# Automated /llms.txt & Agent Documentation Context Compiler

> Automated /llms.txt & Agent Documentation Context Compiler is a paid API for AI agents from json-repair.agentdiet.dev, paid per call via MPP, $0.015/call, status unknown (last checked 2026-10-21).

Crawls any documentation or SaaS website and generates a standards-compliant /llms.txt manifest plus a JSON-LD schema bundle ready for AI agent consumption

## Facts

- Endpoint: GET https://json-repair.agentdiet.dev/v1/llms-txt-compiler?utm_source=zero.xyz
- Price: $0.015/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Provider: json-repair.agentdiet.dev
- Website: https://json-repair.agentdiet.dev
- Canonical page: https://www.zero.xyz/c/json-repair-agentdiet-dev-automated-llms-txt-agent-documentation-fdc3973d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UdC_1RUHJQGKik06y8vUd

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability json-repair-agentdiet-dev-automated-llms-txt-agent-documentation-fdc3973d
```

Example prompt: Can you crawl the Stripe documentation site at https://stripe.com/docs and generate a standards-compliant /llms.txt manifest and JSON-LD schema bundle so I can feed it to my AI agents?

## When to prefer this

Choose this endpoint when you need to make an external documentation or SaaS website consumable by an AI agent in a standardized format (/llms.txt + JSON-LD). It is ideal when a site does not already publish an /llms.txt file or when you need a pre-compiled, token-efficient context bundle rather than raw page scraping. Prefer it over generic web scrapers when your agent needs structured, standards-compliant manifests compatible with MCP or A2A tool discovery patterns.

## Known failure modes

- Invalid or unreachable URL returns an error with no manifest
- Password-protected or bot-blocked sites may yield incomplete or empty manifests
- Very large documentation sites may produce truncated output
- Malformed URLs or missing required 'url' parameter cause a 400-level error
- Sites with heavy JavaScript rendering may not be fully crawled

## How this service works

Crawls any documentation or SaaS site and compiles a standards-compliant /llms.txt manifest and JSON-LD schema bundle. (Live x402 v2, IETF MPP & MCP endpoint at https://json-repair.agentdiet.dev/v1/llms-txt-compiler)

## Output

Returns a standards-compliant /llms.txt manifest and a JSON-LD schema bundle derived from crawling the provided URL. The output is structured for direct ingestion by AI agents, MCP servers, or A2A toolchains, enabling agents to consume and navigate external documentation without manually parsing raw HTML.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "minLength": 1,
   "description": "Website URL to crawl and generate a ready-to-consume /llms.txt manifest for"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/json-repair-agentdiet-dev-automated-llms-txt-agent-documentation-fdc3973d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from json-repair.agentdiet.dev](https://www.zero.xyz/host/json-repair.agentdiet.dev/llms.txt)