|
|
|
|
|
|
by base76
113 days ago
|
|
|
We built CognOS exactly for this: it runs as a local gateway (Docker, no external calls), wraps each LLM output with a signed trust score, decision trace, and EU AI Act risk
classification. The audit trail lives in your own infrastructure. github.com/base76-research-lab/operational-cognos — open source, MIT license.
|
|
|