How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Runloop agents API

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

Runloop agents API is one of 24 APIs that Runloop publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

This API exposes 19 JSON Schema definitions.

Tagged areas include Agents. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, a JSON-LD context, and 19 JSON Schemas.

This API exposes 6 operations across 5 paths, and defines 10 schemas. It is described by OpenAPI 3.2.0, at version 0.1.

Requests are made against a single base URL, https://api.runloop.ai.

6 operations 5 paths 10 schemas 4 GET2 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
0.1
Base URL
https://api.runloop.ai
Authentication
HTTP Bearer
Resource Areas
1

Authentication & Security 1

Runloop agents API declares 1 security scheme for authenticating requests. It accepts HTTP bearer tokens (bearerAuth). By default, every request must be authenticated.

Paths & Operations 6

Across 5 paths, the API surfaces 6 operations — 4 GET, 2 POST. Each is listed below with its method, path, parameters, and response codes.

agents 6
POST
/v1/agents
Create an Agent.
createAgent body → 200400401403500
GET
/v1/agents
List Agents.
listAgents 7 params → 200401403500
GET
/v1/agents/devbox_counts
Get Devbox counts by Agent.
getAgentDevboxCounts → 200401403500
GET
/v1/agents/list_public
List Public Agents.
listPublicAgents 6 params → 200401403500
GET
/v1/agents/{id}
Get an Agent.
getAgent 1 param → 200401403404500
POST
/v1/agents/{id}/delete
Delete an Agent.
deleteAgent 1 param → 200401403404500

Schemas 10

The contract defines 10 schemas that model the data the API accepts and returns. The most detailed are AgentView (6 properties), AgentSource (5 properties), NpmSource (3 properties), PipSource (3 properties). Each schema is shown below with its type and property counts.

GitSource
object
Git-based agent source configuration.
3 properties 1 required
AgentView
object
An Agent represents a registered AI agent entity.
6 properties 4 required
PipSource
object
Pip-based agent source configuration.
3 properties 1 required
ObjectSource
object
Object store agent source configuration.
2 properties 1 required
NpmSource
object
NPM-based agent source configuration.
3 properties 1 required
AgentCreateParameters
object
Parameters for creating a new Agent.
3 properties 1 required
AgentListView
object
A paginated list of Agents.
3 properties 2 required
AgentDevboxCountsView
object
Devbox counts grouped by agent name. Used to efficiently fetch devbox counts for multiple agents in a single request.
2 properties 2 required
AgentSource
object
Agent source configuration.
5 properties 1 required
EmptyRecord
object

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

runloop-ai-agents-api-openapi.yml Raw ↑

Other APIs Runloop publishes across the network.

Runloop apikeys API
Runloop axons API
Runloop Benchmark API
Runloop Blueprint API
Runloop Blueprint-Lifecycle API
Runloop Blueprint-ObservabilityTools API
Runloop Devbox API
Runloop Devbox-FileTools API
Runloop Devbox-Lifecycle API
Runloop Devbox-NetworkTools API
Runloop Devbox-ObservabilityTools API
Runloop Devbox-PersistenceTools API
Where this information came from

This is an independent, third-party profile of Runloop agents API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.