Cyberelf Labs Replay API
The Replay API from Cyberelf Labs — 1 operation(s) for replay.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/cyberelf-link:cyberelf-link-replay-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
description: Verifier-grounded evaluation tools for AI systems. Workbench and report-card requests are stateless and unauthenticated; payloads and results are not persisted. Open Promotion Bench may persist only an opt-in public manifest and sanitized receipt, never task contents or answers. Operational counters and standard access logs are retained.
license:
name: AGPL-3.0-or-later
url: https://www.gnu.org/licenses/agpl-3.0.html
title: Whetstone Tools Replay API
version: 0.8.0
x-build-commit: 780558024ed039fc19bd626d956b4bd3267d61f5
servers:
- url: https://whetstone.cyberelf.link
tags:
- name: Replay
paths:
/api/replay:
post:
operationId: replay
requestBody:
content:
application/json:
example:
events:
- detail: SAVE first_try
kind: control
step: 1
- detail: CHECK is_tree
kind: control
step: 2
- detail: REJECT counterexample n=6
kind: verifier
step: 3
- detail: 'LOAD first_try :: tree hypothesis failed'
kind: control
step: 4
- detail: CHECK is_tree and max_degree <= 2
kind: control
step: 5
- detail: ACCEPT
kind: verifier
step: 6
- detail: ANSWER is_tree and max_degree <= 2
kind: control
step: 7
notes: []
schema:
additionalProperties: false
description: Reconstruct checkpoints, rewinds, branches, and verifier outcomes from control events.
properties:
events:
description: Ordered reasoning-emulator events.
items:
additionalProperties: false
properties:
detail:
type: string
kind:
description: Event class such as control, verifier, model, or observation.
type: string
source:
default: native
type: string
step:
minimum: 0
type: integer
required:
- kind
- detail
type: object
maxItems: 5000
minItems: 1
type: array
notes:
description: Optional analyst notes.
items:
type: string
maxItems: 5000
type: array
required:
- events
type: object
required: true
responses:
'200':
description: Deterministic receipt with item-level decision path and SHA-256 hashes.
'400':
description: Input error (a hint points at /api/examples).
'429':
description: Rate limited.
summary: Turn emulator events into checkpoints, rewinds, notes, and a timeline
tags:
- Replay