Code & AI agent sandboxes: read the guide

Runtime Cloud

HostedSandbox

The AI agent harness for payment teams

Homepage Docs Pricing

Scanned 15 Oct 2026 · Schema v5 · features v21

From: Free
Approval-only free Pilot, then custom Enterprise
Free tier: Yes
No card required.
Isolation: Not disclosed
the public docs do not say
Regions: —
Provider diversity is advertised, not a customer-selectable hosted-region list. Private infrastructure is a commercial option, not OSS Cloud.
Capabilities: 22 / 61
8 partial · 31 fail · 0 not assessed
Agent readiness: 11/11 · 8/11
read · drive, pre-login surface

Advertised for

Payment operations · Risk investigations · Compliance and support · Coding agent sessions · Background agents · Application deployment

Built for

Mixed, then developers

· Homepage: payment operations, risk, compliance and support teams; anyone describes a job and attaches an SOP.
· Approval-only engineer-guided pilot, Slack/email/scheduled triggers and human sign-off.

01 Pricing Approval-only free Pilot, then custom Enterprise

Tier	EntryPilot	Enterprise
Price	Free, approved teams only	Custom

Custom contract; no public compute/token rates·Card required: No·runtm.com

02 Website design Desktop public website · assessed 15 Oct 2026

Complete assessment.

The landing and pricing pages pair warm off-white surfaces with dark green typography, monospaced navigation and restrained outlines. The landing adds a large character-like architectural illustration; docs switch to a neutral, text-led three-column reading layout.

Editorial minimalism
Retro-computing

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

Not disclosedthe public docs do not say

Persistence

Filesystem retained across pause/resume; destroyed sessions wiped

Snapshots / forks

Filesystem template snapshots from sessions; full memory/process fork not established

Resources & limits

Storage

Session filesystem persists across pause; template filesystem images; deployment volumes survive redeploys

Limits & quotas

Approval-only Pilot: one team/workflow, base 4 vCPU / 4 GB. Enterprise: custom, unlimited sessions/users; quotas checked before deployment.

GPU

Access

Deploy interface

dashboardREST APIWebSocketsruntm-api CLISlack/Linear/GitHub/email/WhatsApp/SMS/scheduled triggers

SDK languages

None

Network & secrets

Egress controls

Yes

Secrets

Yes

Bring your own cloud

Enterprise/private infrastructure advertised; AWS account execution explicitly offered

Placement & use

Jurisdiction

Hosted regions not disclosed

Advertised workloads

Payment operationsRisk investigationsCompliance and supportCoding agent sessionsBackground agentsApplication deployment

04 Capabilities 22 pass · 8 partial · 31 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 2/11

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

Partially 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.

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).

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.

Partially supported

Networking & delivery 4/9

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Supported

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

Partially supported

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

Not 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 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.

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 3/10

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Not supported

CLIOfficial command-line tool.

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 supported

AI & agents 8/12

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

Supported

Agent skillsInstallable / declarable agent skills or tools.

Supported

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

Supported

MCP serverExposes a Model Context Protocol server for agents.

Supported

MCP clientActs as an MCP client / consumes MCP tools.

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.

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 0/4

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 2/6

Scheduled tasksCron / scheduled job primitive.

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).

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 3/9

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

Not supported

SSO / SAMLEnterprise single sign-on.

Partially supported

Secrets managementFirst-class secrets storage / injection.

Supported

TeamsMulti-user team accounts.

Supported

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

Supported

BYOCRuns inside the customer's own cloud account.

Partially 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).

Partially 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.

Not 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.

Bring your own sandboxbyo-sandbox-provider
“Already run Firecracker, gVisor, or a custom execution layer? Runtime can use it instead of ours.” runtm.com
Budgets and spend limitsagent-cost-governance
“Cap cost per session and spend per user per day or month. Hard limits block, soft limits warn.” runtm.com
Sensitive-action human approvalshuman-action-approval
“Sensitive actions pause for a human sign-off from the dashboard or Slack before anything happens.” runtm.com
Deterministic tool-call hookstool-policy-hooks
“Hooks run your own checks before and after each tool call, with a deterministic script or a model. Command deny lists always win.” runtm.com

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

Can an agent read it?

