TOtoken compressorCompress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.More to exploreLocalMCP Registry
TOToken CounterCounts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.More to exploreRemoteMCP Registry
TOToken DietCount tokens exactly for any text and see if it fits a 128K, 200K or 1M context window.More to exploreRemoteMCP Registry