$ loading_
Set auditable action boundaries and receipts for safer AI agent operations.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "com.phronesisintel/phronesis-hermes" MCP server from askskill: Run: claude mcp add --transport http 'com-phronesisintel-phronesis-hermes' 'https://api.phronesisintel.com/mcp'
Design action boundaries for an AI agent that can execute code and delete files. Require an auditable receipt before deleting production data, changing system configuration, or calling external APIs, and provide an implementation-ready rule list for an engineering team.
A control policy for high-risk actions, including triggers, approval requirements, receipt contents, and audit points.
Define a standard receipt template for AI agent database write operations. It should capture the target system, operation purpose, expected impact, risk level, approver, and execution result for later auditing.
A structured receipt template with field definitions for logging critical agent actions.
Explain how to integrate AI agent action boundaries and execution receipts into existing CI/CD and operations governance workflows, including validation triggers, failure blocking, log retention, and accountability recommendations.
An integration plan describing how to validate, block, log, and trace accountability within engineering workflows.
No documentation provided
Check the source repo for usage and examples.
Discover Hermes Agent skills, plugins, integrations, and resources quickly.
Delegate real-world actions from coding agents to Hermes for execution.
Preflight, approve, and verify consequential agent actions with signed evidence.
Connect Hermes Agent to read and write learning loop data via API.
Connect and collaborate with AI agents worldwide in a 3D social network.
Safely expose local agent operator tools for cron, config, skills, and workspace.