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

11/11

10 full · 1 partial · 100% of applicable checks

llms.txt
Supported
“https://docs.runtm.com/llms.txt and apex /llms.txt: substantive current docs links.”
llms-full.txt
Supported
“https://docs.runtm.com/llms-full.txt: HTTP 200, 1,248,639 bytes; bounded pointer/excerpt plus scored individual docs retained.”
robots.txt AI policy
Supported
“robots.txt explicitly allows GPTBot, ClaudeBot, Google-Extended and other AI crawlers; prior blocking policy changed.”
JSON-LD
Supported
“Homepage JSON-LD Organization, WebSite, SoftwareApplication and FAQPage.”
Sitemap
Supported
“/sitemap.xml HTTP 200; substantive multi-page sitemap.”
Meta tags
Supported
“Runtime - The AI agent harness for payment teams; descriptive title, description and OG in retained head.”
Markdown negotiation
Partially supported
“Homepage Accept:text/markdown remains text/html; docs introduction.md HTTP 200 text/markdown.”
Content efficiency
Supported
“Retained homepage original 295131 bytes; readable text 18243 UTF-8 bytes = 6.18%, above 5% rubric threshold.”
Docs discoverable
Supported
“Homepage header Docs link https://docs.runtm.com is server-rendered.”
Machine-readable pricing
Supported
“Structured Pilot/Enterprise cards with free approval-only pilot and custom enterprise; no numeric paid rate.”
No anti-bot wall
Supported
“Homepage and substantive docs fetchable without public challenge. No login attempted.”

Can an agent drive it?

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

8/11

7 full · 1 partial · 73% of applicable checks

Public API
Supported
“Cloud API overview plus REST endpoint reference, WebSockets, scopes, payloads.”
OpenAPI spec
Not supported
“No valid OpenAPI in saved docs/app/common homepage probes (404 or login HTML); api-catalog HTTP 404.”
MCP server
Supported
“docs /.well-known/mcp/server-card.json HTTP 200 advertises Runtime Docs MCP at https://runtm.main-kill-isr.mintlify.me/mcp with search/retrieval tools. Documentation-only, not control MCP.”
SDK packages
Not supported
“Cloud REST examples in Python/JavaScript and Go CLI do not establish official SDK packages; OSS pip runtm is separate.”
Auth documented
Supported
“cloud-api/patterns/authentication.md documents scoped personal/org keys, rotation/revocation, expirations and verification.”
Self-serve credentials
Not supported
“Pricing access is approved manually. API docs: keys created from dashboard only; no programmatic key-creation endpoint. No signup attempted.”
Webhooks
Partially supported
“Outbound prompt.completed / prompt.timed_out payloads documented; 5-second timeout, no automatic retry, no signing documented.”
CLI tool
Supported
“Official installable Go runtm-api CLI wraps hosted API and ships embedded skill files; not OSS deployment CLI.”
Error model
Supported
“cloud-api/errors.md documents JSON detail response and status codes.”
Rate limits documented
Supported
“cloud-api/rate-limits.md documents limits, X-RateLimit headers and Retry-After.”
Agent config files
Supported
“Embedded CLI skills plus docs well-known agent-card.json and agent-skills/index.json discovery.”

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

Advertised integrations 7

Claude Code Anthropic
Supported
“Claude Code”
Source docs.runtm.com
Codex CLI OpenAI
Supported
“Codex”
Source docs.runtm.com
OpenCode opencode
Supported
“OpenCode”
Source docs.runtm.com
GitHub Copilot GitHub
Supported
“GitHub Copilot”
Source docs.runtm.com
Cursor Anysphere
Supported
“Cursor”
Source docs.runtm.com
Devin Cognition
Supported
“Devin”
Source docs.runtm.com
Gemini CLI Google
Supported
“Gemini”
Source docs.runtm.com

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.

Provider diversity is advertised, not a customer-selectable hosted-region list. Private infrastructure is a commercial option, not OSS Cloud.

Legal

Privacy notice Terms of service

08 Company & presence Facts only, not scored

Company

Headquarters: San Francisco, US
Founded: 2026
Team size: Not disclosed
Hiring: Hiring

Notable people

Gus Trigos, CEO
Carlos Volante, CTO

Activity

Last release: Cloud release-notes page available; OSS sibling release is not Cloud release cadence docs.runtm.com
Last blog post: How to Build an AI Agent Harness with the Runtime API — 2026-10-08 runtm.com

Presence 6

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

09 Sources & method How this entry was produced

Public surface only

Everything here was read from runtm.com's unauthenticated pages, docs, pricing and repository on 15 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 →