AI developer tools
The numbers you check every day when building on LLMs — tokens, API cost, GPU memory, RAG chunks, fine-tuning data, broken JSON — worked out in your browser with no key needed.
PowerPoint to Markdown converter
Turn a .pptx into clean Markdown — one heading per slide, bullets, tables and speaker notes — ready for a RAG corpus or an LLM prompt.
#02Excel to Markdown table converter
Convert .xlsx sheets to Markdown tables and CSV in the browser, with dates and formulas resolved to their values.
#03Ollama Modelfile generator
Build an Ollama Modelfile — base model, system prompt, sampling parameters, stop sequences — plus the ollama create command.
#04Chat template renderer
See the exact prompt string a model receives: Llama 3, Qwen, Mistral, Gemma, Phi and DeepSeek templates, rendered from your messages.
#05RAG text chunker
Split a document into overlapping chunks exactly as LangChain's RecursiveCharacterTextSplitter would, with Chinese punctuation understood.
#06LLM VRAM calculator
Estimate the GPU memory an open model needs under llama.cpp or Ollama — weights, KV cache and overhead — and which graphics cards it fits.
#07LLM inference speed estimator
Tokens per second for a model size, quantisation and GPU — the roofline numbers vLLM and llama.cpp are bounded by.
#08MCP config generator
Tick the MCP servers you want and get a working config for Claude Desktop, Cursor, VS Code or Claude Code.
#09Fine-tuning JSONL validator
Check an OpenAI chat fine-tuning file line by line before you upload it, and see its token counts and what training will bill.
#10Fine-tuning dataset converter
Convert training data between Alpaca, ShareGPT and OpenAI messages JSONL, with every record detected on its own.
#11LLM API cost calculator
Price a workload across 46 models from OpenAI, Anthropic, Google, DeepSeek, Qwen, Mistral, xAI and more, from a token count or from your actual prompt.
#12Vector similarity calculator
Cosine similarity, dot product and Euclidean distance between embedding vectors, pasted from any model or API response.
#13OCR image to text
Pull text out of screenshots, scans and photos in Chinese, English, Japanese, Korean, German or French, without uploading them.
#14Markdown to plain text cleaner
Strip the Markdown from a ChatGPT or Claude answer — asterisks, hashes, pipes, fences — and keep the text, lists and tables readable.
#15OpenAI Batch API JSONL builder
Turn a list of prompts into a ready-to-upload batch file with custom_id, endpoint and body on every line.
#16Secret scanner for code and config
Check code, .env files and logs for API keys, tokens and private keys with rules ported from gitleaks, before you paste them anywhere.
#17Repo to prompt packer
Pack many source files into one LLM-ready document — directory tree plus every file — with token counts per file.
#18Prompt template filler
Fill {{variables}} in a prompt template from JSON and see the exact prompt the model will get, with what was missing and what went unused.
#19Speech to text (Whisper in the browser)
Transcribe audio or video with OpenAI's Whisper running in your tab, as plain text or SRT subtitles.
#20Sentence similarity checker
Compare sentences by meaning with a multilingual embedding model in your browser and see a cosine-similarity matrix.
#21JSON Schema validator
Check a JSON document against a JSON Schema with Ajv and see every failing path, not just the first one.
#22JSON to JSON Schema generator
Infer a JSON Schema from a sample, with an OpenAI strict-mode option for structured outputs and function calling.
#23HTML to Markdown for LLMs
Turn a web page's HTML into clean Markdown, with tables kept and navigation, scripts and footers removed.
#24PII redactor for AI prompts
Mask phone numbers, emails, ID and card numbers, IBANs, IP addresses and API keys before you paste text into ChatGPT or any other AI.
#25LLM SSE stream decoder
Paste a raw streaming response from OpenAI, Anthropic, Gemini or any OpenAI-compatible API and get back the full text, tool calls, reasoning and token usage.
#26Model size calculator
Paste a config.json and get the parameter count, weights memory at each precision and the KV cache per token.
#27Word to Markdown converter
Convert a .docx file into clean Markdown or semantic HTML with mammoth.js, and see what it could not convert.
#28ChatGPT export to Markdown converter
Turn conversations.json from a ChatGPT data export into clean Markdown — the branch you last saw, without system prompts or tool traffic.
#29JSON repair for LLM output
Fix the broken JSON language models return — single quotes, trailing commas, comments, Python literals, truncated output — and pull it out of the surrounding chatter.
#30OpenAI token counter
Count the tokens in a prompt exactly as OpenAI's tokenizer does, and see where each token starts and ends.