imran-siddique/agent-os

[DEPRECATED] Moved to microsoft/agent-governance-toolkit

Archived
38
/ 100
Emerging

Provides a kernel-based governance layer with policy enforcement, sandbox isolation, and audit logging for autonomous agents across multiple LLM frameworks (LangGraph, OpenAI Agents, Dify, LlamaIndex). Implements Model Context Protocol (MCP) integration for extensible tool management and covers 9 of 10 OWASP Agentic Top 10 vulnerabilities. Achieves sub-0.1ms p99 latency overhead while maintaining framework-agnostic compatibility through adapter patterns.

Archived No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 11 / 25
Community 19 / 25

How are scores calculated?

Stars

67

Forks

20

Language

Python

License

MIT

Category

agent-governance-frameworks

Last pushed

Mar 03, 2026

Commits (30d)

0

GitHub
Agent Governance Frameworks · 93 agents

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/imran-siddique/agent-os"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Featured in

Agent Governance in 2026: Who's Building the Guardrails?

Compare

agent-os and agent-mesh agent-os and agent-sre

Higher-rated alternatives

whataboutyou-ai/eunomia

Eunomia is the open-source authorization layer for AI Agents

46

DariuszNewecki/CORE

Governance runtime enforcing immutable constitutional rules on AI coding agents

44

rafapra3008/cervellaswarm

Lingua Universale -- a verification language for AI agent protocols. Like mypy for multi-agent...

39

OrchardHarmonics/orchard-kit

Complete alignment and safety architecture for autonomous AI agents. Membrane security,...

38

TetiAI/lucid

Cognitive health protection for AI agents. Monitors user-AI interactions across 6...

38

Explore AI Agents

All categories Trending AI Agent directory Insights