How to Clean Messy LLM JSON Output Without Regex Hell

M0N0S0DIUM — Thu, 16 Jul 2026 20:57:33 +0000

You ask an LLM for JSON. It returns:

{
  "name": "John Doe",
  "email": "john@example.com",
  "phone": "555-1234",
  "notes": "Customer called about billing issue -- needs follow-up",
  "tags": ["billing", "urgent"]
}

Looks clean. But paste it into JSON.parse() and boom:

SyntaxError: Unexpected token } in JSON at position 147

The culprit? Trailing comma after the last property. Or maybe it wrapped the whole thing in markdown code fences. Or used single quotes. Or included a comment. Or got cut off mid-token.
You reach for regex. replace(/,\s*}/g, '}') fixes trailing commas. But then you hit markdown fences. Then single quotes. Then a stray // comment. Then a truncated string. Each fix breaks something else.

There's a better way.

Why Existing Tools Fail

Tool	Fails On
Regex	Nested objects, escaped quotes, partial truncation
`jq`	Invalid JSON (trailing commas, comments, single quotes)
Python `json.loads()`	Strict — any violation throws
Online formatters	Manual copy-paste, not automatable
Custom Python scripts	Maintenance burden, edge cases

The pattern: every tool assumes valid JSON. LLM output is almost JSON.

The API Approach: One Call, Pipeline of Fixes

Instead of chaining fragile fixes, define a pipeline — ordered transforms that each handle one class of mess.

curl -X POST https://textforge.co/v1/run \
  -H "Content-Type: application/json" \
  -d '{
    "input": "{name: \"John\", email: \"john@example.com\",}",
    "pipeline": ["removespecial", "removemultiple"]
  }'

Response:

{
  "success": true,
  "input": "{name: \"John\", email: \"john@example.com\",}",
  "pipeline": ["removespecial", "removemultiple"],
  "result": "{\"name\": \"John\", \"email\": \"john@example.com\"}",
  "steps": [
    {"step": 1, "action": "removespecial", "result": "{\"name\": \"John\", \"email\": \"john@example.com\"}"},
    {"step": 2, "action": "removemultiple", "result": "{\"name\": \"John\", \"email\": \"john@example.com\"}"}
  ],
  "execution_time_ms": 3
}

Free tier: 1,000 requests/day. No API key. No account.

I built a text pipeline API: 28 transforms, one endpoint, 1K free/day

M0N0S0DIUM — Sat, 04 Jul 2026 00:25:22 +0000

I was tired of importing 47KB of string utilities across three services just to slugify a URL, camelCase a property, and base64-encode the result.

So I built TextForge: 28 text transformations behind one REST endpoint.

The problem: Every service had its own copy of slugify, camelCase, base64, extractEmails, etc. Version drift, bundle bloat, inconsistent behavior.

The solution: One API, composable pipelines, predictable JSON.

curl -X POST https://textforge.co/v1/run \
  -H "Content-Type: application/json" \
  -d '{"input":"user@example.com","pipeline":["extractemails","slugify","base64encode"]}'

{
  "success": true,
  "result": "dXNlckBleGFtcGxlLmNvbQ==",
  "steps": [
    {"step":1,"action":"extractemails","result":["user@example.com"]},
    {"step":2,"action":"slugify","result":"user-example-com"},
    {"step":3,"action":"base64encode","result":"dXNlci1leGFtcGxlLWNvbQ=="}
  ],
  "execution_time_ms": 3
}

28 transforms: case conversions (camel, snake, kebab, pascal, constant, sentence, title), encoding (base64, HTML, URL, leet, morse), extraction (emails, URLs, numbers), cleaning (trim, remove special, multiple spaces), analysis (word count, palindrome, hash), generation (random strings).

Pricing: Free = 1,000 req/day, no key. Pro = $2.99/mo for 50k/day, webhooks, batch (100 items), API keys, analytics.

Stack: Express + PostgreSQL + Redis on Railway. OpenAPI 3.0 at /api-docs. Dashboard at /dashboard.

Built it because the alternative was maintaining string-utils v2.3.1 across five repos. Now it's one HTTP call.

https://textforge.co