Show HN：Agent OS – AI 代理的 0% 安全違規保證

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

To see all available qualifiers, see our documentation.

A Safety-First Kernel for Autonomous AI Agents - POSIX-inspired primitives with 0% policy violation guarantee

License

imran-siddique/agent-os

Folders and files

Latest commit

History

Repository files navigation

Agent OS

The Linux Kernel for AI Agents

0% Safety Violations | Deterministic Enforcement | POSIX-Inspired

Quick Jump

What is Agent OS?

Agent OS treats LLMs like raw compute and provides OS-level governance.

Current frameworks let the LLM "decide" whether to follow safety rules. Agent OS inverts this: the kernel decides, the LLM computes.

Benchmark Results

Install

Or install specific components:

60-Second Example

Core Concepts

Signals - Control Agents Like Processes

VFS - Structured Memory

IPC Pipes - Type-Safe Agent Communication

MCP Integration (Model Context Protocol)

Agent OS is MCP-native. Run any MCP-compatible agent with kernel safety:

Stateless API (MCP June 2026)

For horizontal scaling and serverless deployment:

AGENTS.md Compatibility

Drop Agent OS into any repo with .agents/agents.md:

Observability

Production-ready monitoring for SOC teams:

Key metrics:

Examples

Architecture

Integrations

Comparison

Contributing

See CONTRIBUTING.md for guidelines.

License

MIT - See LICENSE

Built for engineers who don't trust their agents.

GitHub ·
PyPI ·
Papers

About

A Safety-First Kernel for Autonomous AI Agents - POSIX-inspired primitives with 0% policy violation guarantee

Resources

License

Contributing

Uh oh!

There was an error while loading. Please reload this page.

Stars

Watchers

Forks

Releases

Packages

  0

Contributors

  5

Uh oh!

There was an error while loading. Please reload this page.

Languages

Footer

Footer navigation