AI & LLM 8 Tools Available 100% Client-Side

AI & LLM Engineering

Professional browser-native utilities for prompt engineering, token counting, structured outputs, and RAG vector chunking. All tools operate entirely in your web browser with zero server roundtrips, offline caching, and strict data privacy.

Available Utilities in this Category

Showing all 8 utilities

Essential

Universal LLM Token Counter, Colorizer & Context Estimator

Universal token counter and cost calculator for OpenAI, Anthropic, Gemini, and Llama 3.

✓ Multi-model subword token estimation supporting OpenAI GPT 5.6 (Luna/Sol/Terra/5.5), Claude (Opus 5/Sonnet 5/Fable 5/Haiku 4.5), Gemini 3 (3.7/3.6/3.5/3.1), Grok (4.6/4.5), Qwen (3.8 Max/Flash), DeepSeek (V4 Flash/Pro), Z.ai (GLM 5.3/5.2), and Moonshot (Kimi K3/K2.7)

✓ Interactive token stream colorizer revealing exact subword token splits, prefixes, whitespace handling, and byte-pair boundaries

Launch Utility →

Popular

Interactive System Prompt, Meta-Prompt & Persona Studio

Interactive studio to generate structured, production-ready system prompts and meta-prompts.

✓ Modular Prompt Architecture: Build system prompts with structured sections for Role & Persona, Core Objectives, Operating Rules, Constraints, and Output Format

✓ Model-Specific Presets: Auto-format prompts using Anthropic Claude XML tags (<instructions>, <context>), OpenAI developer messages, or DeepSeek/Llama markdown conventions

Launch Utility →

Essential

LLM Function Calling & Structured Outputs Schema Generator

Generate strict JSON Schemas, OpenAI Structured Outputs, and function calling tools.

✓ Multi-Target Schema Synthesis: Generate compliant schemas for OpenAI Structured Outputs (response_format: json_schema), OpenAI Tools, Anthropic Claude Tools (input_schema), and Gemini FunctionDeclarations

✓ Strict Mode Compliance: Automatically enforces additionalProperties: false, complete required arrays, and non-empty property descriptions required for deterministic LLM constrained decoding

Launch Utility →

New

RAG Document Text Chunker & Token Overlap Splitter

Split documents and code for RAG with recursive, token-aware chunking and overlap.

✓ Multiple Chunking Strategies: Recursive Character Splitting, Token-Length Windowing, Paragraph/Sentence Boundary Splitting, and Markdown Header hierarchy segmentation

✓ Configurable Overlap Percentage: Set chunk overlap (0% to 50% / 10–200 tokens) to maintain contextual coherence across chunk seams and eliminate split-context retrieval failures

Launch Utility →

Essential

DESIGN.md Generator & AI Design System Studio

Generate machine-readable DESIGN.md files, Tailwind v4 @theme tokens, and UI guidelines for Cursor, Claude Code, and Copilot.

✓ Interactive brand color token builder (Primary, Secondary, Accent, Background, Surface, Border, Text)

✓ Typography scale customizer with font families, headings (h1-h4), and body font sizing

Launch Utility →

Popular

AGENTS.md & Multi-Agent Rules Studio (Cursor, Claude, Copilot, Windsurf)

Generate universal AGENTS.md, .cursorrules, CLAUDE.md, and Copilot instructions with stack presets and anti-hallucination guardrails.

✓ Stack-aware preset templates (Next.js 15, Astro 5, React 19, FastAPI, Go, Rust, Flutter)

✓ Setup & build command manager (install, dev, build, test, lint, typecheck)

Launch Utility →

New

llms.txt & llms-full.txt Generator, Validator & Sitemap Importer

Generate and validate spec-compliant llms.txt and llms-full.txt files with live BPE token estimation and sitemap.xml import.

✓ Visual section and resource link manager (Title, URL, concise description, Required vs Optional)

✓ Dual output tabs: Curated /llms.txt index and comprehensive /llms-full.txt markdown bundle

Launch Utility →

LLM JSON Repair & Truncated JSON Fixer

Instantly repair broken, truncated, malformed, or markdown-wrapped JSON outputs from LLMs.

✓ Autonomous AST Repair Engine: Automatically balances unclosed brackets/braces, unescapes strings, converts single quotes, strips markdown backticks, and fixes trailing commas

✓ Truncated Stream Recovery: Intelligently closes incomplete objects and arrays severed by LLM context window limits, max token cutoffs, or interrupted streaming responses

Launch Utility →

WebCraftKit Platform 100% Client-Side Engine

Air-Gapped Privacy & Zero-Latency Developer Utilities

Every cryptographic algorithm, schema transformer, color space converter, and binary extractor runs entirely in your browser RAM. Your tokens, API secrets, and source code are never sent to external servers.

Zero Server Telemetry

•

Sub-Millisecond Execution

•

80 Production Tools

Read Architecture Story →

Explore Other Categories

Dev & Data

Developer & Data Utilities

Format, validate, encode, decode, and transform developer data formats with zero server latency.

→

CSS & Design

CSS & UI Design Tools

Generate high-performance CSS styles, smooth box shadows, modern glassmorphism, and accessible palettes.

→

SEO & Webmaster

Webmaster, SEO & Text Tools

Optimize metadata for search rankings, compose Markdown in real-time, generate sitemaps, and inspect text.

→

Mobile & Apps

Mobile & App Development

Generate Xcode/Android icon suites, design App Store screenshot mockups, convert strings.xml, calculate DPI, and test deep links.

→