Build and manage policy-compliant AI agents with safety enforcement and compliance checking
io.github.imran-siddique/agentos
https://github.com/imran-siddique/agent-os
STDIO
No auth required
Hosted endpoint — paste into any MCP client.
Configuration this server reads at startup.
Policy enforcement mode: strict (block all violations) or permissive (warn only)
Log level: debug, info, warn, or error
Where to find authoritative docs and source for agentos.
Open MCP Agent Studio and connect this server to Claude, GPT, Gemini, DeepSeek and more — no install required.
Open Agent Studio