Pinned Loading
Repositories
Showing 4 of 4 repositories
- guardana Public
Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
- control Public
AI agent supervision framework in alpha. Decide MCP tool calls by policy and check recorded runs (experimental).
- playground Public
A lab that attacks the Guardana verifier and the enforcement plane, and grades what they recorded.
- privacy Public
Building a local-first privacy framework for AI agents and manual use. Text CLI and independent output checks work now; more formats and agent extensions are planned.
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…