Need help with your APIs? I offer API discovery, governance & evangelism services. Explore services →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC
Runloop website screenshot

Runloop

Runloop is the AI Agent Accelerator — secure code sandboxes (Devboxes), evaluation infrastructure (Benchmarks, Scenarios), and production-grade orchestration for AI coding agents at enterprise scale. The platform provides a single REST API and matched Python/TypeScript SDKs covering Devbox lifecycle, Blueprint image building, Snapshot branching, Agent registry, Axon event streams with Broker bridges, Storage Objects, Secrets, Network Policies, Agent Gateways, MCP Configs, and a turnkey eval framework (SWE-Bench Verified, SWE-smith, custom benchmarks). Runloop runs on a custom bare-metal hypervisor with microVM-level isolation and is SOC 2 Type II, HIPAA, and GDPR compliant, with VPC deployment available for regulated workloads. Founded 2023 by Jonathan Wall (Google File System lead, Google Wallet co-founder, Index CTO acquired by Stripe).

agent ready

Solid contracts, transparent operations, and an easy start — typically complete on four or five facets with one clear soft spot.

Kin Score

API Evangelist profiles Runloop the way a machine reads it — 95 machine-readable artifacts across 24 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.

Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Runloop scores 68.3/100 (strong), with a separate agent-readiness read of 48/100 (agent ready). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.

Kin Score

This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 68.3/100 · strong
Contract Quality 18.8 / 25
Developer Ergonomics 12.6 / 20
Commercial Clarity 13.2 / 20
Operational Transparency 4.1 / 13
Governance 10.4 / 12
Discoverability 9.3 / 10
Agent readiness — 48/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 15 / 15
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 0 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3

How we profile Runloop

Each block below is one kind of artifact we hold for Runloop. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.

APIs 24

Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.

Individual APIs this provider publishes, each with its own machine-readable definition.

Runloop agents API

The agents API from Runloop — 5 operation(s) for agents.

Runloop apikeys API

The apikeys API from Runloop — 1 operation(s) for apikeys.

Runloop axons API

The axons API from Runloop — 7 operation(s) for axons.

Runloop Benchmark API

The Benchmark API from Runloop — 25 operation(s) for benchmark.

Runloop Blueprint API

The Blueprint API from Runloop — 11 operation(s) for blueprint.

Runloop Blueprint-Lifecycle API

The Blueprint-Lifecycle API from Runloop — 3 operation(s) for blueprint-lifecycle.

Runloop Blueprint-ObservabilityTools API

The Blueprint-ObservabilityTools API from Runloop — 2 operation(s) for blueprint-observabilitytools.

Runloop Devbox API

The Devbox API from Runloop — 40 operation(s) for devbox.

Runloop Devbox-FileTools API

The Devbox-FileTools API from Runloop — 4 operation(s) for devbox-filetools.

Runloop Devbox-Lifecycle API

The Devbox-Lifecycle API from Runloop — 7 operation(s) for devbox-lifecycle.

Runloop Devbox-NetworkTools API

The Devbox-NetworkTools API from Runloop — 4 operation(s) for devbox-networktools.

Runloop Devbox-ObservabilityTools API

The Devbox-ObservabilityTools API from Runloop — 3 operation(s) for devbox-observabilitytools.

Runloop Devbox-PersistenceTools API

The Devbox-PersistenceTools API from Runloop — 11 operation(s) for devbox-persistencetools.

Runloop Devbox-ShellTools API

The Devbox-ShellTools API from Runloop — 9 operation(s) for devbox-shelltools.

Runloop executions API

The executions API from Runloop — 2 operation(s) for executions.

Runloop gateway-configs API

The gateway-configs API from Runloop — 3 operation(s) for gateway-configs.

Runloop mcp-configs API

The mcp-configs API from Runloop — 3 operation(s) for mcp-configs.

Runloop network-policies API

The network-policies API from Runloop — 3 operation(s) for network-policies.

Runloop objects API

The objects API from Runloop — 8 operation(s) for objects.

Runloop restricted_keys API

The restricted_keys API from Runloop — 1 operation(s) for restricted_keys.

Runloop Scenario API

The Scenario API from Runloop — 17 operation(s) for scenario.

Runloop ScenarioScorer API

The ScenarioScorer API from Runloop — 2 operation(s) for scenarioscorer.

Runloop secrets API

The secrets API from Runloop — 3 operation(s) for secrets.

Runloop streaming API

The streaming API from Runloop — 2 operation(s) for streaming.

Scroll within the panel for all 24 ·

Postman Collections 13

A runnable collection turns the contract into something a developer can execute in seconds. We profile them because the fastest way to trust an API is to make a real call against it.

Ready-to-run Postman collections for exercising this provider's APIs.

Scroll within the panel for all 13 ·

Open Collections 14

Open, tool-agnostic collections carry the same runnable value as Postman without locking you to one client — the portable, forkable form of the same exercise.

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

Runloop Agents API

OPEN COLLECTION

RunLoop API

OPEN COLLECTION

Runloop API Keys API

OPEN COLLECTION

Runloop Axons API

OPEN COLLECTION

Runloop Benchmark API

OPEN COLLECTION

Runloop Blueprint API

OPEN COLLECTION

Runloop Devbox API

OPEN COLLECTION

Runloop Executions API

OPEN COLLECTION

Runloop MCP Configs API

OPEN COLLECTION

Runloop Objects API

OPEN COLLECTION

Runloop Scenario API

OPEN COLLECTION

Runloop Secrets API

OPEN COLLECTION

Scroll within the panel for all 14 ·

Arazzo Workflows 10

Real integrations are rarely a single call. Arazzo describes the multi-step sequences — auth, then create, then confirm — so both a human and an agent can follow the choreography, not just the endpoints.

