Curated list of open-source quantum software projects.

Private demand-response eligibility scoring under FHE. A utility can score households on encrypted smart-meter data without seeing usage.

OpenA2A organization profile

Security checklist and audit tools for MCP (Model Context Protocol) server deployments

Example A2A agent implementations with security best practices and input validation

GitHub Action that automatically adds and updates OpenA2A trust score badges in your README

GitHub Action: OpenA2A Registry trust gate for AI package dependencies

Agent Trust Protocol (ATP) — an open standard for verifiable trust assertions about AI agents

Agent Identity Protocol (AIP) — an open standard for AI agent identity, capabilities, and trust

AI Agent Kill Chain: A systematic framework for attacking and defending autonomous AI agent systems. The MITRE ATT&CK equivalent for AI agents.

Agent Behavioral Governance Specification (ABGS) - Behavioral safety framework for AI agents

AI Agent Threat Matrix: A structured framework for classifying, detecting, and defending against attacks on AI agent systems

On-device models that detect and classify AI agent attacks. A 2M-param classifier (<1ms, offline) and a 1.7B-param analyst, shipping inside HackMyAgent, Secretless, and the OpenA2A CLI.

VirusTotal for AI packages. ai-trust check <pkg> returns a 0-100 trust score from the OpenA2A Registry trust graph, covering security scans, advisories, and dependency risk. For MCP servers, A2A ag…

Production hardening guide for AI agents — prompt injection defense, tool sandboxing, and credential management

Guide to protecting API keys and credentials from AI agent exposure — .env safety, secret scanning, and Secretless AI

One scan for AI risk. `opena2a review` checks an AI project across credentials, shadow agents, MCP servers, and dependencies, returns a score, and routes each finding to the tool that fixes it. Ope…

Open Agent Security Benchmark - 222 attack scenarios, product-agnostic adapter interface, MITRE ATLAS mapped

One command to keep secrets out of AI (LLMs). Works with Claude Code, Cursor, Copilot, Windsurf, and any AI coding tool.

Agent Runtime Protection - runtime security monitoring for AI agents

A firewall for browser agents. Chrome extension that detects, monitors, and controls AI agents in your browser. Identifies Playwright, Puppeteer, Selenium, Anthropic Computer Use, and OpenAI Operat…

Cryptography as a service. Post-quantum ready (ML-KEM, ML-DSA), FIPS 140-2/3 compliant, context-driven encryption with zero-config SDKs. "Life is hard but cryptography doesn't have to be."

Damn Vulnerable AI Agent is a deliberately vulnerable AI agent platform for security testing and education.

Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.

Agent Identity Management (AIM) - Security management for autonomous AI agents and MCP servers

Cryptography as a service. Post-quantum ready (ML-KEM, ML-DSA), FIPS 140-2/3 compliant, context-driven encryption with zero-config SDKs. - "Life is hard but cryptography doesn't have to be"

TLS/SSL security analyzer for quantum readiness assessment and CNSA 2.0 compliance

Cryptographic Dependency Scanner - Identify quantum-vulnerable cryptographic algorithms in your software dependencies. Part of the QRAMM Toolkit.

Cryptographic Discovery Scanner - Find every cryptographic algorithm in your codebase and know your quantum risk - part of the QRAMM Toolkit by CSNP

The IAM layer for AI agents: cryptographic identity, capability authorization, and audit trails for non-human identities. Open source.