For AI engineers

The open dev console for working with LLMs.

Free, browser-based tools for the day-to-day reality of prompt engineering, retrieval, and shipping production AI. No accounts, no telemetry on what you paste.

Browse all tools Star on GitHub

Featured tools

View all →

Multi-Model Token Counter

Live

Count tokens and estimate cost across GPT, Claude, Gemini, Llama and DeepSeek side-by-side.

#tokens#cost#pricing

Prompt Diff Viewer

Live

Compare two prompts side-by-side with character, word, and token-level deltas plus an inline diff.

#diff#prompts#iteration

Context Window Budget Calculator

Live

Paste system, retrieved docs, history and user message; see per-model fill % and how much budget is left.

#context#tokens#rag

RAG Chunk Visualizer

Live

Paste a document, see how it gets chunked under fixed, recursive, or markdown-aware strategies side-by-side.

#rag#chunking#retrieval

JSON Schema Generator

Live

Paste sample JSON; get an OpenAI-strict or Anthropic-tool schema with the structured-output gotchas handled.

#schema#structured-output#json

Prompt Template Manager

Live

Auto-detect {{var}}, ${var}, or <var> syntax. Preview substitutions. Export as Python or TypeScript.

#templates#prompts#export

Runs in your browser

Tokenizers, diffs, and similarity calculations execute locally. Your prompts never reach our servers.

Built for working engineers

Each tool solves a specific, recurring problem in production AI work — not a demo of an idea.

Free, with optional Pro

Everything is free to use. A Pro tier (coming soon) adds saved projects, team sharing, and an API for CI/CD.