Multi-step API workflows described with the Arazzo specification.

Runloop Bootstrap a Devbox from an Object Artifact

Create and complete a storage object, generate its download URL, then boot a devbox and pull the artifact into it.

ARAZZO

Runloop Build Blueprint and Launch Devbox

Build a custom blueprint image, poll until the build completes, then launch a devbox from it and wait for running.

ARAZZO

Runloop Create Scenario and Run It

Define a repeatable AI coding evaluation scenario, start a run of it, poll until it is scored, then complete the run.

ARAZZO

Runloop Graceful Snapshot and Shutdown

Synchronously snapshot a running devbox's disk to preserve its state, then permanently shut the devbox down.

ARAZZO

Runloop Provision Devbox and Run a Command

Create a devbox, wait for it to reach running, then execute a shell command asynchronously and wait for completion.

ARAZZO

Runloop Publish an Object Artifact

Create a storage object, mark its upload complete to make it read-only, then generate a presigned download URL for it.

ARAZZO

Runloop Score a Running Scenario Run

Start a run of an existing scenario, wait for it to be running, trigger scoring, then complete the run.

ARAZZO

Runloop Snapshot and Restore a Devbox

Take an asynchronous disk snapshot of a running devbox, poll until it completes, then launch a new devbox from that snapshot.

ARAZZO

Runloop Suspend and Resume a Devbox

Suspend a running devbox to free compute, wait until it is suspended, then resume it and wait until it is running again.

ARAZZO

Runloop Write, Execute, and Read a File on a Devbox

Boot a devbox, write a file into it, run a command that transforms the file, then read the resulting contents back.

ARAZZO

Scroll within the panel for all 10 ·

Pricing Plans 1

Pricing is part of the interface. Machine-readable plans tell you what a tier costs and includes before you commit — one of the six things the Kin Score reads for commercial clarity.

Published pricing tiers and plan structures.

Rate Limits 1

Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.

Documented rate limits and quota policies.

Runloop Ai Rate Limits

0 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.

Cost, billing, and metering signals for API financial operations.

Semantic Vocabularies 1

JSON-LD contexts give the data shared meaning across APIs. We profile them because semantics are what let a machine reconcile 'customer' here with 'customer' somewhere else.

JSON-LD contexts and semantic vocabularies used across these APIs.

Runloop Context

52 classes · 19 properties

JSON-LD

Spectral Rules 2

Governance rulesets we run against this provider's specs — the automated checks behind parts of the score. Profiling them makes the quality bar explicit and re-runnable, not a matter of opinion.

Runloop API Rules

6 rules · 5 warnings

SPECTRAL

Runloop API Rules

8 rules · 1 errors · 5 warnings

SPECTRAL

JSON Schema 18

Standalone JSON Schema definitions describe the data models behind the API. We profile them so the shapes are validatable on their own — useful long after a single request is forgotten.

Standalone JSON Schema definitions for this provider's data models.

Runloop Agent

6 properties

JSON SCHEMA

Runloop Api Key

4 properties

JSON SCHEMA

Runloop Axon

3 properties

JSON SCHEMA

Runloop Benchmark Run

11 properties

JSON SCHEMA

Runloop Benchmark

10 properties

JSON SCHEMA

Runloop Blueprint

13 properties

JSON SCHEMA

Runloop Devbox

18 properties

JSON SCHEMA

Runloop Execution

5 properties

JSON SCHEMA

Runloop Gateway Config

7 properties

JSON SCHEMA

Runloop Launch Parameters

13 properties

JSON SCHEMA

Runloop Mcp Config

6 properties

JSON SCHEMA

Runloop Network Policy

6 properties

JSON SCHEMA

Runloop Object

9 properties

JSON SCHEMA

Runloop Restricted Key

5 properties

JSON SCHEMA

Runloop Scenario

10 properties

JSON SCHEMA

Runloop Secret

4 properties

JSON SCHEMA

Runloop Snapshot

8 properties

JSON SCHEMA

Runloop Tunnel

6 properties

JSON SCHEMA

Scroll within the panel for all 18 ·

JSON Structure 1

JSON Structure captures the data shapes in a form built for tooling — a complement to JSON Schema that keeps the model machine-legible.

JSON Structure definitions describing this provider's data shapes.

Runloop Devbox Structure

8 properties

JSON STRUCTURE

Examples 5

Real request and response payloads are what turn a spec from abstract into obvious — and they're one of the twelve things an agent needs to call an API correctly on the first try.

Example request and response payloads for these APIs.

Security Posture 3

Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Runloop Ai Authentication

http · 1 scheme

SECURITY

Runloop Ai Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Runloop Ai Trust Center

SOC 2, HIPAA, FedRAMP, GDPR

SECURITY

Agentic Access 1

An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.

Recommended x-agentic-access execution contracts for AI agents.

Runloop Ai Agentic Access

302 operations · 154 acting · 8 human-in-the-loop

302 operations · 154 acting

AGENTIC

Resources

Every other property we hold for Runloop — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.

Get Started 2

Portal, sign-up, and the first successful call

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

Learn 1

Tutorials, courses, talks, and written guidance

Commercial 3

Pricing, plans, and the legal terms of use

Other 2

Properties that don't map to a standard resource type

← All providers · Data indexed from github.com/api-evangelist/runloop-ai · machine-readable index on apis.io