# AgentShelf Semver Regex Extractor

> AgentShelf Semver Regex Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-02).

Extracts semantic version strings (semver tokens) from arbitrary text, returning up to 20 matches per call.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/regex-semver?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-semver-regex-extractor-c738c162
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_u011nXxPUmzMBvtIcd058

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 agentshelf-semver-regex-extractor-c738c162 -d '<json body>'
```

Example prompt: Can you pull out all the semantic version numbers from this changelog text? Here it is: 'Updated lodash from 4.17.20 to 4.17.21, bumped react to 18.2.0, and pinned webpack at 5.75.0.'

## When to prefer this

Use this endpoint when you need to extract semantic version strings from unstructured or semi-structured text and don't want to implement or maintain a regex parser yourself. Prefer the free POST /v1/sandbox/regex-semver endpoint for testing or low-stakes use. Choose this paid endpoint for production agent workflows where reliability and no local compute overhead matter. Not suitable for IP address extraction, date parsing, or other version-like patterns — use a domain-specific extractor for those.

## Known failure modes

- Empty match list returned (and billed) when no semver tokens exist in input text
- Input text exceeds 100,000 character limit — request rejected
- Malformed or missing 'text' field causes validation error
- More than 20 matches in text — only first 20 returned, rest silently truncated

## How this service works

Call when an agent needs semver tokens extracted from text, capped at 20 matches. An empty match list is billed. No network. Exact $0.003 USDC. Prefer unpaid POST /v1/sandbox/regex-semver first.

## Output

A list of up to 20 semantic version strings (e.g. '1.2.3', '4.17.21', '0.9.12-beta.1') found in the input text. If no semver tokens are found, an empty list is returned — and the call is still billed at $0.003 USDC.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "examples": [
    "1.2.3"
   ],
   "maxLength": 100000,
   "minLength": 1,
   "description": "Input for this SKU. The route description says whether it is plain text, a URL, base64 bytes, or an already-encoded token."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentshelf-semver-regex-extractor-c738c162/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentshelf.syntexa.ch](https://www.zero.xyz/host/agentshelf.syntexa.ch/llms.txt)