Skip to content
AI Dev Toolkit.
Esc
  • AI Token CounterCount tokens for GPT, Claude, Gemini, DeepSeek, Qwen and more.Tool
  • LLM API Cost CalculatorEstimate per-request, daily and monthly API costs.Tool
  • AI Model ComparisonCompare prices, context windows and features across models.Tool
  • AI Model Pricing PagesSpecs, real costs and cheaper alternatives for popular models.Tool
  • Context Window CheckerSee whether your text fits each model's context window.Tool
  • Subscription vs API CalculatorFind out whether a chat plan or the API is cheaper for you.Tool
  • GPU / VRAM CalculatorCheck how much VRAM a local model needs and which GPUs fit.Tool
  • Claude Code Error DatabaseExact Claude Code error messages with tested fixes.Tool

Category

Utilities for working with AI output and AI crawlers

Small tools for jobs that come up around AI: fixing the JSON a model got wrong, and deciding which AI crawlers may use your website.

Start here

Pick a tool by what you need

Tools

Every tool in this category

Coming next: Chat Format Converter, RAG Text Chunker.

About

How these tools fit together

Language models write JSON one token at a time, so their output can arrive wrapped in a code fence, with comments or trailing commas, or cut off at the output limit. JSON repair fixes what can be fixed, shows exactly what it changed, and warns when output was truncated, because a repaired cut-off answer is still missing data.

AI companies run several crawlers with different jobs: some collect training data, some build AI search indexes, and some fetch a page only when a user asks. Blocking all of them also removes you from AI answers. The robots.txt generator groups 27 crawlers by purpose, writes the file, and checks your current robots.txt with the same matching rules crawlers use (RFC 9309).

Both run entirely in your browser and show their working. JSON repair is built on the open-source jsonrepair library and lists every change as a diff, so you can check nothing was invented. The crawler list comes from each operator’s own documentation for its user-agent names and was last reviewed on 2026-10-08.

Read

Guides

FAQ

Questions people ask

Does robots.txt actually stop AI crawlers?

Only crawlers that choose to follow it. The major AI companies document that their crawlers respect robots.txt, but it is a request, not a lock. To enforce a block, use your host’s or CDN’s bot controls as well.

Will blocking GPTBot remove my site from ChatGPT?

Not by itself. GPTBot collects training data; OpenAI’s search crawler is OAI-SearchBot, and ChatGPT-User fetches pages when a user asks. The robots.txt generator lets you block training while allowing search.

Is it safe to paste my data into JSON repair?

The repair runs entirely in your browser; nothing is uploaded. Still, avoid pasting secrets into any web tool out of habit.

Why not just ask the model for valid JSON?

You should, using the provider’s structured output feature where it exists. Repair is the fallback for output that still arrives broken, for example when a response hits its length limit.