Agentos
by imran-siddiquecommunityv1.0.1
69
20
Agent OS is a governance kernel for autonomous AI agents that ensures policy enforcement, auditability, and compliance during agent actions. It provides deterministic governance with minimal latency.
From the registry: Build and manage policy-compliant AI agents with safety enforcement and compliance checking
Install & configure
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `agentos` MCP server into my current AI client (that's you).
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","agentos-mcp-server"]
Note: Part of Agent OS (ai-agent-governance) ecosystem. Published as agentos-mcp-server on npm. Provides 10 tools for agent creation, policy enforcement, compliance (SOC 2/GDPR/HIPAA), HITL, and audit logging.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: Part of Agent OS (ai-agent-governance) ecosystem. Published as agentos-mcp-server on npm. Provides 10 tools for agent creation, policy enforcement, compliance (SOC 2/GDPR/HIPAA), HITL, and audit logging.
Tools (4)
Agent OS
Policy enforcement and action interception for AI agents.
AgentMesh
Identity, trust, and delegation management.
Agent SRE
Service Level Objectives, chaos testing, and circuit breakers.
Agent Hypervisor
Management of agent execution environments.
Prerequisites
- • Python 3.9+
Packages
agentos-mcp-server
npmv1.0.1transport: stdio
Details
- Language
- Python
- License
- MIT
- Released
- Feb 2, 2026
- Last commit
- Mar 3, 2026
- Registry name
- io.github.imran-siddique/agentos