Calculates the number of tokens in a string using gpt-3-encoder. Essential for estimating LLM costs and ensuring prompts fit within context windows.
Permissions are shown for transparency. In demo mode these agents are stubbed, and no real privileged actions run unless you wire them into your local runner.
receipts.jsonartifacts/This agent is designed to emit a run receipt with steps + artifacts. See Runs & Receipts for examples.