~/tools / request-translator
Provider request translator
Every multi-provider team hits the same seams: system prompts move, max_tokens renames itself, and tool definitions restructure entirely. Paste a request in either dialect — it auto-detects the format and emits the other side, tool schemas included. This is my production provider-abstraction layer, shrunk into a widget.
TOOL 03
Provider request translator
my provider-agnostic layer, shrunk into a widgetpaste either dialect on the left — it detects and translates
// translated request appears hereHandles system prompts, max_tokens, temperature and tool definitions in both directions — the exact seams my unification layer papers over across OpenAI, Anthropic and Bedrock.
more
tools.siblings
Token & cost metercount tokens · compare API cost across modelsRAG capacity plannercorpus size → vectors, RAM, embed costGPU VRAM calculatorwill that model fit on your card?JSONL dataset inspectorfine-tune data sanity check, fully localPrompt diffword-level diff for prompt iterationPrompt linterESLint for system prompts