The product stack for governing AI agent work.
APort is organized around the controls enterprise teams already ask for: identity, enforcement, audit evidence, reusable controls, and rollout governance. Developers still get direct implementation paths through quickstarts, framework docs, and the policy catalog.
Name the agent
Control the action
Keep the proof
Fastest path
Let the agent do the setup, keep the human in control.
APort’s setup flow treats AI agents as the likely operator: give them one instruction, then review the generated workflow, passport, or hook before it lands.
Recommended
Let my agent prepare the review-first setup.
Ask Claude, Codex, Cursor, Goose, or another agent to prepare APort setup with the official machine-readable skills, then review the diff before anything lands.
Read https://aport.io/.well-known/agent-skills/index.json and use the most specific APort skill for this repo.
Prepare a reviewable, report-only APort setup change first.
Show me the diff before commit or PR.
Do not enable blocking enforcement, create hosted secrets, install with sudo,
or mark checks as required unless I explicitly approve it.APort is deterministic infrastructure. The agent can prepare the change, but enforcement and secret-bearing setup remain human-approved.
Product catalog
Enterprise names, developer implementation paths.
The product pages describe what buyers can adopt. Each page links to the existing live implementation surface so setup instructions, frameworks, and policy data stay DRY.
GitHub Repository Guard
APort verifies pull-request evidence, protected-path changes, workflow permissions, and repository context before AI-generated code reaches main.
AI Agent Passport
An AI agent passport records an agent's owner, capabilities, and limits. APort uses that identity record with policy checks to authorize each connected tool call before it runs. The passport declares authority; the installed guardrail enforces it.
Runtime Enforcement
APort guardrails evaluate shell, file, web, MCP, repository, and framework tool calls before the agent can act.
Decision Audit Trails
APort records policy decisions with context, reasons, timestamps, and signatures so teams can reconstruct what happened and why.
AI Control Packs
AI Control Packs are APort's enterprise-facing policy bundles for finance, data, repository, messaging, web, system, MCP, and deliverable workflows.
Enterprise AI Governance
APort helps companies roll out guardrails, hosted verification, repository protection, and signed evidence across employee AI tools and agent workflows.
Revenue path
Start with a pilot, not a sprawling procurement exercise.
The fastest adoption path is GitHub Repository Guard or runtime enforcement for one team, with hosted signed decisions turned on when the customer needs audit evidence.