# APort

APort is a pre-action authorization layer for AI agents. It checks GitHub pull
requests, shell commands, file access, MCP tools, and payment actions against an
agent passport and policy before they execute, then records signed allow or deny
decisions for audit.

## What APort Offers

- AI agent passports with owner, capabilities, limits, regions, and status.
- GitHub Repository Guard for AI-generated pull requests and pushes.
- Runtime guardrails for Claude Code, Cursor, Goose, Codex CLI, Gemini CLI,
  OpenClaw, LangChain, CrewAI, DeerFlow, n8n, MCP tools, and custom agents.
- Hosted policy verification at `/api/verify/policy/{policy_id}`.
- Local/offline evaluation for development and open-source use.
- Organization audit, signed decisions, and pilot support for teams.

## Start Here

- [Quickstart](https://aport.io/quickstart)
- [Products](https://aport.io/products)
- [About APort](https://aport.io/about.md)
- [GitHub Repository Guard](https://aport.io/products/github-repository-guard)
- [Frameworks](https://aport.io/frameworks)
- [AI Control Packs](https://aport.io/products/control-packs)
- [Policy catalog](https://aport.io/policy-packs)
- [Pricing](https://aport.io/pricing)
- [Auth guide](https://aport.io/auth.md)
- [API docs](https://aport.io/api/documentation)
- [OpenAPI](https://aport.io/api/openapi-json)
- [Skill](https://aport.io/skill)
- [Skills library](https://aport.io/skills)
- [ARD catalog](https://aport.io/.well-known/ard.json)