Do the AI tools call an AI model?

No. They analyse and prepare prompts, datasets and schemas locally. They do not send anything to OpenAI, Anthropic or other providers.

How accurate is the token counter?

It uses the same tokenizer encodings published by the model providers, so counts match what the API reports for supported models.

Is my data uploaded anywhere?

No. These tools run inside your browser tab, so your input and files stay on your device. Nothing is saved on a server.

AI & LLM tools

Developer tools for building with large language models: exact token counting, context-window and API cost planning, prompt linting, JSONL dataset checks, RAG chunking, structured-output validation, function-calling and MCP tool schemas, and prompt redaction. Everything runs locally — your prompts and datasets never leave the browser.

23 tools in this category · 10 sub-categories

Datasets

AI Dataset Deduplicator

Remove exact and near-duplicate rows from fine-tuning datasets.

AI Dataset Statistics Analyzer

Profile a JSONL training set: token stats, roles, duplicates and cost.

Chat Dataset Converter

Convert between OpenAI chat, ShareGPT, Alpaca and prompt/completion.

Datasets & JSONL

JSONL Validator

Validate JSONL and fine-tuning datasets line by line.

JSONL Formatter

Pretty-print, minify, sort and deduplicate JSON Lines files.

JSONL ↔ JSON Converter

Convert JSON Lines to a JSON array and back again.

Embeddings

Embedding Similarity Calculator

Cosine, dot product and distance between two embedding vectors.

Embedding Vector Inspector

Inspect dimensions, norm, mean and spread of an embedding vector.

Privacy & Safety

AI PII & Secret Redactor

Strip emails, keys, tokens and personal data before prompting an LLM.

Prompt Engineering

Prompt Linter

Audit prompts for vague wording, missing formats and leaked secrets.

RAG & Context

RAG Text Chunker

Split documents into token-sized overlapping chunks for embedding.

RAG & Prompts

Prompt Diff & Compare

Compare two prompt versions word by word with a token delta.

LLM Output Diff

Compare two model responses to measure drift between runs or models.

Context Window Packer

Fit as many RAG chunks as possible into a model context budget.

Schemas

MCP Tool Schema Generator

Generate an MCP, OpenAI or Anthropic tool schema from example arguments.

Schemas & Tools

LLM Structured Output Validator

Check that a model's JSON reply matches your JSON Schema.

AI Tool Schema Builder

Build function-calling schemas for OpenAI, Claude, Gemini, MCP and the AI SDK.

MCP Tool Schema Validator

Validate Model Context Protocol tool definitions before you ship them.

AI Tool Schema Converter

Convert function-calling schemas between OpenAI, Anthropic, Gemini and MCP.

JSON Schema to AI Tool Schema

Wrap any JSON Schema into a ready-to-use function-calling tool.

Tokens & Cost

AI Token Counter

Count exact LLM tokens for GPT, Claude and Gemini prompts.

LLM Context Window Calculator

See if your system, context and user messages fit the model window.

LLM API Cost Calculator

Estimate GPT, Claude and Gemini API spend per call and per month.

About ai & llm tools

Plan prompts and budgets before you call a model. Count tokens, estimate API cost, check JSONL training files, split documents into RAG chunks and validate structured output or tool schemas — without sending your prompts to any service.