canonical: https://jentic.com/apis/randomlovecraft.com/randomlovecraft

# Random Lovecraft

Random sentences from the complete works of H.P. Lovecraft. CORS-enabled. The API exposes 4 endpoints.

## For AI agents

Programmatically a random sentence, a specific sentence. Covers 4 operations.

## Scope

Does not handle payments, communications, or crm - use for developer tools only.

## Capabilities

- A random sentence
- Random sentences from a specific book
- List all books
- Access Random Lovecraft developer tools resources via REST API

## Use cases

### Developer Tools Operations

Use the Random Lovecraft to perform developer tools operations programmatically. The API provides 4 endpoints covering core functionality including a random sentence, a specific sentence, random sentences from a specific book.

Example prompt: Call GET /sentences to a random sentence

### Automated Sentences Management

Automate sentences operations by combining multiple Random Lovecraft endpoints. Agents can a specific sentence and then random sentences from a specific book in a single workflow.

Example prompt: Call GET `/sentences/{id}` to a specific sentence, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Random Lovecraft endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle none tokens manually.

Example prompt: Search Jentic for 'a random sentence', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/sentences` | A random sentence |
| GET | `/sentences/{id}` | A specific sentence |
| GET | `/books/{id}/sentences` | Random sentences from a specific book |
| GET | `/books` | List all books |

## Key resources

- **Sentences** — Operations related to Sentences
- **Books** — Operations related to Books

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 56 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 100 / 100
  - Developer Experience & Jentic Compatibility: 61 / 100
  - AI-Readiness & Agent Experience: 39 / 100
  - Agent Usability: 94 / 100
  - Security: 100 / 100
  - AI Discoverability: 25 / 100
- **View full report:** https://jentic.com/apis/randomlovecraft.com/randomlovecraft/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring the Random Lovecraft API by hand still means writing a client for its sentence and book endpoints and paging through results yourself, even though it needs no auth. Through Jentic you install once, import the Random Lovecraft API from the API Directory, and your agent calls it with no credential to manage.
- **Permission scoping:** Random Lovecraft puts the book id in the URL path (`/books/{id}/sentences`), so a rule can pin your agent to reading one book, but every endpoint is read-only. You limit the agent to the operations it needs, such as fetching random sentences, and there are no write or destructive operations to grant.
- **Credential handling:** The Random Lovecraft API requires no credential, so there is no secret to store. Any configuration your Jentic One instance holds stays out of the agent's prompt, logs, and context.
- **Discovery method:** Agents search Jentic by intent such as 'get a random Lovecraft sentence' or 'list the books', and Jentic returns the matching Random Lovecraft operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Github** — Alternative developer tools API
- **Gitlab** — Alternative developer tools API

## FAQ

### What authentication does the Random Lovecraft use?

The Random Lovecraft uses no authentication. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I a random sentence with the Random Lovecraft?

Yes. Use the GET /sentences endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Random Lovecraft?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I a random sentence through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'a random sentence'. Jentic returns the matching Random Lovecraft operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Random Lovecraft have?

The Random Lovecraft exposes 4 endpoints covering sentences, books operations.

### Can I limit what my agent is allowed to do with the Random Lovecraft API?

Yes. Because Jentic One is self-hosted, you set the rules that decide which Random Lovecraft operations your agent may call, and every endpoint here is a read-only GET, so there is nothing destructive to grant. You can allow just the operations the agent needs, such as GET /sentences for a random sentence or GET /books to list titles, and leave out the rest. Since the book id sits in the path at GET `/books/{id}/sentences`, a rule can even pin the agent to reading a single book.