Utterance-time honesty linting for AI companions: catches an agent claiming sensor data it has no sensor for, before the text reaches the user. Extracted from a live local companion system; every rule tuned against real incidents.
What is the levi909-create/percept-lint GitHub project? Description: "Utterance-time honesty linting for AI companions: catches an agent claiming sensor data it has no sensor for, before the text reaches the user. Extracted from a live local companion system; every rule tuned against real incidents.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.
Question is copied to clipboard — paste it after the AI opens.
Clone via HTTPS
Clone via SSH
Download ZIP
Download master.zipReport bugs or request features on the percept-lint issue tracker:
Open GitHub Issues