Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.clearmaas.com/llms.txt

Use this file to discover all available pages before exploring further.

ClearMaas does not log, store, or retain the content of your prompts or model outputs.

​
What this means, concretely

  • Requests (prompts, messages, tool call payloads, uploaded audio and images) are routed to the destination provider in memory and discarded as soon as the response comes back.
  • Responses (generated text, tool results, generated images, TTS audio) are streamed back to you in memory and not written to any persistent store.
  • Error logs capture a truncated error message from the upstream (e.g., “rate limit exceeded”, “context length exceeded”) for debugging — but never the prompt or response content that triggered the error.

​
What we do keep

See Data Handling for the full list. In summary: timestamps, token counts, latency, and HTTP status codes — the metadata necessary to bill correctly and detect abuse. Never content.

​
Why this is the default (not a per-request opt-in)

Some API platforms let you toggle retention per-request. We made non-retention the default because:
  1. The overwhelming majority of commercial and personal use cases don’t benefit from having prompt content stored.
  2. A default-on flag is an attack surface — misconfiguration leaks prompts.
  3. Zero retention is a differentiator from direct-provider use: OpenAI retains 30 days of abuse logs; Anthropic retains similarly. ClearMaas does not add a second retention layer on top.
If you need content retention for your own observability or evaluation, capture prompts and responses in your own application before sending them. ClearMaas will never hold a copy.

​
Caveat: upstream providers still receive your data

ClearMaas routes traffic to the chosen upstream — OpenAI, Anthropic, Google, and so on — under each provider’s own terms and retention policies. The zero-retention guarantee covers ClearMaas’s own servers; it does not cover what those upstream providers retain. If you need end-to-end retention guarantees that span the upstream too, check that provider’s policy or pick one that offers explicit ZDR itself.