed openapi.json/swagger.json return 404; SDK intro links no REST spec.”
MCP server
Not supported
“No documented Model Context Protocol control server; .well-known/mcp 404.”
SDK packages
Partially supported
“One official TypeScript/JavaScript npm SDK @earendil-works/gondolin.”
Auth documented
Not applicable
“Local runtime requires no service-account API authentication. Upstream secret documentation is not Gondolin API authentication.”
Self-serve credentials
Not applicable
“No hosted account/API credential issuance.”
Webhooks
Not applicable
“Local process control plane, no hosted event webhook endpoint; JS hooks are not webhooks.”
CLI tool
Supported
“https://earendil-works.github.io/gondolin/cli/ official npx CLI for bash/exec/list/attach/snapshot/build.”
Error model
Partially supported
“https://earendil-works.github.io/gondolin/sdk-vm/ documents ExecResult exitCode/signal/stdout/stderr and abort rejection; no common JSON error envelope.”
Rate limits documented
Not applicable
“No hosted API or provider-imposed request-rate quotas; CPU/memory are local VM configuration.”
Agent config files
Partially supported
“https://github.com/earendil-works/gondolin/blob/main/AGENTS.md available; .well-known/agent HTTP 404, no additional agent-config/skill discovery surface found.”

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

Advertised integrations 1

Pi earendil-works
Supported
“This extension overrides pi's built-in `read`/`write`/`edit`/`bash` tools so they execute inside a Gondolin micro-VM instead of on the host.”
Source github.com

Plausible compatibility 14

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.

Aider
Amp
Antigravity
Claude Code
Codex CLI
Devin
Droid
Gemini CLI
Goose
Hermes Agent
Kilo Code
Kiro CLI
OpenCode
Qwen Code

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.

06 Open source Apache-2.0 · fetched by machine, not quoted from marketing

Licence & repository

Licence: Apache-2.0OSI
Primary language: TypeScript
Stars: 2,281
Forks: 140
Created: 3 Feb 2026
Archived: No

Activity

Last commit: 4 Oct 2026
Latest release: sandbox-helpers--0.13.0 · 4 Oct 2026
Issues open / closed: 19 / 67 · 78% closed

Latest GitHub release is sandbox helper bundle 0.13.0; runtime v0.13.0 published 2026-10-04, previous runtime v0.12.0 2026-05-19 and v0.11.0 2026-05-18. Image/helper/runtime tags are published independently; not a uniform cadence.

Fetched via gh on 12 Oct 2026.

Self-hosting

Methods: package-managersource-build
You operate: nodejsqemu

Free under Apache-2.0 plus operator hardware/infrastructure. macOS/Linux only; ARM64 most tested, Linux x86_64 krun smoke builds documented. QEMU default, libkrun optional/experimental; guest assets ~200MB+ cached on first use. Custom image builds require cpio/lz4/e2fsprogs; optional OCI roots require Docker/Podman. No managed hosting/control plane. Disk checkpoints exclude RAM, tmpfs and VFS; no HTTP/2/3, QUIC/WebRTC in default network model. Security docs explicitly exclude complete DoS isolation.

Documentation signals 5/8

SupportedQuickstart
SupportedAPI reference
SupportedSelf-host guide
Not supportedChangelog
Not supportedOpenAPI
Not supportedllms.txt
SupportedExamples
SupportedArchitecture doc

07 Company & presence Facts only, not scored

Company

Headquarters: Not disclosed
Founded: —
Team size: Not disclosed
Hiring: Hiring: Member of the Technical Staff, Founder’s Office, Go to Market

Activity

Last release: — github.com
Last blog post: —

Presence 3

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 earendil-works.github.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 →