I am building mnki, an open trust layer for agents: identity, delegated authority with constraints, and an evidence trail per action, underneath MCP and A2A rather than replacing them. UiPath's customers are audited by default, which is why I would like a view from your side.
Two things in this repository caught my eye: a governance skill in preview, and a section on reducing permission prompts with an install-permissions command. That is the tension I am working on. Fewer prompts means the authority has to be decided somewhere else and recorded; more prompts means nobody reads them. When your customers run coded agents next to RPA, what do their auditors ask for: who approved which action, under which policy, with what evidence?
Twenty minutes would help me; a reply here is plenty. Reference implementation, Apache-2.0: https://github.com/MNKIAgentOS/agent-trust; integration paths: https://mnki.com/docs/integrations. Thank you for publishing the skills openly, with stability labels; that is rare from a vendor.
I am building mnki, an open trust layer for agents: identity, delegated authority with constraints, and an evidence trail per action, underneath MCP and A2A rather than replacing them. UiPath's customers are audited by default, which is why I would like a view from your side.
Two things in this repository caught my eye: a governance skill in preview, and a section on reducing permission prompts with an install-permissions command. That is the tension I am working on. Fewer prompts means the authority has to be decided somewhere else and recorded; more prompts means nobody reads them. When your customers run coded agents next to RPA, what do their auditors ask for: who approved which action, under which policy, with what evidence?
Twenty minutes would help me; a reply here is plenty. Reference implementation, Apache-2.0: https://github.com/MNKIAgentOS/agent-trust; integration paths: https://mnki.com/docs/integrations. Thank you for publishing the skills openly, with stability labels; that is rare from a vendor.