aport-spec: The Open Agent Passport (OAP) Specification for AI Agent Trust
This repository profile is provided by osrepos.com, an open source repository discovery platform.
Summary
The aport-spec repository introduces the Open Agent Passport (OAP) specification, a critical framework for establishing trust in AI agents. It defines a lightweight, cryptographically verifiable credential, enabling real-time, pre-action authorization for AI agents across various platforms. OAP provides the essential runtime trust layer for secure and scalable agentic commerce.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
The aporthq/aport-spec repository introduces the Open Agent Passport (OAP) v1.0 specification (currently a draft), designed to establish a runtime trust rail for AI agents. As AI agents increasingly handle digital commerce, the critical challenge of trusting unseen agents emerges. OAP addresses this by providing a lightweight, cryptographically verifiable credential that enables real-time, pre-action authorization for AI agents across any platform. It shifts the focus from who built an agent to what it is allowed to do at the point of action.
Why Use and Benefits
The rapid acceleration of agentic commerce demands a robust trust infrastructure, which current solutions, primarily focused on agent identity, fail to provide. Merchants and platforms require instant verification and sub-100ms authorization decisions before sensitive data or money moves.
OAP offers a comprehensive solution by providing the essential runtime trust layer for secure and scalable agentic commerce. Key benefits include:
- Pre-action Authorization: Ensures agents are authorized before sensitive operations.
- Cryptographically Signed Decisions: Provides immutable audit trails for all actions.
- Global Suspend Capabilities: Allows for instant risk mitigation across platforms.
- Standardized Policy Packs: Enables consistent enforcement of rules.
- Instant Trust: Delivers authorization decisions in under 100 milliseconds.
- Standards Compliance: Built to integrate with existing identity frameworks like W3C Verifiable Credentials and complement KYC/KYB.
Implementation Guidance
The aport-spec repository provides comprehensive guidance for both platform builders and developers looking to implement the OAP specification.
For Platform Builders:
- Understand the Specification: Begin by reading the OAP v1.0 Specification.
- Review Examples: Explore the examples to understand implementation patterns.
- Validate Implementation: Utilize the conformance runner for testing and validation.
- Integrate with VCs: Follow the VC mapping guide for Verifiable Credentials integration.
For Developers:
- API Integration: Use the OpenAPI spec for client generation.
- SDK Implementation: Follow the integration guides.
- Policy Development: Review the capability registry for defining agent capabilities.
Examples
The repository includes various examples to help developers understand and implement the OAP specification:
- Passport Examples: See Template Passport and Instance Passport for agent identity and capabilities.
- Decision Examples: Review Allow Decision and Deny Decision for authorization decisions.
- Verifiable Credentials Examples: Find Passport and Decision as VCs to understand VC integration.
Links
Related repositories
Similar repositories that may be relevant next.
Atlas: Source Control for AI Coding Agents
September 17, 2026
Atlas is an innovative source control system designed specifically for AI coding agents. It allows developers to manage multiple agents, track their changes, and query their activities in a unified environment. Built in Rust, Atlas ensures that every agent's commit is linked to its session, providing full context including prompts and tool calls.
Goon: Autonomous AI Worker for Software Development and Custom Workflows
September 15, 2026
Goon is a self-hosted, autonomous AI worker designed to streamline software development and automate custom workflows. Built with Go and having zero dependencies, it operates as a daemon, capable of tasks from writing code and opening PRs to summarizing emails and monitoring logs. It learns from your context and asks for human approval before acting, ensuring controlled and intelligent automation.
cc-polymath: Context-Efficient Skills for Claude Code Development
September 10, 2026
cc-polymath is an innovative GitHub repository offering a vast collection of atomic skills and workflows specifically designed for Claude Code. It addresses the challenge of providing comprehensive development knowledge without overwhelming the AI's context window. By employing a progressive discovery system, cc-polymath ensures context efficiency and high-quality skill access across a wide range of technical domains.
karpathy-llm-wiki: Build a Karpathy-Style LLM Knowledge Base
September 9, 2026
karpathy-llm-wiki is an Agent Skills-compatible tool that implements Karpathy's LLM Wiki idea, allowing users to build a durable knowledge base. It enables LLMs to maintain structured wiki pages by ingesting sources, compiling knowledge, and answering questions with citations. This project offers a robust alternative to traditional RAG for compounding knowledge over time.
Source repository
Open the original repository on GitHub.